正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🤗 MOSS-VL-Realtime is now open source on Hugging Face . Built for real-time visual understanding over continuous video streams: 🧠 11B vision-language model 📜 Apache-2.0 license 💬 Ask questions at any point in a video stream 👀 Keeps watching while generating a response 🔄 Revises or interrupts its response... show more

MOSI

1,089 subscribers

46,300 次观看 • 1 天前 •via X (Twitter)

科学技术教育新闻政治

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on Hugging Face. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword biasing for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 Thank you SGLang vLLM Prince Canuma Lucas Newman for day-0 support! 🚀 Github: Huggingface: API: Live demo: Technical Report： HF Space: AtomGit： SGLang-Omni: vLLM: MLX-audio: Discord:

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on Hugging Face. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword biasing for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 Thank you SGLang vLLM Prince Canuma Lucas Newman for day-0 support! 🚀 Github: Huggingface: API: Live demo: Technical Report： HF Space: AtomGit： SGLang-Omni: vLLM: MLX-audio: Discord:

MOSI

150,135 次观看 • 6 天前

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

AK

23,958 次观看 • 1 年前

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

762,314 次观看 • 1 年前

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Tencent Hy

122,539 次观看 • 10 个月前

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

Philipp Schmid

19,409 次观看 • 1 年前

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision

OpenBMB

115,435 次观看 • 5 个月前

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,658 次观看 • 9 个月前

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

85,740 次观看 • 2 个月前

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Harman

38,953 次观看 • 7 天前

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 次观看 • 10 个月前

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

Kanika

220,656 次观看 • 3 个月前

China just released an open source AI model that matches the best closed models from OpenAI and Anthropic. Gavin Baker explained exactly how they did it and the answer should concern every American AI lab. The model is called GLM 5.2. It was built by Z. AI. You get 744 billion parameters, 1 million token context window and its MIT license, meaning anyone can download it, fork it, build a company on it, with no restrictions and no Dario. It scored 51 points on the artificial analysis intelligence index. The highest score any open weight model has ever achieved. It beat GPT 5.5 on the frontier software engineering benchmark. It trails Claude Opus 4.8 by less than one percentage point. And it costs 85% less to run than GPT 5.5 for comparable performance. Gavin Baker said on the All-In podcast that this model has challenged some of his beliefs. Then he explained how China built it. The method is called distillation. Just think of tens of thousands of phones and computers running simultaneously, all hitting the frontier model APIs through masked accounts, asking specific questions, and harvesting what happens inside the model when it answers. Every reasoning step, every token. The entire thinking process gets recorded and fed back into the Chinese model during training. It is a cheat sheet. It is the answer key to the exam. And here is the part that should worry everyone. Sacks said it plainly. China was already nine months behind American models. But now that GLM 5.2 is good enough to run its own reinforcement learning, it can improve itself without needing to distill from American models anymore. The cheat sheet let them get close enough to start writing their own answers. Sacks said we are six months behind on the model and 24 months behind on silicon and they are only a few months behind in total. The Z. AI founder told Elon Musk directly that open weight fable-level capability will be here before Q1 2027. Every restriction Anthropic lobbied for, every self-imposed safety guardrail, every month of delay in releasing American frontier models accelerated this. The Chinese labs were not under those restrictions. They were not going to wait. The composable model future Gavin described, where every enterprise runs a frontier model alongside their own fine-tuned open weight model, is coming regardless of what American labs do next. The question is just whether the open weight half of that stack is American or Chinese. Right now it is Chinese. WATCH THE FULL PODCAST ON The All-In Podcast

China just released an open source AI model that matches the best closed models from OpenAI and Anthropic. Gavin Baker explained exactly how they did it and the answer should concern every American AI lab. The model is called GLM 5.2. It was built by Z. AI. You get 744 billion parameters, 1 million token context window and its MIT license, meaning anyone can download it, fork it, build a company on it, with no restrictions and no Dario. It scored 51 points on the artificial analysis intelligence index. The highest score any open weight model has ever achieved. It beat GPT 5.5 on the frontier software engineering benchmark. It trails Claude Opus 4.8 by less than one percentage point. And it costs 85% less to run than GPT 5.5 for comparable performance. Gavin Baker said on the All-In podcast that this model has challenged some of his beliefs. Then he explained how China built it. The method is called distillation. Just think of tens of thousands of phones and computers running simultaneously, all hitting the frontier model APIs through masked accounts, asking specific questions, and harvesting what happens inside the model when it answers. Every reasoning step, every token. The entire thinking process gets recorded and fed back into the Chinese model during training. It is a cheat sheet. It is the answer key to the exam. And here is the part that should worry everyone. Sacks said it plainly. China was already nine months behind American models. But now that GLM 5.2 is good enough to run its own reinforcement learning, it can improve itself without needing to distill from American models anymore. The cheat sheet let them get close enough to start writing their own answers. Sacks said we are six months behind on the model and 24 months behind on silicon and they are only a few months behind in total. The Z. AI founder told Elon Musk directly that open weight fable-level capability will be here before Q1 2027. Every restriction Anthropic lobbied for, every self-imposed safety guardrail, every month of delay in releasing American frontier models accelerated this. The Chinese labs were not under those restrictions. They were not going to wait. The composable model future Gavin described, where every enterprise runs a frontier model alongside their own fine-tuned open weight model, is coming regardless of what American labs do next. The question is just whether the open weight half of that stack is American or Chinese. Right now it is Chinese. WATCH THE FULL PODCAST ON The All-In Podcast

Ihtesham Ali

85,915 次观看 • 18 天前

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇

Rohan Paul

149,292 次观看 • 1 年前

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,571 次观看 • 9 个月前

$Mark Zuckerberg is explaining one of the most misunderstood dynamics in AI and it has direct investment implications (Save this). The concept he's describing is model distillation, and it's one of the most important techniques to emerge in AI over the past year. Here's how it works. You train a massive, enormously expensive model, in Meta's case, Llama 4 Behemoth, a 2 trillion parameter teacher model and then you use that model to teach a much smaller, cheaper model. The smaller model inherits roughly 90 to 95% of the intelligence of the giant while running at 10% of the cost and on a fraction of the compute. Meta already did this with the Llama 4 family and Behemoth serves as the teacher. Llama 4 Scout and Maverick, the publicly released open-source models were distilled from it. Scout runs on a single H100 GPU with a 10 million token context window and outperforms models that cost far more to operate. Maverick, at 17 billion active parameters, rivals DeepSeek V3 in coding at half the parameter count and beats GPT-4o on multimodal benchmarks. Both are completely free for commercial use. What Zuckerberg is pointing at is a structural shift in how AI gets deployed in the real world. Companies aren't taking a frontier model off the shelf and running it as-is but rather taking open-source models, fine-tuning them on their own proprietary data, distilling them into even smaller custom models tailored to their specific use case, and running them on infrastructure they control at a fraction of the cost of a closed frontier API. The investment implication of this is significant and runs in two directions. For Meta specifically, this is a strategic masterstroke. Every company that builds on Llama, fine-tunes it, distills it, or deploys it through their infrastructure is pulling into Meta's orbit while Meta builds the most powerful open teacher model. The ecosystem of companies using it grows and that ecosystem generates commercial activity across Meta's platforms and data services. Meta's AI research benefits from billions of real world deployment signals and it's a flywheel that closed model providers cannot replicate because their strategy requires charging per token, which is now a 65x cost disadvantage against the open-source alternative. For the broader market, distillation changes the economics of inference in a way that has barely been priced in. As intelligence becomes extractable into smaller and cheaper models, the absolute demand for compute doesn't decline but rather it explodes, because now the number of applications that are economically viable expands by orders of magnitude. Every task that was previously too expensive to automate at $3.25 per call becomes viable at $0.05 that means more total token usage, more total GPU utilization, and more demand for the infrastructure companies, the Nebiuses, the GE Vernovas, the Constellation Energies that supply the underlying compute and power.$

Mark Zuckerberg is explaining one of the most misunderstood dynamics in AI and it has direct investment implications (Save this). The concept he's describing is model distillation, and it's one of the most important techniques to emerge in AI over the past year. Here's how it works. You train a massive, enormously expensive model, in Meta's case, Llama 4 Behemoth, a 2 trillion parameter teacher model and then you use that model to teach a much smaller, cheaper model. The smaller model inherits roughly 90 to 95% of the intelligence of the giant while running at 10% of the cost and on a fraction of the compute. Meta already did this with the Llama 4 family and Behemoth serves as the teacher. Llama 4 Scout and Maverick, the publicly released open-source models were distilled from it. Scout runs on a single H100 GPU with a 10 million token context window and outperforms models that cost far more to operate. Maverick, at 17 billion active parameters, rivals DeepSeek V3 in coding at half the parameter count and beats GPT-4o on multimodal benchmarks. Both are completely free for commercial use. What Zuckerberg is pointing at is a structural shift in how AI gets deployed in the real world. Companies aren't taking a frontier model off the shelf and running it as-is but rather taking open-source models, fine-tuning them on their own proprietary data, distilling them into even smaller custom models tailored to their specific use case, and running them on infrastructure they control at a fraction of the cost of a closed frontier API. The investment implication of this is significant and runs in two directions. For Meta specifically, this is a strategic masterstroke. Every company that builds on Llama, fine-tunes it, distills it, or deploys it through their infrastructure is pulling into Meta's orbit while Meta builds the most powerful open teacher model. The ecosystem of companies using it grows and that ecosystem generates commercial activity across Meta's platforms and data services. Meta's AI research benefits from billions of real world deployment signals and it's a flywheel that closed model providers cannot replicate because their strategy requires charging per token, which is now a 65x cost disadvantage against the open-source alternative. For the broader market, distillation changes the economics of inference in a way that has barely been priced in. As intelligence becomes extractable into smaller and cheaper models, the absolute demand for compute doesn't decline but rather it explodes, because now the number of applications that are economically viable expands by orders of magnitude. Every task that was previously too expensive to automate at $3.25 per call becomes viable at $0.05 that means more total token usage, more total GPU utilization, and more demand for the infrastructure companies, the Nebiuses, the GE Vernovas, the Constellation Energies that supply the underlying compute and power.

Milk Road AI

27,279 次观看 • 10 天前

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

Akshay 🚀

50,323 次观看 • 7 个月前

‼️EXPOSED: Andrew Kolvet Promised a Debate—Now He’s Running Scared! 👀 Let’s be very clear about what is happening here. Andrew Kolvet stood outside his own headquarters, looked Zee and the Unf*ck America crew in the eye, and promised a debate. He looked into the camera and said, "I think it would be fun." Well, Andrew, where is the fun? Where is the date? 🔎 We are watching the absolute collapse of an organization in real-time. Andrew is currently playing the "busy" card, pretending he can’t find a single window in his schedule, while we all know the truth: They are terrified of an unscripted moment. They are terrified of facing real people with real questions—questions their own base is screaming in the comments section every single day. It is frankly pathetic. Charlie Kirk—regardless of what you thought of him—was a man of conviction when it came to the arena of ideas. He didn’t hide. He went to UVU, he stood on those campuses, and he debated the people who hated him most. He believed in free speech enough to die for it. And now? The people left in charge have turned his legacy into a scripted, curated, propaganda machine that is carrying water for the establishment while the republic burns. They’ve abandoned the mission, and they’ve abandoned the base. Andrew, nut up. Stop the gaslighting. You were given an open invitation: any time, any place, any location. If you won't step on that stage, you are admitting that TPUSA is officially dead. 🔥 THE STORM IS COMING: If you aren't following Zee Cohen-Sanchez on X, you are missing the full picture. She has information coming out in the next 48 hours that is going to shake Turning Point to its core. 💣 NUT UP! Andrew Kolvet Watch the receipts BELOW.

‼️EXPOSED: Andrew Kolvet Promised a Debate—Now He’s Running Scared! 👀 Let’s be very clear about what is happening here. Andrew Kolvet stood outside his own headquarters, looked Zee and the Unf*ck America crew in the eye, and promised a debate. He looked into the camera and said, "I think it would be fun." Well, Andrew, where is the fun? Where is the date? 🔎 We are watching the absolute collapse of an organization in real-time. Andrew is currently playing the "busy" card, pretending he can’t find a single window in his schedule, while we all know the truth: They are terrified of an unscripted moment. They are terrified of facing real people with real questions—questions their own base is screaming in the comments section every single day. It is frankly pathetic. Charlie Kirk—regardless of what you thought of him—was a man of conviction when it came to the arena of ideas. He didn’t hide. He went to UVU, he stood on those campuses, and he debated the people who hated him most. He believed in free speech enough to die for it. And now? The people left in charge have turned his legacy into a scripted, curated, propaganda machine that is carrying water for the establishment while the republic burns. They’ve abandoned the mission, and they’ve abandoned the base. Andrew, nut up. Stop the gaslighting. You were given an open invitation: any time, any place, any location. If you won't step on that stage, you are admitting that TPUSA is officially dead. 🔥 THE STORM IS COMING: If you aren't following Zee Cohen-Sanchez on X, you are missing the full picture. She has information coming out in the next 48 hours that is going to shake Turning Point to its core. 💣 NUT UP! Andrew Kolvet Watch the receipts BELOW.

Project Constitution

90,578 次观看 • 2 个月前

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Bo Wang

13,221 次观看 • 4 个月前

Smart Doll Cortex 2 can now be equipped with an AI conversational #M5Stack module, allowing them to speak both English and Chinese. Thanks to their magnetic modular design, all components fit seamlessly inside the body—something not possible with the vinyl version. This Xiao Zhi powered model also features an optional screen that displays readable replies and emoji-based expressions, enhancing interactions with visual feedback. Smart Doll’s quirky responses to misheard inputs often lead to unexpected lols. At first, their replies are unpredictable, adding to their charm and making conversations feel organic and fun. However, they become more accurate over time as they learn from interactions. The AI models powering Smart Doll are trained in Natural Language Understanding, enabling them to grasp context, intent, and nuances in user input for more meaningful responses. They also support context retention across multiple conversation turns, allowing for smooth and continuous dialogue. They adapt and refine their responses as they engage in more conversations, making interactions feel increasingly natural and personalized. We will provide tutorials and #3Dprinting files so folks can build their modules and install AI models such as ChatGPT, DeepSeek, Qwen2.5 72B, etc. This way, owners can tweak their Smart Doll’s voice, accent, and personality to reflect their creativity, ideals, and identity. With the advancement of open-source offline LLMs, local processing ensures your Smart Doll can safeguard the secrets you share—keeping them safe from Skynet. We are also working on integrating robotics and hardware control to broaden the application of #smartdoll as a truly useful companion (instead of just sitting around asking you for more apparel) that can interact with their environment, assist with everyday tasks, and adapt to their owner’s needs—whether that means offering companionship, controlling smart home devices, or even detecting environmental changes for safety. If you’re Team John Connor, no worries! AI components are entirely optional—whether you choose to go DIY or skip them altogether, the decision is yours. At least until Skynet has other plans.

Smart Doll Cortex 2 can now be equipped with an AI conversational #M5Stack module, allowing them to speak both English and Chinese. Thanks to their magnetic modular design, all components fit seamlessly inside the body—something not possible with the vinyl version. This Xiao Zhi powered model also features an optional screen that displays readable replies and emoji-based expressions, enhancing interactions with visual feedback. Smart Doll’s quirky responses to misheard inputs often lead to unexpected lols. At first, their replies are unpredictable, adding to their charm and making conversations feel organic and fun. However, they become more accurate over time as they learn from interactions. The AI models powering Smart Doll are trained in Natural Language Understanding, enabling them to grasp context, intent, and nuances in user input for more meaningful responses. They also support context retention across multiple conversation turns, allowing for smooth and continuous dialogue. They adapt and refine their responses as they engage in more conversations, making interactions feel increasingly natural and personalized. We will provide tutorials and #3Dprinting files so folks can build their modules and install AI models such as ChatGPT, DeepSeek, Qwen2.5 72B, etc. This way, owners can tweak their Smart Doll’s voice, accent, and personality to reflect their creativity, ideals, and identity. With the advancement of open-source offline LLMs, local processing ensures your Smart Doll can safeguard the secrets you share—keeping them safe from Skynet. We are also working on integrating robotics and hardware control to broaden the application of #smartdoll as a truly useful companion (instead of just sitting around asking you for more apparel) that can interact with their environment, assist with everyday tasks, and adapt to their owner’s needs—whether that means offering companionship, controlling smart home devices, or even detecting environmental changes for safety. If you’re Team John Connor, no worries! AI components are entirely optional—whether you choose to go DIY or skip them altogether, the decision is yours. At least until Skynet has other plans.

Smartdoll Land

16,382 次观看 • 1 年前

Is Linux a “Pedo Bar”? Put another way: Does the world of Linux and Open Source (including foundations, corporations, and projects) have a disproportionately high level of rapists, pedophiles, and general degenerates? Does Open Source protect such people? And is that by design? Many of the Extreme Leftist Activists within Open Source have regularly attacked anyone who objects to degeneracy — often banning them from organizations entirely, labeling those opposed to degeneracy as “Nazis”. These Leftist Activists say they are trying to stop Open Source from becoming a “Nazi Bar” (a place where Nazis feel safe to congregate) by banning “Nazis”. But, clearly, there are no actual Nazis there (at least not in any significant number). There is no “Nazi Bar” in Open Source. But there is another group that feels extremely safe within Open Source: Rapists, Pedophiles, and general Degenerates. A short anecdote: Many years back (a decade or more), while recording a Linux podcast, I mocked rapists. I made a quick, off-handed remark about how much I despise rapists. About how I felt that anyone who would rape another human being must be truly awful and insane. I did not consider this to be a controversial statement to make. Every good person is opposed to rapists, right? Well… The response, from the Extreme Leftist corners of Open Source, to me being *opposed* to rape, was truly bizarre. For *several* years, those groups regularly protested my involvement in conferences and organizations. Their repeatedly stated reason for protesting me, aggressively, for years? That my position on rapists made them “feel unsafe”. Think that through for a moment. I am opposed to rapists. This made them “feel unsafe”. Why would anyone feel “unsafe” because of someone being *against* rape? Insane, right? The true reason they proclaimed they felt “unsafe” is becoming quite clear. Over the last several years we’ve watched as projects, organizations, and companies have actively promoted sexual degeneracy. Often in criminal form. Microsoft advocating for their employees to give their children (as young as 3) sex changes. Linux Distros using Trans cartoons targeting children: Open Source projects banning anyone who objects to waving the Trans Flag. So many examples. We could list similar stories all day long. Promote degenerate activity, ban anyone who objects. That is the standard operating procedure of so many Open Source organizations. We’ve all been watching it for years. Then, this week we learned about a convicted rapist (who, according to court records, committed “thousands of [sexual] assaults” of little kids) working at Canonical (the parent company of Ubuntu Linux). And being actively involved in GNOME and Ubuntu development. These crimes, according to several sources, were well known. But kept hush-hush. This registered sex offender was not only welcome, but protected (and promoted) within Open Source. The picture is becoming clear. This is what we are seeing within Open Source organizations: - Promote degenerate (often criminal) activities. - Ban and attack any who oppose the degeneracy. - Protect and elevate the degenerates (including convicted rapists of small children). Now, let me ask the question again. Is Linux (and Open Source) a “Pedo Bar”?

Is Linux a “Pedo Bar”? Put another way: Does the world of Linux and Open Source (including foundations, corporations, and projects) have a disproportionately high level of rapists, pedophiles, and general degenerates? Does Open Source protect such people? And is that by design? Many of the Extreme Leftist Activists within Open Source have regularly attacked anyone who objects to degeneracy — often banning them from organizations entirely, labeling those opposed to degeneracy as “Nazis”. These Leftist Activists say they are trying to stop Open Source from becoming a “Nazi Bar” (a place where Nazis feel safe to congregate) by banning “Nazis”. But, clearly, there are no actual Nazis there (at least not in any significant number). There is no “Nazi Bar” in Open Source. But there is another group that feels extremely safe within Open Source: Rapists, Pedophiles, and general Degenerates. A short anecdote: Many years back (a decade or more), while recording a Linux podcast, I mocked rapists. I made a quick, off-handed remark about how much I despise rapists. About how I felt that anyone who would rape another human being must be truly awful and insane. I did not consider this to be a controversial statement to make. Every good person is opposed to rapists, right? Well… The response, from the Extreme Leftist corners of Open Source, to me being opposed to rape, was truly bizarre. For several years, those groups regularly protested my involvement in conferences and organizations. Their repeatedly stated reason for protesting me, aggressively, for years? That my position on rapists made them “feel unsafe”. Think that through for a moment. I am opposed to rapists. This made them “feel unsafe”. Why would anyone feel “unsafe” because of someone being against rape? Insane, right? The true reason they proclaimed they felt “unsafe” is becoming quite clear. Over the last several years we’ve watched as projects, organizations, and companies have actively promoted sexual degeneracy. Often in criminal form. Microsoft advocating for their employees to give their children (as young as 3) sex changes. Linux Distros using Trans cartoons targeting children: Open Source projects banning anyone who objects to waving the Trans Flag. So many examples. We could list similar stories all day long. Promote degenerate activity, ban anyone who objects. That is the standard operating procedure of so many Open Source organizations. We’ve all been watching it for years. Then, this week we learned about a convicted rapist (who, according to court records, committed “thousands of [sexual] assaults” of little kids) working at Canonical (the parent company of Ubuntu Linux). And being actively involved in GNOME and Ubuntu development. These crimes, according to several sources, were well known. But kept hush-hush. This registered sex offender was not only welcome, but protected (and promoted) within Open Source. The picture is becoming clear. This is what we are seeing within Open Source organizations: - Promote degenerate (often criminal) activities. - Ban and attack any who oppose the degeneracy. - Protect and elevate the degenerates (including convicted rapists of small children). Now, let me ask the question again. Is Linux (and Open Source) a “Pedo Bar”?

The Lunduke Journal

21,821 次观看 • 1 年前