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。

Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks. Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low... show more

👋 Jan

13,077 subscribers

130,234 次观看 • 8 个月前 •via X (Twitter)

教育科学技术财经

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

Introducing a brand new way to use Jan 💛 You can now search the web, do deep research, and let Jan use your browser. Powered by Jan-v2-VL-Max, 30B model beating Gemini 2.5 Pro & DeepSeek R1 on execution benchmarks. Try it:

👋 Jan

29,403 次观看 • 6 个月前

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

👋 Jan

23,063 次观看 • 6 个月前

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

👋 Jan

690,311 次观看 • 11 个月前

Today we’re introducing Scribe v2: the most accurate transcription model ever released. While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.

Today we’re introducing Scribe v2: the most accurate transcription model ever released. While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.

ElevenLabs

556,841 次观看 • 6 个月前

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

👋 Jan

17,759 次观看 • 10 个月前

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: To run it locally: - Install Jan Beta: - Download Jan-nano in Jan Hub - Settings -> MCP, enable MCP and add your Serper API key for web tools Full technical report will be published shortly.

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: To run it locally: - Install Jan Beta: - Download Jan-nano in Jan Hub - Settings -> MCP, enable MCP and add your Serper API key for web tools Full technical report will be published shortly.

Menlo Research

56,600 次观看 • 1 年前

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 次观看 • 8 个月前

Introducing Jan-Code-4B 💻 A compact coding model tuned for practical day-to-day tasks. Generation, refactors, debugging, tests — all runnable locally in Jan. Download Jan: Model:

Introducing Jan-Code-4B 💻 A compact coding model tuned for practical day-to-day tasks. Generation, refactors, debugging, tests — all runnable locally in Jan. Download Jan: Model:

👋 Jan

109,873 次观看 • 4 个月前

Thank you to everyone who has played The Alters and to 11 bit studios | NEW GAME REVEALED for letting me be part of The Alters | MAJOR UPDATE OUT NOW🐑 love from, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, and Jan. #TheAlters

Thank you to everyone who has played The Alters and to 11 bit studios | NEW GAME REVEALED for letting me be part of The Alters | MAJOR UPDATE OUT NOW🐑 love from, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, and Jan. #TheAlters

Alex Jordan

63,640 次观看 • 1 年前

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

👋 Jan

40,181 次观看 • 8 个月前

Alibaba engineer who leads Qwen explained the future of open agent models in 25 minutes - better than $2000 LLM training courses. pre-train the base ->SFT -> RLHF -> tool use -> multi-modal -> ship a whole family (chat / VL / coder / math / QwQ). That loop is why Qwen quietly became the most downloaded open model family on Hugging Face. Qwen base + Qwen-VL + Qwen-Coder + QwQ reasoning - that's the stack. Watch and save it, then read the article below.

Alibaba engineer who leads Qwen explained the future of open agent models in 25 minutes - better than $2000 LLM training courses. pre-train the base ->SFT -> RLHF -> tool use -> multi-modal -> ship a whole family (chat / VL / coder / math / QwQ). That loop is why Qwen quietly became the most downloaded open model family on Hugging Face. Qwen base + Qwen-VL + Qwen-Coder + QwQ reasoning - that's the stack. Watch and save it, then read the article below.

h100envy

112,785 次观看 • 9 天前

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 次观看 • 7 个月前

Running Qwen2 VL 72B 4bit 🇨🇳 quantized model on Mac Mini M4 Pro 64GB. It works very well and delivers good accuracy, suitable for practical use cases. Integrating MLX and MLX-VLM backend into Sparrow as main solution for local inference and data extraction. Kudos to Prince Canuma for porting Qwen2 VL to MLX.

Running Qwen2 VL 72B 4bit 🇨🇳 quantized model on Mac Mini M4 Pro 64GB. It works very well and delivers good accuracy, suitable for practical use cases. Integrating MLX and MLX-VLM backend into Sparrow as main solution for local inference and data extraction. Kudos to Prince Canuma for porting Qwen2 VL to MLX.

Andrej Baranovskij

13,742 次观看 • 1 年前

Oh wow…ElevenLabs just dropped the most accurate transcription model ever. - v2 Realtime: built for agents, ultra low latency - v2 Batch: built for scale, subtitling, captioning Transcription just got solved 🤯

Oh wow…ElevenLabs just dropped the most accurate transcription model ever. - v2 Realtime: built for agents, ultra low latency - v2 Batch: built for scale, subtitling, captioning Transcription just got solved 🤯

Alvaro Cintas

156,082 次观看 • 6 个月前

LFM2-VL support with GGUF and llama.cpp 🥳 You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on Hugging Face

LFM2-VL support with GGUF and llama.cpp 🥳 You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on Hugging Face

Maxime Labonne

19,947 次观看 • 10 个月前

We are recruiting beta testers for Sela Agent. Apply: Recruitment: Jan 7 to Jan 11 Test period: Jan 12 to Jan 30 Selected testers will receive the Sela Pioneer role in Discord. Details and requirements:

We are recruiting beta testers for Sela Agent. Apply: Recruitment: Jan 7 to Jan 11 Test period: Jan 12 to Jan 30 Selected testers will receive the Sela Pioneer role in Discord. Details and requirements:

Selanet

12,848 次观看 • 6 个月前

No Claude plan? You can still use Claude Code. Connect it to Jan and run local models on your own machine. That means no subscription and no token caps. Download Jan v0.7.7 at

No Claude plan? You can still use Claude Code. Connect it to Jan and run local models on your own machine. That means no subscription and no token caps. Download Jan v0.7.7 at

👋 Jan

250,560 次观看 • 4 个月前

⚫️⚪️BounceBit V2 - 悟 Bodhi CeDeFi V2 & BounceClub V2 V2 rethinks the structure of the current model and will upgrade #BTCfi as we know it. ⚫️additional $BB utility ⚪️CeDeFi SaaS ♣️AI agents and more... This September 2024, details below.

⚫️⚪️BounceBit V2 - 悟 Bodhi CeDeFi V2 & BounceClub V2 V2 rethinks the structure of the current model and will upgrade #BTCfi as we know it. ⚫️additional $BB utility ⚪️CeDeFi SaaS ♣️AI agents and more... This September 2024, details below.

BounceBit

129,629 次观看 • 1 年前

#VibeCoding with MiMo-V2-Flash just leveled up 🌊 ⚡️ What's new: → "Thinking" mode support for Claude Code, Kilo , and Cline → Better stability and smoother experience across all scenarios 🆓 Free API access until Jan 20, 2026 Give it a spin and share your feedback!

#VibeCoding with MiMo-V2-Flash just leveled up 🌊 ⚡️ What's new: → "Thinking" mode support for Claude Code, Kilo , and Cline → Better stability and smoother experience across all scenarios 🆓 Free API access until Jan 20, 2026 Give it a spin and share your feedback!

Xiaomi MiMo

28,829 次观看 • 5 个月前

8 years in the making, it’s finally here. The perfect DeFi swap engine. Introducing Ultra v2 With key innovations like RTSE v2, Dynamic Execution, MEV Protect, JupShield, and Gasless Support, Ultra v2 removes all pain points to deliver an entirely new trading experience 👇

8 years in the making, it’s finally here. The perfect DeFi swap engine. Introducing Ultra v2 With key innovations like RTSE v2, Dynamic Execution, MEV Protect, JupShield, and Gasless Support, Ultra v2 removes all pain points to deliver an entirely new trading experience 👇

Jupiter

614,464 次观看 • 1 年前