Introducing DeepConf: Deep Think with Confidence 🚀 First method... to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens. It also delivers many strong advantages for parallel thinking: 🔥 Performance boost: ~10% accuracy across models & datasets ⚡ Ultra-efficient: Up to 85% fewer tokens generated 🔧 Plug & play: Works with ANY existing model - zero training needed (no hyperparameter tuning as well!) ⭐ Easy to deploy: Just ~50 lines of code in vLLM (see PR below) 📚 Paper: 🌐 Project: joint work with: Yichao Fu , xuewei_wang, Yuandong Tian (see details in the comments below)show more

🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation... acceleration with semantic-aware sparse attention! 🏆Spotlight paper accepted by #NeurIPS2025 ✅ Training-free & plug-and-play ✅ Up to 2.5× faster on HunyuanVideo, 1.9× faster on Wan 2.1 ✅ SOTA quality preserved (no artifacts, no flickering, no distortion) 📚Paper: 💻Code: 🌐Website: ⚡Attention Kernel: Joint work with: @randwalk0 Yilong Zhao Muyang Li Jintao Zhang Han Cai Yujun Lin Xiuyu Li Chenfeng_X Kelly Peng Jianfei Chen Song Han Kurt Keutzer Ion Stoica See details below ⬇️ (1/6) NeurIPS Conference #NeurIPS #VideoGeneration #GenerativeAI #MachineLearning #EfficientAI #OpenSourceshow more

🍌 Just released NanoBanana Pro LoRA Dataset Generator with... fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:show more

You can now vibe code a 3D website using... this open source model. - Totally free - Runs even locally - Works with any image This workflow is compatible with all tools (Replit, Lovable, Claude Code, etc.) Quick steps below:show more

Introducing Dexter. An open source financial agent in ~200... lines of code. Think: Claude Code, but for finance. What Dexter does today: • plans tasks • runs on its own • validates its work • researches stocks It’s built with OSS tools like for managing LLMs, prompts, outputs, etc. No coding experience needed to run. Goal: build the best financial agent and share every line of code along the way. Next: evals, starting withshow more

vLLM + open-webui running gpt-oss-120b on a tinybox green... v2 Just `vllm serve openai/gpt-oss-120b --tensor-parallel-size 4 --async-scheduling` and you have a local OpenAI API you can trust.show more

GPT-5.5 in Codex is a delight to work with:... - Super sharp with responses - It understands intent better than any model - Great "personality" - Gets lots of stuff done without pausing unnecessarily It generated this beautiful artifact design. Huge win for OpenAI.show more

Ready to upscale your mobile game development without losing... performance? 👉 Say hello to Arm Accuracy Super Resolution It's our open source solution derived from FSR2, designed to increase the resolution of images from low to high with our efficient shader code:show more

📢📢📢Introducing xGen-MM-Vid (BLIP-3-Video)! This highly efficient multimodal language model... is laser-focused on video understanding. Compared to other models, xGen-MM-Vid represents a video with a fraction of the visual tokens (e.g., 32 vs. 4608 tokens). Paper: Website: Researcher’s 🧵:👇show more

China is literally on 🔥 Baidu from China has... launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.show more

Vibe coded this RPG game with Three.js this weekend.... Took 10+ hours using sonnet 3.7. Graphics generated using stable diffusion. Optimized with grok and gpt 4.5. Zero code edit, just let AI cook. Details 👇show more

Working with multiple models in Chat? The model picker... in VS Code is now organized by provider, making it easier to browse, search, and switch between models. You'll also see provider names next to your recent models for quicker recognition. 💡 Tip: Use /models for quick access.show more

LongWriter Unleashing 10,000+ Word Generation from Long Context LLMs... discuss: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability.show more

Robot Utility Models (RUMs) enable basic tasks – door... opening, drawer opening, object reorientation, etc. – at ~90% accuracy without ANY finetuning (i.e. zero-shot) in unseen new environments. Fully open source!!! models, data, code & hw. We think this is super exciting, why?👇 1. Unlocks many practical home utility tasks that often involve these basic tasks as part of an action chain. “Go get me a fork” involves opening the kitchen door and then opening the cutlery drawer. 2. This works well **zero-shot in unseen and new** environments, which is practically a huge deal. Turn the robot on, and get going. 3. The recipe for building a new model is fairly generic, and we think with a bit more refinement this can be a general recipe to build many more Utility models. More details and access 👇show more

🚀 What if physical AI policies could interact with... generated worlds in real time? Introducing OmniDreams, a generative world model for closed-loop autonomous vehicle simulation. Tech report, code, models, and data samples are available now. Project: Code: Model: Join the #omnidreams discord channel:show more

Here's a fun one with Seedance 2.0 You can... just tell the model to end with the first frame, so you can create looping videos without using first/last frames, a feature especially helpful when using the Omni variant of SD2. Generated in CapCut with early access. Prompt below (it's a big one):show more

Introducing Dexter 2.0 Open source. Built for financial research.... Like Claude Code, but for stocks. What Dexter does: • plans tasks • runs on its own • validates its work • researches stocks It uses OSS tools like , with a fresh stack of typescript, react, ink, and bun. Fast to build. Easy to use. No coding required. My favorite project of the year.show more

We’re thrilled to launch GPT-OSS—the 120B-parameter open-source LLM—on Phala... Cloud! 🚀 🔒 Run the fully OSS model inside a secure TEE for end-to-end confidential AI. Explore the build 👉show more

We built a better alternative to json-render & A2UI... Up to 3x faster rendering & 67% fewer tokens. Far fewer broken outputs. We've been shipping Generative UI interfaces to 10,000+ developers for the past year. We know where JSON-based rendering breaks in production. So we built a new format - one that works with how models actually generate, not against it. And today we're open sourcing it: openui [dot] comshow more