🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

With the success of LLM agents like OpenAI Operator, we are entering a new scaling era, but how do we train these agent models? We present InSTA, the largest training environment for LLM agents, containing live web navigation tasks for 150k diverse websites in multiple

Think your LLM loves endless pre-training? 🚨 Think again! Plot twist ahead! 🎢 While it (obviously) gives better base models, it might not necessarily give a better starting point for all the fancy post-training we do these days (instruction FT, multimodal FT, etc.). 👀

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free

Introducing DeepCoder-14B-Preview - our fully open-sourced reasoning model reaching o1 and o3-mini level on coding and math. The best part is, we’re releasing everything: not just the model, but the dataset, code, and training recipe—so you can train it yourself!🔥 Links below:

🌏 Building web-scale agents, and tired of Math and Coding tasks? Come chat with us at ICLR in Singapore. We are presenting InSTA at the DATA-FM workshop in the second Oral session, April 28th 2:30pm. InSTA is the largest environment for training agents, spanning 150k live

When we train models to do QA, are we robustly improving context dependency? No! In our ICLR Oral (Fri 11 AM), we show that if the base model knows the facts already, it shortcuts and learns to ignore the context completely! Visit us to learn more about knowledge conflicts 😀

Excited for Sachin and Christina's talk tomorrow, a surprising result with major implications for VLM training!

Join me & @hbxnov at #ICLR2025 for our very purple poster on risks of LLM evals by private companies! 🕒 Today, 10am | 🪧 #219 Beyond Llama drama, LMSYS incorporation & ARC-AGI train/test fiasco, we discuss irreducible biases—even when firms act in good faith. Come say hi! 💜

Building LLM Agents? Come to my talk at the #ICLR DATA-FM workshop today at 2:30pm, Hall 4, Section 4. I'll be presenting InSTA, our work building the largest environment for agents on the live internet. arxiv.org/abs/2502.06776 #Agents #LLM

Starting in 15 min!

It was challenging to organize the workshop as the sole in-person organizer, and I’m deeply grateful to everyone for their incredible support in making it a great success. Danqi Chen Peter Henderson Kyle Lo Vahab Mirrokni Bryan Kian Hsiang Low Xinran Gu Brandon Trabucco Zheng Xu, Edward Yeo,

30+ years of Media Lab students, alumni, and postdocs at CHI 2025 in Yokohama! Photo courtesy of Professor Pattie Maes. #chi2025

They’re here. 🔥 Inception’s diffusion LLMs — lightning fast, state-of-the-art, and now public. Go build the future → platform.inceptionlabs.ai #GenAI #dLLMs #diffusion

Qwen3 models are fantastic. Its impressive that Alibaba built a frontier-class LLM in such a short time.

𝘏𝘶𝘮𝘢𝘯𝘴 𝘵𝘩𝘪𝘯𝘬 𝘧𝘭𝘶𝘪𝘥𝘭𝘺—𝘯𝘢𝘷𝘪𝘨𝘢𝘵𝘪𝘯𝘨 𝘢𝘣𝘴𝘵𝘳𝘢𝘤𝘵 𝘤𝘰𝘯𝘤𝘦𝘱𝘵𝘴 𝘦𝘧𝘧𝘰𝘳𝘵𝘭𝘦𝘴𝘴𝘭𝘺, 𝘧𝘳𝘦𝘦 𝘧𝘳𝘰𝘮 𝘳𝘪𝘨𝘪𝘥 𝘭𝘪𝘯𝘨𝘶𝘪𝘴𝘵𝘪𝘤 𝘣𝘰𝘶𝘯𝘥𝘢𝘳𝘪𝘦𝘴. But current reasoning models remain constrained by discrete tokens, limiting their full

Dear MAGA friends, I have been worrying about STEM in the US a lot, because right now the Senate is writing new laws that cut 75% of the STEM budget in the US. Sorry for the long post, but the issue is really important, and I want to share what I know about it. The entire

🚨Self-Challenging Language Model Agents🚨 📝: arxiv.org/abs/2506.01716 A new paradigm to train LLM agents to use different tools with challenging self-generated data ONLY: Self-challenging agents (SCA) both propose new tasks and solve them, using self-generated verifiers to

Upon graduation, I paused to reflect on what my PhD had truly taught me. Was it just how to write papers, respond to brutal reviewer comments, and survive without much sleep? Or did it leave a deeper imprint on me — beyond the metrics and milestones? Turns out, it did. A

Say ahoy to 𝚂𝙰𝙸𝙻𝙾𝚁⛵: a new paradigm of *learning to search* from demonstrations, enabling test-time reasoning about how to recover from mistakes w/o any additional human feedback! 𝚂𝙰𝙸𝙻𝙾𝚁 ⛵ out-performs Diffusion Policies trained via behavioral cloning on 5-10x data!