In the last two months, RAGEN has powered Agent RL training frameworks for over 300,000 people. Now, we’re introducing VAGEN—the first open-source framework that trains *Visual* Agents using multi-turn Reinforcement Learning! 🚀(1/n)

Super excited to introduce VAGEN!! We trained a 3B VLM agent in Sokoban and it can sometimes solve 6-step game! Honored be part of the team!

🐇Introducing Alice, our most recent work on advancing weak-to-strong generalization! Instead of students passively absorbing what teachers feed them, Alice puts stronger student models in the driver's seat - it incentivizes student models to self-generate supervision based on

Thrilled to share my first project at NVIDIA! ✨ Today’s language models are pre-trained on vast and chaotic Internet texts, but these texts are unstructured and poorly understood. We propose CLIMB — Clustering-based Iterative Data Mixture Bootstrapping — a fully automated

“What is the answer of 1 + 1?” Large Reasoning Models (LRMs) may generate 1500+ tokens just to answer this trivial question. Too much thinking 🤯 Can LRMs be both Faster AND Stronger? Yes. Introducing LASER💥: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

🚨 #Alert Our recent work is accepted in #ICCV2025. 🎉 Huge thanks to our second author 💛 Byung-Kwan Lee (Byung-Kwan Lee), one of the best #KAIST colleagues I've ever seen, and our third author 💛 Jianshu Zhang (Jianshu Zhang), as well as amazing collaborations with #KAIST, #NAVER,

Welcome to check our latest paper! Fortunate to be the part of this awesome team.🫶

Excited to share our new survey on the reasoning paradigm shift from "Think with Text" to "Think with Image"! 🧠🖼️ Our work offers a roadmap for more powerful & aligned AI. 🚀 📜 Paper: arxiv.org/pdf/2506.23918 ⭐ GitHub (400+🌟): github.com/zhaochen0110/A…

🧠 How can AI evolve from statically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘢𝘣𝘰𝘶𝘵 𝘪𝘮𝘢𝘨𝘦𝘴 → dynamically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘪𝘮𝘢𝘨𝘦𝘴 as cognitive workspaces, similar to the human mental sketchpad? 🔍 What’s the 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗿𝗼𝗮𝗱𝗺𝗮𝗽 from tool-use → programmatic

Excited to witness a new breakthrough in linking cues across multi-image, which shows performance boost in our VLM2-Bench! 👍🏻 Welcome check this paper out as well as explore new approaches that can achieve higher performance in our VLM2-Bench!

Heading out to #ACL2025 in Vienna with six main/finding papers to present! 🇦🇹✈️🤩 Would love to chat about research on multimodal model reasoning and agent, as well as opportunities in my group HKUST NLP. Please DM if you'd like to meet!

HKUST NLP UIUC NLP ACL 2025 [1/n] "𝘔𝘢𝘵𝘤𝘩𝘪𝘯𝘨 𝘤𝘶𝘦𝘴 𝘧𝘰𝘳 𝘪𝘥𝘦𝘯𝘵𝘪𝘤𝘢𝘭 𝘰𝘣𝘫𝘦𝘤𝘵𝘴, 𝘥𝘪𝘴𝘵𝘪𝘯𝘤𝘵 𝘢𝘵𝘵𝘳𝘪𝘣𝘶𝘵𝘦𝘴 𝘧𝘰𝘳 𝘶𝘯𝘪𝘲𝘶𝘦 𝘰𝘯𝘦𝘴." Such 𝙘𝙧𝙤𝙨𝙨-𝙘𝙤𝙣𝙩𝙚𝙭𝙩 𝙫𝙞𝙨𝙪𝙖𝙡 𝙧𝙚𝙖𝙨𝙤𝙣𝙞𝙣𝙜 is extremely simple and straightforward for the human cognitive process,

Find us at the poster booth ✨Wed 7/30 11am Hall 4/5 ✨

Excited to speak at today's Agentic AI Summit! Happy to catch up if you also attend! 📍 Frontier Stage 📅4:50pm PT "Lightning Talks" Session 🔗Project website: agent-trust.camel-ai.org 🔗Slides: drive.google.com/file/d/1zC2hm0…

Can’t agree more…

Life update: Today marks the beginning of my PhD journey at Northwestern University! Excited for the road ahead. 🎓💜 #PhDlife #Northwestern

World Model Reasoning for VLM Agents (NeurIPS 2025, Score 5544) We release VAGEN to teach VLMs to build internal world models via visual state reasoning: - StateEstimation: what is the current state? - TransitionModeling: what is next? MDP → POMDP shift to handle the partial

🚀Excited to share our NeurIPS 2025 paper VAGEN, a scalable RL framework that trains VLM agents to reason as world models. VLM agents often act without tracking the world: they lose state, fail to anticipate effects, and RL wobbles under sparse, late rewards. Our solution is

I quite like the new DeepSeek-OCR paper. It's a good OCR model (maybe a bit worse than dots), and yes data collection etc., but anyway it doesn't matter. The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language