Latest Papers

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Taming LLMs by Scaling Learning Rates with Gradient Grouping

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

HardTests: Synthesizing High-Quality Test Cases for LLM Coding

Large Language Models for Data Synthesis

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time