6 papers
DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training
Haisen Luo, Yiwei Liu, Haoning Wang +13
Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distilla…
VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
Shihao Wang, Guo Chen, De-an Huang +6
While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative fram…
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Xiaoyu Tian, Haotian Wang, Shuaiting Chen +12
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing meth…
SIMA 2: A Generalist Embodied Agent for Virtual Worlds
SIMA team, Adrian Bolton, Alexander Lerchner +63
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a signifi…
Seeing before Observable: Potential Risk Reasoning in Autonomous Driving via Vision Language Models
Jiaxin Liu, Xiangyu Yan, Liang Peng +11
Ensuring safety remains a key challenge for autonomous vehicles (AVs), especially in rare and complex scenarios. One critical but understudied aspect is the \textbf{potential risk}…
Adaptive Tool Generation with Models as Tools and Reinforcement Learning
Chenpeng Wang, Xiaojie Cheng, Chunye Wang +2
Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deplo…