4 papers
Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning
Ziheng Huang, Yicheng Bao, Xueheng Li +8
Streaming video assistance requires models to answer asynchronous questions from an observed prefix under a fixed context budget. Existing approaches model response timing or compr…
Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them
Yicheng Bao, Zhenkun Gao, Xiahui Guo +7
Historical photographs and other canonical images can now be edited seamlessly with a single instruction, often leaving no reliable pixel-level trace. In such cases, the only evide…
VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
Zhenkun Gao, Yicheng Bao, Jinlong Peng +13
Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR). However, existing multimo…
Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
Sen Wang, Bangwei Liu, Zhenkun Gao +4
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only…