5 papers
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
Yang Tian, Rui Wang, Xumeng Wen +5
Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide lim…
Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability
Yang Tian, Zhengpeng Shi, Yu Zhou +1
Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover co…
TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
Xiangrui Liu, Minghao Qin, Yan Shu +5
Identifying key temporal intervals within long videos, known as temporal grounding (TG), is important to video understanding and reasoning tasks. In this paper, we introduce a new…
MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers
Yang Tian, Zheng Lu, Mingqi Gao +2
Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sour…
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
Xiangrui Liu, Yan Shu, Zheng Liu +3
Despite advanced token compression techniques, existing multimodal large language models (MLLMs) still struggle with hour-long video understanding. In this work, we propose Video-X…