11 papers
GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
Zihao Lin, Haibo Wang, Zhiyang Xu +7
Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos whil…
IR: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +3
Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without ge…
Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +2
Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores w…
How Do Large Language Models Learn Concepts During Continual Pre-Training?
Barry Menglong Yao, Sha Li, Yunzhi Yao +4
Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large lan…
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
Mohammad Beigi, Ying Shen, Parshin Shojaee +5
Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or re…
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Haibo Wang, Zhiyang Xu, Yu Cheng +6
Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal groundin…