DTP-OPSD: Reinforcement Learning with Distractor-Aware Temporal-Privilege On-Policy Self-Distillation for Temporal Video Grounding

arXiv:2611.00120v1 Announce Type: new Abstract: Temporal Video Grounding (TVG) aims to localize the start and end times of an event described by a language query in a video. The task becomes particularly challenging when the same video contains multiple repeated, similar, or opposite events. On these hard examples, all responses sampled by Group Relative Policy Optimization (GRPO) may miss the target and receive zero temporal Intersection-over-Union (tIoU). Their group-relative advantages are then all zero, leaving no useful policy gradient signal. To address this, we propose DTP-OPSD, a reinforcement learning framework with distractor-aware temporal-privilege on-policy self-distillation. The student observes the clean video and generates responses on-policy, while a shared-weight teacher observes a privileged video in which the target window is marked by red full-frame borders and same-video distractor windows by blue full-frame borders. For the distillation loss, the teacher evaluates student-generated prefixes and provides dense token-level Jensen-Shannon divergence supervision. This supervision…