Video-OPD uses on-policy distillation from a frontier teacher to turn sparse episode rewards into dense step-wise signals for more efficient post-training of MLLMs on temporal video grounding.
Tempo-r0: A video-mllm for temporal video grounding through efficient temporal sensing reinforcement learning.arXiv preprint arXiv:2507.04702, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MLLMs know event timing during prefill via sparse Temporal Grounding Heads but lose it in autoregressive decoding; restricting visual context to the high-attention interval at inference time improves VTG performance on three benchmarks.
citing papers explorer
-
Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
Video-OPD uses on-policy distillation from a frontier teacher to turn sparse episode rewards into dense step-wise signals for more efficient post-training of MLLMs on temporal video grounding.
-
MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
MLLMs know event timing during prefill via sparse Temporal Grounding Heads but lose it in autoregressive decoding; restricting visual context to the high-attention interval at inference time improves VTG performance on three benchmarks.