← Back to all news
arXiv Computer Vision By Kaishen Wang, Dongdi Zhao, Yijun Liang, Dingqiang Ye, Ruibo Chen, Heng Huang, Di Fu

Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding

Read the original on arXiv Computer Vision →

The paper introduces Clue-OPSD, a clue‑privileged on‑policy self‑distillation framework that improves long‑video understanding by focusing on short, question‑relevant clue intervals rather than the entire video. Experiments on multiple benchmarks and Qwen3.5 model scales show that this approach consistently outperforms standard backbone models and competes strongly with supervised post‑training baselines, all while requiring fewer input frames and no additional inference modules.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 28

Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models

Video-OPSD introduces a post‑training framework for Video Large Language Models that leverages privileged visual evidence to enhance on‑policy self‑distillation. The method constructs a self‑teacher conditioned only on annotated evidence frames, while the student processes the full video, allowing the teacher to provide more focused supervision. Additionally, an evidence‑guided token optimization scheme weights distillation based on each token’s reliance on privileged evidence, improving perceptually grounded reasoning. Experiments demonstrate consistent gains over standard OPSD and comparable performance to GRPO with less training time.

By Ziyue Wang, Shiqi Huang, Weiwen Xu, Bihan Wen, Xudong Jiang
llmsefficiencybenchmarks
More like this →
arXiv Machine Learning
Jul 7

Incentivizing Vision Language Models to Search for Long Video Question Answering

arXiv:2607. 02959v1 Announce Type: cross Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process.

By Harsh Goel, S P Sharan, Sahil Shah, Minkyu Choi, Joungbin An, Kristen Grauman, Sandeep P. Chinchali
llmsagentsnlpreinforcement-learningbenchmarks
More like this →