arXiv Computer Vision

Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding

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
arXiv AI
Aug 21

VISD: Enhancing Video Reasoning via Structured Self-Distillation

arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.

By Hao Lin, Kunyang Lv, Xu Jiang, Jingqi Tian, Zhongjing Du, Jiayu Ding, Qiaoman Zhang, Hongbo Jin
arXiv Computer Vision
Aug 27

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

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.

By Kaishen Wang, Dongdi Zhao, Yijun Liang, Dingqiang Ye, Ruibo Chen, Heng Huang, Di Fu
arXiv Computer Vision
Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim
arXiv Computation and Language
3d ago

On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data

arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...

By Hongyuan Zhang, Xianda Guo, Yanlun Peng, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, Ping Luo
arXiv Computer Vision
Aug 21

Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding

arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.

By Yanxiang Huang, Guohua Gao, Zhaoyang Wei
arXiv AI
Aug 25

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

VisionCoach is an input‑adaptive reinforcement learning framework that enhances spatio‑temporal grounding in video reasoning by using visual prompting during training. The system selectively applies visual prompts to challenging inputs, amplifying question‑relevant evidence and suppressing distractors, and then internalizes these improvements through self‑distillation so that inference can be performed on raw videos without prompts. Experiments on multiple benchmarks (V‑STAR, VideoMME, World‑Sense, VideoMMMU, PerceptionTest, and Charades‑STA) show that VisionCoach achieves state‑of‑the‑art performance while maintaining a single efficient inference pathway.

By Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal