arXiv Computer Vision August 28, 2026 By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim

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

Read the original on arXiv Computer Vision →

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.

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.

arXiv Computer Vision

1d ago

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

arXiv:2608.27065v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has recently emerged as an effective post-training paradigm that improves policy optimization through dense token-le...

By Ziyue Wang, Shiqi Huang, Weiwen Xu, Bihan Wen, Xudong Jiang

llms efficiency benchmarks

arXiv AI

Jun 8

Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization

arXiv:2606. 07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs).

By Shizhe Xiang, Ke An, Wenlong Yu, Yue Liu, Jian Luan, Pei Fu, Qilong Wang

llms reinforcement-learning efficiency multimodal safety

arXiv AI

Jun 11

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.

By Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp

llms nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 30

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.

By Xiaojun Wu, Xiaoguang Jiang, Huiyang Li, Jucai Zhai, Dengfeng Liu, Qiaobo Hao, Huang Liu, Zhiguo Yang, Ji Xie, Ninglun Gu, Jin Yang, Kailai Zhang, Yelun Bao, Jun Wang

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 17

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

arXiv:2607. 14682v1 Announce Type: new Abstract: Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge.

By Harikrishnan P M, Goutham Vignesh, Ganesh Parab, Saisubramaniam Gopalakrishnan, Vishal Vaddina, Varun V, Rohit Agrawal

nlp reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv AI

Aug 19

SOD: Step-wise On-policy Distillation for Small Language Model Agents

SOD: Step-wise On-policy Distillation for Small Language Model Agents proposes a new framework that adaptively reweights distillation strength at each reasoning step based on step-level divergence. This approach mitigates cascading errors in tool-integrated reasoning by attenuating misleading teacher signals in high-divergence regions while preserving dense guidance where student and teacher align. Experiments on math, science, and code benchmarks show up to 20.86% improvement over the second-best baseline, with a 0.6B student scoring 26.13% on AIME 2025.

By Qiyong Zhong, Mao Zheng, Mingyang Song, Xin Lin, Jie Sun, Houcheng Jiang, Xiang Wang, Junfeng Fang

llms agents reinforcement-learning efficiency benchmarks

One email a morning, machine-written

Related stories

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

Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

SOD: Step-wise On-policy Distillation for Small Language Model Agents