paper-with-me

홈 › Papers

VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization

2025-05-25 · Yunxin Li, Xinyu Chen, Zitao Li, Zhenyu Liu, Longyue Wang, Wenhan Luo, Baotian Hu, Min Zhang

Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy Optimization (GRPO), are limited by data preparation bottlenecks (e.g., noise or high cost) and exhibit unstable improvements in the quality of long chain-of-thoughts (CoTs) and downstream performance.To address these limitations, we propose VerIPO, a Verifier-guided Iterative Policy Optimization method designed to gradually improve video LLMs' capacity for generating deep, long-term reasoning chains. The core component is Rollout-Aware Verifier, positioned between the GRPO and Direct Preference Optimization (DPO) training phases to form the GRPO-Verifier-DPO training loop. This verifier leverages small LLMs as a judge to assess the reasoning logic of rollouts, enabling the construction of high-quality contrastive data, including reflective and contextually consistent CoTs. These curated preference samples drive the efficient DPO stage (7x faster than GRPO), leading to marked improvements in reasoning chain quality, especially in terms of length and contextual consistency. This training loop benefits from GRPO's expansive search and DPO's targeted optimization. Experimental results demonstrate: 1) Significantly faster and more effective optimization compared to standard GRPO variants, yielding superior performance; 2) Our trained models exceed the direct inference of large-scale instruction-tuned Video-LLMs, producing long and contextually consistent CoTs on diverse video reasoning tasks; and 3) Our model with one iteration outperforms powerful LMMs (e.g., Kimi-VL) and long reasoning models (e.g., Video-R1), highlighting its effectiveness and stability.

📄 PDF Abstract BibTeX arXiv:2505.19000

Code (1)

hitsz-tmg/veripo 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving

2025-05-19 · Haoyuan Wu, Xueyi Chen, Rui Ming, Jilong Gao 외

Large language models (LLMs) demonstrate significant reasoning capabilities, particularly through long chain-of-thought (CoT) processes, which can be elicited by reinforcement learning (RL). However, prolonged CoT reason…

Reinforcement Learning (RL)

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

2024-09-30 · Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai 외

In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-to-end models. However, long video under…

EgoSchemaLanguage ModellingLarge Language ModelQuestion Answering+3

Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data

2025-09-26 · Zishan Ahmad, Saisubramaniam Gopalakrishnan arxiv

Large Language Models (LLMs), despite their remarkable capabilities, rely on singular, pre-dominant reasoning paradigms, hindering their performance on intricate problems that demand diverse cognitive strategies. To addr…

Question Answering

SiLVR: A Simple Language-based Video Reasoning Framework

2025-05-30 · Ce Zhang, Yan-Bo Lin, Ziyang Wang, Mohit Bansal 외

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilit…

MathMMEMMLUToken Reduction+2

VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

2025-11-21 · Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang 외 arxiv

Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, h…

Visual Reasoning