Cover Image

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Qianhao, Lou, Jie, Yu, Xing, Lin, Hongyu, Sun, Le, Han, Xianpei, Lu, Yaojie
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
by: Yuan, Qianhao, et al.
Published: (2025)

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
by: Yuan, Qianhao, et al.
Published: (2025)

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
by: Wen, Xueru, et al.
Published: (2024)

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
by: Yuan, Qianhao, et al.
Published: (2025)

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
by: Liu, Yanjiang, et al.
Published: (2026)

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
by: Li, Zichao, et al.
Published: (2025)

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
by: Ren, Mengjie, et al.
Published: (2026)

ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch
by: Chen, Jiawei, et al.
Published: (2025)

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
by: Bian, Ning, et al.
Published: (2024)

REInstruct: Building Instruction Data from Unlabeled Corpus
by: Chen, Shu, et al.
Published: (2024)

Open Grounded Planning: Challenges and Benchmark Construction
by: Guo, Shiguang, et al.
Published: (2024)

Few-shot Named Entity Recognition via Superposition Concept Discrimination
by: Chen, Jiawei, et al.
Published: (2024)

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
by: Mo, Guozhao, et al.
Published: (2025)

Executing Natural Language-Described Algorithms with Large Language Models: An Investigation
by: Zheng, Xin, et al.
Published: (2024)

Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
by: Li, Zhuoqun, et al.
Published: (2024)

Academically intelligent LLMs are not necessarily socially intelligent
by: Xu, Ruoxi, et al.
Published: (2024)

Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
by: Zheng, Xin, et al.
Published: (2024)

SoFA: Shielded On-the-fly Alignment via Priority Rule Following
by: Lu, Xinyu, et al.
Published: (2024)

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
by: Wen, Xueru, et al.
Published: (2024)

Coupled Variational Reinforcement Learning for Language Model General Reasoning
by: Wen, Xueru, et al.
Published: (2025)

Multi-Facet Counterfactual Learning for Content Quality Evaluation
by: Zheng, Jiasheng, et al.
Published: (2024)

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models
by: Liang, Qiao, et al.
Published: (2025)

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
by: Xiang, Hao, et al.
Published: (2024)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
by: Tang, Qiaoyu, et al.
Published: (2024)

PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
by: Li, Zhuoqun, et al.
Published: (2025)

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
by: Li, Zhuoqun, et al.
Published: (2024)

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
by: Li, Zichao, et al.
Published: (2026)

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
by: Peng, Xiaoxuan, et al.
Published: (2026)

READoc: A Unified Benchmark for Realistic Document Structured Extraction
by: Li, Zichao, et al.
Published: (2024)

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
by: Guan, Xinyan, et al.
Published: (2024)

Transferable Post-training via Inverse Value Learning
by: Lu, Xinyu, et al.
Published: (2024)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
by: Mao, Yingzhi, et al.
Published: (2025)

RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback
by: Tang, Qiaoyu, et al.
Published: (2025)

ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
by: Bian, Ning, et al.
Published: (2023)

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
by: Zheng, Jiasheng, et al.
Published: (2026)

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
by: Wen, Xueru, et al.
Published: (2025)

The Life Cycle of Knowledge in Big Language Models: A Survey
by: Cao, Boxi, et al.
Published: (2023)

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
by: Li, Zhuoqun, et al.
Published: (2025)

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring
by: Li, Zichao, et al.
Published: (2024)

Learning or Self-aligning? Rethinking Instruction Fine-tuning
by: Ren, Mengjie, et al.
Published: (2024)