Image de couverture de livre

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hong, Minjie, Guo, Zirun, Xia, Yan, Wang, Zehan, Zhang, Ziang, Jin, Tao, Zhao, Zhou
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
par: Guo, Zirun, et autres
Publié: (2025)

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence
par: Zhang, Ziang, et autres
Publié: (2025)

Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation
par: He, Yongbo, et autres
Publié: (2026)

Thinking with Programming Vision: Towards a Unified View for Thinking with Images
par: Guo, Zirun, et autres
Publié: (2025)

Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
par: Qiu, Yansheng, et autres
Publié: (2025)

Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
par: Guo, Zirun, et autres
Publié: (2024)

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
par: Guo, Zirun, et autres
Publié: (2024)

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises
par: Guo, Zirun, et autres
Publié: (2025)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
par: Guo, Zirun, et autres
Publié: (2025)

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
par: Li, Yuanshuai, et autres
Publié: (2025)

Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision
par: Yan, Weicai, et autres
Publié: (2025)

Towards Faithful Reasoning in Comics for Small MLLMs
par: Feng, Chengcheng, et autres
Publié: (2026)

UniAPO: Unified Multimodal Automated Prompt Optimization
par: Zhu, Qipeng, et autres
Publié: (2025)

Low-rank Prompt Interaction for Continual Vision-Language Retrieval
par: Yan, Weicai, et autres
Publié: (2025)

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
par: Wang, Zehan, et autres
Publié: (2024)

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
par: Yuan, Jiakang, et autres
Publié: (2025)

Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs
par: Deng, Naihao, et autres
Publié: (2024)

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
par: Huang, Jincai, et autres
Publié: (2026)

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
par: Ji, Yikun, et autres
Publié: (2025)

S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
par: Xu, Beining, et autres
Publié: (2025)

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
par: Zeng, Xiangyu, et autres
Publié: (2024)

Enhancing Advanced Visual Reasoning Ability of Large Language Models
par: Li, Zhiyuan, et autres
Publié: (2024)

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
par: Guo, Zirun, et autres
Publié: (2024)

Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization
par: Liu, Boyang, et autres
Publié: (2025)

VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation
par: Huang, Peng, et autres
Publié: (2025)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
par: Li, Qiaoru, et autres
Publié: (2026)

SpatialTree: How Spatial Abilities Branch Out in MLLMs
par: Xiao, Yuxi, et autres
Publié: (2025)

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
par: Yang, Cheng, et autres
Publié: (2025)

ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
par: Qu, Xiangyan, et autres
Publié: (2025)

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
par: Du, Dazhao, et autres
Publié: (2026)

Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning
par: Li, Yian, et autres
Publié: (2024)

Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation
par: Fu, Kang, et autres
Publié: (2026)

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
par: Wang, Zehan, et autres
Publié: (2024)

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
par: Zhang, Bob, et autres
Publié: (2025)

LLM-I: LLMs are Naturally Interleaved Multimodal Creators
par: Guo, Zirun, et autres
Publié: (2025)

VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
par: Jiang, Pengfei, et autres
Publié: (2025)

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting
par: Zhang, Tao, et autres
Publié: (2025)

OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces
par: Wang, Zehan, et autres
Publié: (2024)

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
par: Wang, Jingchao, et autres
Publié: (2025)

Reasoning Can Hurt the Inductive Abilities of Large Language Models
par: Jin, Haibo, et autres
Publié: (2025)