Image de couverture de livre

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Qihan, Dai, Weilong, Liu, Jinlong, He, Wanggui, Jiang, Hao, Song, Mingli, Chen, Jingyuan, Yao, Chang, Song, Jie
Format:	Preprint
Publié:	2025
Sujets:	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

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
par: Huang, Qihan, et autres
Publié: (2024)

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
par: Huang, Qihan, et autres
Publié: (2025)

MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
par: Wang, Xierui, et autres
Publié: (2024)

Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
par: Huang, Qihan, et autres
Publié: (2024)

Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
par: Wang, Yi, et autres
Publié: (2025)

PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning
par: Liu, Jinlong, et autres
Publié: (2026)

On the Concept Trustworthiness in Concept Bottleneck Models
par: Huang, Qihan, et autres
Publié: (2024)

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
par: Tong, Yunze, et autres
Publié: (2026)

AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs
par: Chang, Boyu, et autres
Publié: (2026)

LG-CAV: Train Any Concept Activation Vector with Language Guidance
par: Huang, Qihan, et autres
Publié: (2024)

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
par: Zhang, Peng, et autres
Publié: (2026)

ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
par: Xue, Mengqi, et autres
Publié: (2022)

IRPO: Boosting Image Restoration via Post-training GRPO
par: Xu, Haoxuan, et autres
Publié: (2025)

AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
par: Chao, Yuhao, et autres
Publié: (2025)

Debiasing Text-to-Image Diffusion Models
par: He, Ruifei, et autres
Publié: (2024)

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
par: Zeng, Qian, et autres
Publié: (2025)

CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
par: Song, Qi, et autres
Publié: (2025)

Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
par: Xie, Yuechen, et autres
Publié: (2025)

Diffusion Model Quantization: A Review
par: Zeng, Qian, et autres
Publié: (2025)

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
par: Tang, Siao, et autres
Publié: (2025)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
par: Ma, Xiaoxiao, et autres
Publié: (2026)

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery
par: Yao, Nanjie, et autres
Publié: (2026)

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
par: Liu, Jie, et autres
Publié: (2026)

Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
par: Zhang, Longxiang, et autres
Publié: (2026)

Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
par: Yuan, Jiangye, et autres
Publié: (2026)

Rethinking Token Reduction for Large Vision-Language Models
par: Wang, Yi, et autres
Publié: (2026)

DanceGRPO: Unleashing GRPO on Visual Generation
par: Xue, Zeyue, et autres
Publié: (2025)

Improving Alignment in LVLMs with Debiased Self-Judgment
par: Yang, Sihan, et autres
Publié: (2025)

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
par: Zhang, Evelyn, et autres
Publié: (2025)

Sampling-Aware Quantization for Diffusion Models
par: Zeng, Qian, et autres
Publié: (2025)

On the Evaluation Consistency of Attribution-based Explanations
par: Duan, Jiarui, et autres
Publié: (2024)

MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
par: Qi, Yu, et autres
Publié: (2026)

FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
par: Zhong, Haonan, et autres
Publié: (2026)

TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition
par: Yang, Xiahan, et autres
Publié: (2025)

HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
par: Chen, Ruyi, et autres
Publié: (2026)

SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
par: Xie, Yuechen, et autres
Publié: (2026)

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
par: Wang, Yibin, et autres
Publié: (2025)

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
par: Huang, Chao, et autres
Publié: (2025)

MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimation
par: Dong, Yue-Jiang, et autres
Publié: (2024)

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
par: Li, Keliang, et autres
Publié: (2025)