Cover Image

Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Mingrui, Liu, Haogeng, Liang, Hao, Huang, Huaibo, Zhang, Wentao, He, Ran
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
by: Chen, Mingrui, et al.
Published: (2026)

Advancing Vision Transformer with Enhanced Spatial Priors
by: Fan, Qihang, et al.
Published: (2026)

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
by: Liu, Haogeng, et al.
Published: (2024)

Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
by: Fan, Qihang, et al.
Published: (2024)

RMT: Retentive Networks Meet Vision Transformers
by: Fan, Qihang, et al.
Published: (2023)

InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
by: Liu, Haogeng, et al.
Published: (2024)

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
by: Han, Xiaotian, et al.
Published: (2024)

DeVAn: Dense Video Annotation for Video-Language Models
by: Liu, Tingkai, et al.
Published: (2023)

Vision Transformer with Sparse Scan Prior
by: Zhang, Yuguang, et al.
Published: (2024)

Breaking the Low-Rank Dilemma of Linear Attention
by: Fan, Qihang, et al.
Published: (2024)

LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration
by: Ai, Yuang, et al.
Published: (2024)

Marmot: Object-Level Self-Correction via Multi-Agent Reasoning
by: Sun, Jiayang, et al.
Published: (2025)

Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
by: Ai, Yuang, et al.
Published: (2023)

ZePo: Zero-Shot Portrait Stylization with Faster Sampling
by: Liu, Jin, et al.
Published: (2024)

Rectifying Magnitude Neglect in Linear Attention
by: Fan, Qihang, et al.
Published: (2025)

NOFT: Test-Time Noise Finetune via Information Bottleneck for Highly Correlated Asset Creation
by: Li, Jia, et al.
Published: (2025)

Random Wins All: Rethinking Grouping Strategies for Vision Tokens
by: Fan, Qihang, et al.
Published: (2026)

Lightweight Vision Transformer with Bidirectional Interaction
by: Fan, Qihang, et al.
Published: (2023)

Synthetic Perception: Can Generated Images Unlock Latent Visual Prior for Text-Centric Reasoning?
by: Huang, Yuesheng, et al.
Published: (2025)

Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
by: Ai, Yuang, et al.
Published: (2023)

Unlocking the Potential of Diffusion Priors in Blind Face Restoration
by: Miao, Yunqi, et al.
Published: (2025)

Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
by: Ai, Yuang, et al.
Published: (2025)

InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
by: Gao, Nan, et al.
Published: (2025)

Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification
by: Wang, Zi, et al.
Published: (2022)

Vision Transformer with Super Token Sampling
by: Huang, Huaibo, et al.
Published: (2022)

CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
by: Hao, Xiangzhao, et al.
Published: (2026)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
by: Liu, Xuannan, et al.
Published: (2024)

MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
by: Bai, Purui, et al.
Published: (2026)

TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
by: Feng, Hengyi, et al.
Published: (2026)

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
by: Ai, Yuang, et al.
Published: (2025)

DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration
by: Gao, Nan, et al.
Published: (2024)

Label What Matters: Modality-Balanced and Difficulty-Aware Multimodal Active Learning
by: Zeng, Yuqiao, et al.
Published: (2026)

Straighter Flow Matching via a Diffusion-Based Coupling Prior
by: Xing, Siyu, et al.
Published: (2023)

Survey on AI-Generated Media Detection: From Non-MLLM to MLLM
by: Zou, Yueying, et al.
Published: (2025)

Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
by: Liang, Hao, et al.
Published: (2025)

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
by: Lin, Honglin, et al.
Published: (2026)

VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition
by: Jin, Hongbo, et al.
Published: (2025)

Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
by: Ge, Shiran, et al.
Published: (2025)

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning
by: Chen, Tieyuan, et al.
Published: (2025)

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior
by: Li, Mingrui, et al.
Published: (2025)