Image de couverture de livre

Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lv, Shuai, Liu, Chang, Tang, Feng, Yuan, Yujie, Zhou, Aojun, Zhang, Kui, Yang, Xi, Song, Yangqiu
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
par: Zhao, Xiangyu, et autres
Publié: (2025)

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
par: Liu, Xinyu, et autres
Publié: (2025)

Revisiting Neural Networks for Continual Learning: An Architectural Perspective
par: Lu, Aojun, et autres
Publié: (2024)

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

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
par: Lu, Aojun, et autres
Publié: (2025)

Boosting Reasoning in Large Multimodal Models via Activation Replay
par: Xing, Yun, et autres
Publié: (2025)

MIRROR: Multimodal Iterative Reasoning via Reflection on Visual Regions
par: Zhang, Haoyu, et autres
Publié: (2026)

NODI: Out-Of-Distribution Detection with Noise from Diffusion
par: Zhou, Jingqiu, et autres
Publié: (2024)

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification
par: Sun, Linzhuang, et autres
Publié: (2025)

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
par: Liu, Benlin, et autres
Publié: (2024)

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning
par: Wang, Ke, et autres
Publié: (2025)

UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
par: Li, Hongrui, et autres
Publié: (2026)

NOAH: Learning Pairwise Object Category Attentions for Image Classification
par: Li, Chao, et autres
Publié: (2024)

GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
par: Lu, Xudong, et autres
Publié: (2025)

MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
par: Hu, Zhaofeng, et autres
Publié: (2024)

Adapt before Continual Learning
par: Lu, Aojun, et autres
Publié: (2025)

Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
par: Lu, Aojun, et autres
Publié: (2026)

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
par: Huang, Qihan, et autres
Publié: (2025)

SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model
par: Guo, Yu, et autres
Publié: (2026)

Indoor Obstacle Discovery on Reflective Ground via Monocular Camera
par: Xue, Feng, et autres
Publié: (2024)

Boosting Multimodal Learning via Disentangled Gradient Learning
par: Wei, Shicai, et autres
Publié: (2025)

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
par: Chen, Xinyan, et autres
Publié: (2025)

SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion
par: Guo, Jiajie, et autres
Publié: (2025)

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
par: Chen, Shuhang, et autres
Publié: (2026)

FastBoost: Progressive Attention with Dynamic Scaling for Efficient Deep Learning
par: Yuan, JunXi
Publié: (2025)

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
par: Chen, Dongyang, et autres
Publié: (2026)

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
par: Jiang, Haonan, et autres
Publié: (2026)

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
par: Shi, Weikang, et autres
Publié: (2025)

From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
par: Jia, Hongrui, et autres
Publié: (2026)

A Multi-Agent Framework with Structured Reasoning and Reflective Refinement for Multimodal Empathetic Response Generation
par: Wang, Liping, et autres
Publié: (2026)

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
par: Tian, Changyuan, et autres
Publié: (2026)

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
par: Wang, Shan, et autres
Publié: (2025)

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
par: Huang, Muye, et autres
Publié: (2025)

ASAM: Boosting Segment Anything Model with Adversarial Tuning
par: Li, Bo, et autres
Publié: (2024)

ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
par: Lin, Yijie, et autres
Publié: (2026)

LTRL: Boosting Long-tail Recognition via Reflective Learning
par: Zhao, Qihao, et autres
Publié: (2024)

DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation
par: Chen, Xi, et autres
Publié: (2025)

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
par: Jiang, Songtao, et autres
Publié: (2026)

EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing
par: Khalid, Umar, et autres
Publié: (2024)

Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
par: Wu, Gang, et autres
Publié: (2025)