Copertina

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yongxin, Yang, Zhicheng, Cao, Meng, Han, Mingfei, Lin, Haokun, Zhu, Yingying, Chang, Xiaojun, Liang, Xiaodan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation
di: Wang, Yongxin, et al.
Pubblicazione: (2024)

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
di: Ma, Liang, et al.
Pubblicazione: (2025)

StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
di: Hu, Panwen, et al.
Pubblicazione: (2024)

Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
di: Li, Mingjie, et al.
Pubblicazione: (2024)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
di: Yang, Zhicheng, et al.
Pubblicazione: (2026)

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
di: Yang, Zhicheng, et al.
Pubblicazione: (2026)

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
di: Han, Mingfei, et al.
Pubblicazione: (2024)

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
di: Li, Shuozhe, et al.
Pubblicazione: (2026)

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
di: Yang, Zhicheng, et al.
Pubblicazione: (2025)

CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory
di: Zhao, Haokun, et al.
Pubblicazione: (2025)

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
di: Yang, Zhicheng, et al.
Pubblicazione: (2025)

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning
di: Yang, Chengcao
Pubblicazione: (2026)

Generative Universal Verifier as Multimodal Meta-Reasoner
di: Zhang, Xinchen, et al.
Pubblicazione: (2025)

LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
di: Hao, Haihong, et al.
Pubblicazione: (2026)

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
di: Shan, Xiaojun, et al.
Pubblicazione: (2025)

Multimodal Fact-Level Attribution for Verifiable Reasoning
di: Wan, David, et al.
Pubblicazione: (2026)

Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
di: Lin, Bingqian, et al.
Pubblicazione: (2024)

Efficient Training of Large Vision Models via Advanced Automated Progressive Learning
di: Li, Changlin, et al.
Pubblicazione: (2024)

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
di: Lin, Bingqian, et al.
Pubblicazione: (2024)

ATG: Benchmarking Automated Theorem Generation for Generative Language Models
di: Lin, Xiaohan, et al.
Pubblicazione: (2024)

StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models
di: Zhang, Xiangxiang, et al.
Pubblicazione: (2025)

Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery
di: Fang, Yingying, et al.
Pubblicazione: (2024)

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
di: Qian, Zhe, et al.
Pubblicazione: (2026)

Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram
di: Zhang, Ming-Liang, et al.
Pubblicazione: (2024)

Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
di: Zhao, Qiannian, et al.
Pubblicazione: (2026)

Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
di: Cao, Meng, et al.
Pubblicazione: (2025)

EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
di: Lin, Bingqian, et al.
Pubblicazione: (2025)

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
di: Kwon, Yongchan, et al.
Pubblicazione: (2025)

GCPO: When Contrast Fails, Go Gold
di: Wu, Hao, et al.
Pubblicazione: (2025)

Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
di: Jing, Peiyuan, et al.
Pubblicazione: (2025)

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
di: Chen, Yi, et al.
Pubblicazione: (2025)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
di: Ma, Zhengzhao, et al.
Pubblicazione: (2026)

GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
di: Liu, Ruiheng, et al.
Pubblicazione: (2026)

Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos
di: Cao, Meng, et al.
Pubblicazione: (2026)

Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning
di: Pang, Yuqi, et al.
Pubblicazione: (2025)

Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation
di: Zhang, Chenghao, et al.
Pubblicazione: (2026)

MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning
di: Liu, Hongjun, et al.
Pubblicazione: (2025)

No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers
di: Marsili, Damiano, et al.
Pubblicazione: (2025)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
di: Cao, Chentao, et al.
Pubblicazione: (2025)

Multimodal Fine-grained Reasoning for Post Quality Evaluation
di: Guo, Xiaoxu, et al.
Pubblicazione: (2025)