Copertina

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kancheti, Sai Srinivas, Kanade, Aditya, Sinha, Rohit, Balasubramanian, Vineeth N, Ganu, Tanuja
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
di: Kancheti, Sai Srinivas, et al.
Pubblicazione: (2026)

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
di: Sinha, Rohit, et al.
Pubblicazione: (2026)

Do You See Me : A Multidimensional Benchmark for Evaluating Visual Perception in Multimodal LLMs
di: Kanade, Aditya, et al.
Pubblicazione: (2025)

Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
di: Kuchibhotla, Hari Chandana, et al.
Pubblicazione: (2025)

Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?
di: Kuchibhotla, Hari Chandana, et al.
Pubblicazione: (2024)

Interpretable Model Drift Detection
di: Panda, Pranoy, et al.
Pubblicazione: (2025)

MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning
di: Kumar, Somnath, et al.
Pubblicazione: (2024)

RadPhi-3: Small Language Models for Radiology
di: Ranjit, Mercy, et al.
Pubblicazione: (2024)

$\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
di: Devalapally, Arnav, et al.
Pubblicazione: (2026)

Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity
di: Pathak, Harsharaj, et al.
Pubblicazione: (2026)

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
di: Liu, Jie, et al.
Pubblicazione: (2026)

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
di: Tian, Changyuan, et al.
Pubblicazione: (2026)

CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization
di: Hou, Xinhai, et al.
Pubblicazione: (2025)

LogicCBMs: Logic-Enhanced Concept-Based Learning
di: Vemuri, Deepika SN, et al.
Pubblicazione: (2025)

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
di: Wang, Hengyi, et al.
Pubblicazione: (2024)

Can Reasons Help Improve Pedestrian Intent Estimation? A Cross-Modal Approach
di: Khindkar, Vaishnavi, et al.
Pubblicazione: (2024)

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
di: Rong, Xuankun, et al.
Pubblicazione: (2025)

PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
di: Li, Yantao, et al.
Pubblicazione: (2026)

Understanding Task Transfer in Vision-Language Models
di: Sachdeva, Bhuvan, et al.
Pubblicazione: (2025)

Where does an LLM begin computing an instruction?
di: Pola, Aditya, et al.
Pubblicazione: (2025)

LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation
di: Mo, Shentong, et al.
Pubblicazione: (2026)

Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting
di: Arora, Nirmit, et al.
Pubblicazione: (2025)

Designing Culturally Aligned AI Systems For Social Good in Non-Western Contexts
di: Dennison, Deepak Varuvel, et al.
Pubblicazione: (2025)

DanceGRPO: Unleashing GRPO on Visual Generation
di: Xue, Zeyue, et al.
Pubblicazione: (2025)

C2FDrone: Coarse-to-Fine Drone-to-Drone Detection using Vision Transformer Networks
di: Rebbapragada, Sairam VC, et al.
Pubblicazione: (2024)

Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks
di: Garg, Tanmay, et al.
Pubblicazione: (2024)

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
di: Qiu, Longtian, et al.
Pubblicazione: (2025)

Improving Visual Representation Alignment Generation with GRPO
di: Mo, Shentong, et al.
Pubblicazione: (2026)

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
di: Li, Yujun, et al.
Pubblicazione: (2026)

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
di: He, Xiaoxuan, et al.
Pubblicazione: (2026)

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
di: Lv, Weijiang, et al.
Pubblicazione: (2026)

Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning
di: Sinha, Sanchit, et al.
Pubblicazione: (2026)

Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance
di: Santra, Sanchayan, et al.
Pubblicazione: (2025)

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
di: Yao, Huanjin, et al.
Pubblicazione: (2025)

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
di: Zhang, Liyu, et al.
Pubblicazione: (2026)

Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering
di: Srivastava, Pragya, et al.
Pubblicazione: (2024)

Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
di: Moll, Johannes, et al.
Pubblicazione: (2025)

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

Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media
di: M, Megha Mariam K., et al.
Pubblicazione: (2026)

Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
di: Xu, Shaodong, et al.
Pubblicazione: (2026)