Copertina

Reinforcing Consistency in Video MLLMs with Structured Rewards

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Quan, Yihao, Shi, Zeru, Zhao, Jinman, Tang, Ruixiang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Improving Visual Reasoning with Iterative Evidence Refinement
di: Shi, Zeru, et al.
Pubblicazione: (2026)

SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization
di: Wang, Peiyao, et al.
Pubblicazione: (2025)

Unhackable Temporal Rewarding for Scalable Video MLLMs
di: Yu, En, et al.
Pubblicazione: (2025)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
di: Che, Liwei, et al.
Pubblicazione: (2026)

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
di: Wang, Jiahao, et al.
Pubblicazione: (2025)

Video-R1: Reinforcing Video Reasoning in MLLMs
di: Feng, Kaituo, et al.
Pubblicazione: (2025)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
di: Fan, Kaixuan, et al.
Pubblicazione: (2025)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
di: Ouyang, Kun, et al.
Pubblicazione: (2025)

Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Video
di: Tu, Mingxiao, et al.
Pubblicazione: (2026)

Spatial Preference Rewarding for MLLMs Spatial Understanding
di: Qiu, Han, et al.
Pubblicazione: (2025)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
di: Wang, Qi, et al.
Pubblicazione: (2025)

Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-Tuning
di: Aoshima, Takehiro, et al.
Pubblicazione: (2025)

MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
di: Wang, Yueqian, et al.
Pubblicazione: (2025)

VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking
di: Meng, Desen, et al.
Pubblicazione: (2025)

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
di: Li, Yunheng, et al.
Pubblicazione: (2026)

GVT2RPM: An Empirical Study for General Video Transformer Adaptation to Remote Physiological Measurement
di: Wang, Hao, et al.
Pubblicazione: (2024)

Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
di: Wu, Jingze, et al.
Pubblicazione: (2026)

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
di: Zhao, Jiahe, et al.
Pubblicazione: (2025)

CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perception
di: Zhang, Zengxi, et al.
Pubblicazione: (2023)

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
di: Zhao, Zijia, et al.
Pubblicazione: (2024)

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
di: An, Zhaochong, et al.
Pubblicazione: (2026)

SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
di: Alansari, Mohamad, et al.
Pubblicazione: (2026)

Low-Rank Interconnected Adaptation across Layers
di: Zhong, Yibo, et al.
Pubblicazione: (2024)

SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval
di: Zhao, Ruixiang, et al.
Pubblicazione: (2026)

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
di: Le, Minh-Quan, et al.
Pubblicazione: (2026)

Quantitative Video World Model Evaluation for Geometric-Consistency
di: Wu, Jiaxin, et al.
Pubblicazione: (2026)

Exploring the Design Space of Visual Context Representation in Video MLLMs
di: Du, Yifan, et al.
Pubblicazione: (2024)

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
di: Tang, Yuqi, et al.
Pubblicazione: (2026)

Touch-R1: Reinforcing Touch Reasoning in MLLMs
di: Lai, Yingxin, et al.
Pubblicazione: (2026)

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
di: Li, Hongyu, et al.
Pubblicazione: (2025)

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
di: Ping, Bowen, et al.
Pubblicazione: (2025)

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
di: Guo, Minghao, et al.
Pubblicazione: (2026)

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
di: Liu, Yuanxin, et al.
Pubblicazione: (2025)

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
di: Li, Jiachen, et al.
Pubblicazione: (2024)

RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees
di: Xu, Yichen, et al.
Pubblicazione: (2026)

DiffArtist: Towards Structure and Appearance Controllable Image Stylization
di: Jiang, Ruixiang, et al.
Pubblicazione: (2024)

GVDIFF: Grounded Text-to-Video Generation with Diffusion Models
di: Dou, Huanzhang, et al.
Pubblicazione: (2024)

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
di: Fang, Bo, et al.
Pubblicazione: (2025)

SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement
di: Shi, Zeru, et al.
Pubblicazione: (2024)

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
di: Liu, Yuanxin, et al.
Pubblicazione: (2025)