Image de couverture de livre

Test-Time Temporal Sampling for Efficient MLLM Video Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Kaibin, Lin, Mingbao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Motion-Aware Video MLLM
par: Zhao, Zijia, et autres
Publié: (2025)

RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
par: Xun, Shuhang, et autres
Publié: (2025)

MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
par: Tan, Wenhui, et autres
Publié: (2026)

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
par: Liu, Zuyan, et autres
Publié: (2024)

Progressive Video Condensation with MLLM Agent for Long-form Video Understanding
par: Yin, Yufei, et autres
Publié: (2026)

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding
par: Wang, Yiheng, et autres
Publié: (2026)

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents
par: Chen, Boyu, et autres
Publié: (2025)

Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
par: Zhang, Haoyu, et autres
Publié: (2025)

Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
par: Yue, Feng, et autres
Publié: (2025)

ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
par: Zhu, Wenjie, et autres
Publié: (2025)

MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding
par: Ran, Ran, et autres
Publié: (2026)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
par: Hu, Pengfei, et autres
Publié: (2025)

In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
par: Peng, Taiying, et autres
Publié: (2025)

VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
par: Waheed, Abdul, et autres
Publié: (2025)

Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing
par: Jiang, Pengfei, et autres
Publié: (2024)

TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding
par: Tang, Canhui, et autres
Publié: (2025)

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
par: Wang, Shaobo, et autres
Publié: (2025)

dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
par: Xin, Yi, et autres
Publié: (2025)

OCC-MLLM-Alpha:Empowering Multi-modal Large Language Model for the Understanding of Occluded Objects with Self-Supervised Test-Time Learning
par: Yang, Shuxin, et autres
Publié: (2024)

UniVST: A Unified Framework for Training-free Localized Video Style Transfer
par: Song, Quanjian, et autres
Publié: (2024)

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
par: Lin, Zhihang, et autres
Publié: (2024)

Elysium: Exploring Object-level Perception in Videos via MLLM
par: Wang, Han, et autres
Publié: (2024)

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
par: Zhang, Haoji, et autres
Publié: (2025)

Temporal Cluster Assignment for Efficient Real-Time Video Segmentation
par: Yung, Ka-Wai, et autres
Publié: (2025)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
par: Bagrov, Natan, et autres
Publié: (2025)

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
par: Cheng, Junhao, et autres
Publié: (2025)

Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing
par: Yang, Hao, et autres
Publié: (2026)

Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling
par: Qin, Ziran, et autres
Publié: (2025)

Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks
par: Yang, Min, et autres
Publié: (2024)

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
par: Qi, Haozhe, et autres
Publié: (2026)

EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
par: Ahn, Geo, et autres
Publié: (2026)

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
par: Zhao, Xinkui, et autres
Publié: (2025)

EasyInv: Toward Fast and Better DDIM Inversion
par: Zhang, Ziyue, et autres
Publié: (2024)

DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On
par: Zhan, Wengyi, et autres
Publié: (2024)

MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval
par: Cai, Weitong, et autres
Publié: (2024)

Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning
par: Tian, Kaibin, et autres
Publié: (2024)

VideoMamba: State Space Model for Efficient Video Understanding
par: Li, Kunchang, et autres
Publié: (2024)

Progressive Supernet Training for Efficient Visual Autoregressive Modeling
par: Chen, Xiaoyue, et autres
Publié: (2025)

VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding
par: Zhao, Henghao, et autres
Publié: (2025)

V-CORE: Temporally Consistent Video Understanding for Video-LLM
par: Kang, Zhengjian, et autres
Publié: (2026)