Cover Image

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jianrui, Yang, Yue, Tripathi, Rohun, Han, Winson, Krishna, Ranjay, Clark, Christopher, Lee, Yong Jae, Lee, Sangho
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MolmoPoint: Better Pointing for VLMs with Grounding Tokens
by: Clark, Christopher, et al.
Published: (2026)

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
by: Clark, Christopher, et al.
Published: (2026)

Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos
by: Zhang, Jianrui, et al.
Published: (2024)

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
by: Jain, Jitesh, et al.
Published: (2025)

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
by: Gao, Ziqi, et al.
Published: (2026)

VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
by: Yadav, Tanush, et al.
Published: (2026)

STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing
by: Lee, Junsung, et al.
Published: (2025)

One Diffusion to Generate Them All
by: Le, Duong H., et al.
Published: (2024)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
by: Hyun, Jeongseok, et al.
Published: (2025)

Visual Representations inside the Language Model
by: Liu, Benlin, et al.
Published: (2025)

MAMS: Model-Agnostic Module Selection Framework for Video Captioning
by: Lee, Sangho, et al.
Published: (2025)

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
by: Zhang, Tianyi, et al.
Published: (2026)

Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
by: Huang, Weikai, et al.
Published: (2025)

RefTok: Reference-Based Tokenization for Video Generation
by: Fan, Xiang, et al.
Published: (2025)

VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation
by: Zou, Bocheng, et al.
Published: (2024)

Can Language Models Laugh at YouTube Short-form Videos?
by: Ko, Dayoon, et al.
Published: (2023)

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples
by: Zhang, Jianrui, et al.
Published: (2024)

B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
by: Choi, Changho, et al.
Published: (2025)

VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
by: Wang, Feng, et al.
Published: (2026)

Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoring
by: Xu, Mingjie, et al.
Published: (2025)

Posterior Augmented Flow Matching
by: Stoica, George, et al.
Published: (2026)

Reasoning-Augmented Representations for Multimodal Retrieval
by: Zhang, Jianrui, et al.
Published: (2026)

EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models
by: Xu, Wenhao, et al.
Published: (2025)

Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation
by: Zhou, Hanyu, et al.
Published: (2025)

TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
by: Zhou, Xingcheng, et al.
Published: (2025)

VideoCoF: Unified Video Editing with Temporal Reasoner
by: Yang, Xiangpeng, et al.
Published: (2025)

TrajTok: Learning Trajectory Tokens enables better Video Understanding
by: Zheng, Chenhao, et al.
Published: (2026)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
by: Jun, Youngjun, et al.
Published: (2026)

Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents
by: Xu, Zhou, et al.
Published: (2026)

Stateful Token Reduction for Long-Video Hybrid VLMs
by: Jiang, Jindong, et al.
Published: (2026)

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach
by: Rai, Ayush K., et al.
Published: (2023)

Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens
by: Sun, Dengdi, et al.
Published: (2024)

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
by: Fan, Xiang, et al.
Published: (2024)

OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models
by: Kang, Minseok, et al.
Published: (2026)

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
by: Kim, Chris Dongjoo, et al.
Published: (2025)

Towards Long-Form Spatio-Temporal Video Grounding
by: Gu, Xin, et al.
Published: (2026)

Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining
by: Zhuang, Weijun, et al.
Published: (2026)

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
by: Cai, Mu, et al.
Published: (2024)

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
by: Zheng, Chenhao, et al.
Published: (2025)

Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer
by: Noghre, Ghazal Alinezhad, et al.
Published: (2024)