Cover Image

TrajTok: Learning Trajectory Tokens enables better Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Chenhao, Zhang, Jieyu, Zhang, Jianing, Huang, Weikai, Kumar, Ashutosh, Kong, Quan, Tuzel, Oncel, Li, Chun-Liang, Krishna, Ranjay
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

TrajTok: Technical Report for 2025 Waymo Open Sim Agents Challenge
by: Zhang, Zhiyuan, et al.
Published: (2025)

Iterated Learning Improves Compositionality in Large Vision-Language Models
by: Zheng, Chenhao, et al.
Published: (2024)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
by: Gao, Ziqi, et al.
Published: (2024)

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
by: Ma, Zixian, et al.
Published: (2024)

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

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

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
by: Hsieh, Cheng-Yu, et al.
Published: (2025)

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

LiTo: Surface Light Field Tokenization
by: Chang, Jen-Hao Rick, et al.
Published: (2026)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

TrajLoom: Dense Future Trajectory Generation from Video
by: Zhang, Zewei, et al.
Published: (2026)

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

Video-Based Reward Modeling for Computer-Use Agents
by: Song, Linxin, et al.
Published: (2026)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2024)

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
by: Hsieh, Yu-Guan, et al.
Published: (2024)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
by: Mirzadeh, Iman, et al.
Published: (2024)

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
by: Yang, Yinuo, et al.
Published: (2026)

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
by: Zhang, Zhiyuan, et al.
Published: (2025)

TrajSV: A Trajectory-based Model for Sports Video Representations and Applications
by: Wang, Zheng, et al.
Published: (2025)

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
by: Susladkar, Onkar, et al.
Published: (2026)

AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
by: Chowdhury, Sanjoy, et al.
Published: (2025)

DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs
by: Park, Minyoung, et al.
Published: (2026)

PoseTraj: Pose-Aware Trajectory Control in Video Diffusion
by: Ji, Longbin, et al.
Published: (2025)

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2023)

Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators
by: Hu, Zhengyu, et al.
Published: (2024)

Pretraining with hierarchical memories: separating long-tail and common knowledge
by: Pouransari, Hadi, et al.
Published: (2025)

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
by: Zhang, Jianrui, et al.
Published: (2026)

ElasticTok: Adaptive Tokenization for Image and Video
by: Yan, Wilson, et al.
Published: (2024)

MUSCLE: A Model Update Strategy for Compatible LLM Evolution
by: Echterhoff, Jessica, et al.
Published: (2024)

3D Shape Tokenization via Latent Flow Matching
by: Chang, Jen-Hao Rick, et al.
Published: (2024)

FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
by: Qiu, Haonan, et al.
Published: (2024)

Task Me Anything
by: Zhang, Jieyu, et al.
Published: (2024)

ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
by: Wang, Xiaoce, et al.
Published: (2026)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
by: Zou, Quanchen, et al.
Published: (2026)

SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization
by: Tan, Zhentao, et al.
Published: (2024)

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
by: Pouransari, Hadi, et al.
Published: (2024)

Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation
by: Zhang, Zhiyang, et al.
Published: (2025)

Offline Training of Language Model Agents with Functions as Learnable Weights
by: Zhang, Shaokun, et al.
Published: (2024)

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