Cover Image

Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Siyou, Wu, Huanan, Shao, Juexi, Ma, Yinghao, Gan, Yujian, Luo, Yihao, Wang, Yuwei, Nie, Dong, Wang, Lu, Wu, Wenqing, Zhang, Le, Poesio, Massimo, Yu, Juntao
Format:	Preprint
Published:	2025
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

Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
by: Shao, Juexi, et al.
Published: (2025)

GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
by: Zhai, Ziyu, et al.
Published: (2026)

$μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation
by: Li, Siyou, et al.
Published: (2025)

Improving LLMs' Learning for Coreference Resolution
by: Gan, Yujian, et al.
Published: (2025)

NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment
by: Wu, Wenqing, et al.
Published: (2026)

ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog
by: Gan, Yujian, et al.
Published: (2024)

CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following
by: Ma, Yinghao, et al.
Published: (2025)

ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation
by: Li, Siyou, et al.
Published: (2024)

MDC-R: The Minecraft Dialogue Corpus with Reference
by: Madge, Chris, et al.
Published: (2025)

ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
by: Ge, Jiawei, et al.
Published: (2026)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
by: Wang, Wenxuan, et al.
Published: (2025)

Large Language Models as Minecraft Agents
by: Madge, Chris, et al.
Published: (2024)

Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain
by: Lu, Pengcheng, et al.
Published: (2024)

Understanding The Effect Of Temperature On Alignment With Human Opinions
by: Pavlovic, Maja, et al.
Published: (2024)

Data Augmentation for Fake Reviews Detection in Multiple Languages and Multiple Domains
by: Liu, Ming, et al.
Published: (2025)

A LLM Benchmark based on the Minecraft Builder Dialog Agent Task
by: Madge, Chris, et al.
Published: (2024)

The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation
by: Pavlovic, Maja, et al.
Published: (2024)

Referential ambiguity and clarification requests: comparing human and LLM behaviour
by: Madge, Chris, et al.
Published: (2025)

Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
by: Li, Nan, et al.
Published: (2025)

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
by: Pavlovic, Maja, et al.
Published: (2026)

Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference
by: Anh, Dang, et al.
Published: (2025)

Hypernetworks for Perspectivist Adaptation
by: Ignatev, Daniil, et al.
Published: (2025)

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling
by: Ju, Shaobo, et al.
Published: (2026)

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
by: Luo, Yongdong, et al.
Published: (2025)

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
by: Xu, Chenyi, et al.
Published: (2026)

Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
by: Wu, Zhanyu, et al.
Published: (2026)

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
by: Wang, Shaoguang, et al.
Published: (2026)

Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detection
by: Mo, Yujian, et al.
Published: (2025)

LDRFusion: A LiDAR-Dominant multimodal refinement framework for 3D object detection
by: Wang, Jijun, et al.
Published: (2025)

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
by: Shao, Wei, et al.
Published: (2025)

Extending Activation Steering to Broad Skills and Multiple Behaviours
by: van der Weij, Teun, et al.
Published: (2024)

Finding and breaking the realistic rate-distance limit of continuous variable quantum key distribution
by: Wang, Xuyang, et al.
Published: (2018)

Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
by: Chen, Seng Nam, et al.
Published: (2026)

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
by: Wang, Xiangchen, et al.
Published: (2025)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback
by: Wang, Zheng, et al.
Published: (2024)

EGTM: Event-guided Efficient Turbulence Mitigation
by: Li, Huanan, et al.
Published: (2025)

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression
by: Jiang, Wei, et al.
Published: (2026)

See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops
by: Dong, Zixuan, et al.
Published: (2025)

Total Thoracoscopic Surgery for Late Mitral Paravalvular Leakage Repair in A Beating Heart
by: Huanan Liu
Published: (2023)