Copertina

Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Yihong, Ma, Fei, Shao, Yihua, Guo, Jingcai, Yu, Zitong, Cui, Laizhong, Tian, Qi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
di: Ji, Yicheng, et al.
Pubblicazione: (2025)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
di: Wu, Zhenkai, et al.
Pubblicazione: (2025)

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
di: Wu, Hao, et al.
Pubblicazione: (2026)

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
di: Guo, Yansong, et al.
Pubblicazione: (2026)

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
di: Chen, Boyuan, et al.
Pubblicazione: (2024)

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
di: He, Lehan, et al.
Pubblicazione: (2024)

HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task
di: Tian, Yu, et al.
Pubblicazione: (2024)

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
di: Liu, Tianhui, et al.
Pubblicazione: (2026)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
di: Jiang, Titong, et al.
Pubblicazione: (2025)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
di: Li, Yangfu, et al.
Pubblicazione: (2025)

Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
di: Ye, Weihao, et al.
Pubblicazione: (2024)

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
di: Wu, Hao, et al.
Pubblicazione: (2026)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
di: Wen, Zichen, et al.
Pubblicazione: (2025)

Similarity-Aware Token Pruning: Your VLM but Faster
di: Jeddi, Ahmadreza, et al.
Pubblicazione: (2025)

Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling
di: Hu, He, et al.
Pubblicazione: (2025)

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
di: Tang, Yihong, et al.
Pubblicazione: (2024)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
di: Li, Xue, et al.
Pubblicazione: (2025)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
di: Tang, Zicong, et al.
Pubblicazione: (2025)

In-Context Meta LoRA Generation
di: Shao, Yihua, et al.
Pubblicazione: (2025)

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
di: Zhang, Di, et al.
Pubblicazione: (2024)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
di: Zhong, Yiwu, et al.
Pubblicazione: (2024)

EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents
di: Li, Xinze, et al.
Pubblicazione: (2026)

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
di: Sheta, Hala, et al.
Pubblicazione: (2025)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
di: Wang, Nan, et al.
Pubblicazione: (2026)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
di: Son, Jaemin, et al.
Pubblicazione: (2025)

Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection
di: Li, Jianwei, et al.
Pubblicazione: (2023)

Navigation with VLM framework: Towards Going to Any Language
di: Yin, Zecheng, et al.
Pubblicazione: (2024)

Efficient Whole Slide Pathology VQA via Token Compression
di: Lyu, Weimin, et al.
Pubblicazione: (2025)

SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models
di: Liu, Zheng, et al.
Pubblicazione: (2024)

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
di: Ma, Chuang, et al.
Pubblicazione: (2026)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
di: Bagrov, Natan, et al.
Pubblicazione: (2025)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
di: Li, Geng, et al.
Pubblicazione: (2026)

Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration
di: Park, ChaeHun, et al.
Pubblicazione: (2024)

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
di: Hu, Zhe, et al.
Pubblicazione: (2025)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
di: Zhang, Ce, et al.
Pubblicazione: (2025)

SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
di: Wang, Siting, et al.
Pubblicazione: (2025)

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
di: Hu, Wenbo, et al.
Pubblicazione: (2025)

PersonaVLM: Long-Term Personalized Multimodal LLMs
di: Nie, Chang, et al.
Pubblicazione: (2026)

Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
di: Yu, Yongcan, et al.
Pubblicazione: (2025)

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
di: Shang, Yuying, et al.
Pubblicazione: (2024)