Copertina

CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lei, Jingyu, Wang, Gaoang, Lee, Der-Horng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion
di: Yang, Zhiwen, et al.
Pubblicazione: (2025)

Ego3DT: Tracking Every 3D Object in Ego-centric Videos
di: Hao, Shengyu, et al.
Pubblicazione: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
di: Zhang, Luyuan, et al.
Pubblicazione: (2026)

Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
di: Xu, Rui, et al.
Pubblicazione: (2025)

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
di: Wang, Gaoang, et al.
Pubblicazione: (2022)

Video Token Merging for Long-form Video Understanding
di: Lee, Seon-Ho, et al.
Pubblicazione: (2024)

HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing
di: Akl, Ahmed, et al.
Pubblicazione: (2026)

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
di: Sun, Zhichao, et al.
Pubblicazione: (2026)

Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs
di: Che, Liwei, et al.
Pubblicazione: (2025)

That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation
di: Pramatarov, Georgi, et al.
Pubblicazione: (2024)

Vision-centric Token Compression in Large Language Model
di: Xing, Ling, et al.
Pubblicazione: (2025)

Lossless Token Merging Even Without Fine-Tuning in Vision Transformers
di: Lee, Jaeyeon, et al.
Pubblicazione: (2025)

Self-Improving Small Object Grounding in LVLMs
di: Yang, Tianze, et al.
Pubblicazione: (2026)

Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
di: Shen, Meng, et al.
Pubblicazione: (2026)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
di: Sun, Han, et al.
Pubblicazione: (2026)

Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion
di: Hu, Qingguo, et al.
Pubblicazione: (2025)

Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
di: Hu, Wenhao, et al.
Pubblicazione: (2025)

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
di: Chen, Yangneng, et al.
Pubblicazione: (2026)

CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
di: Kan, Zhehan, et al.
Pubblicazione: (2024)

Object-centric Video Question Answering with Visual Grounding and Referring
di: Wang, Haochen, et al.
Pubblicazione: (2025)

ToSA: Token Merging with Spatial Awareness
di: Huang, Hsiang-Wei, et al.
Pubblicazione: (2025)

Video, How Do Your Tokens Merge?
di: Pollard, Sam, et al.
Pubblicazione: (2025)

Sequential Token Merging: Revisiting Hidden States
di: Wen, Yan, et al.
Pubblicazione: (2025)

R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
di: Xie, Jiahao, et al.
Pubblicazione: (2026)

Rethinking Image-to-Video Adaptation: An Object-centric Perspective
di: Qian, Rui, et al.
Pubblicazione: (2024)

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
di: Li, Siyuan, et al.
Pubblicazione: (2025)

Local Representative Token Guided Merging for Text-to-Image Generation
di: Lee, Min-Jeong, et al.
Pubblicazione: (2025)

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
di: Jin, Xin, et al.
Pubblicazione: (2025)

HTTM: Head-wise Temporal Token Merging for Faster VGGT
di: Wang, Weitian, et al.
Pubblicazione: (2025)

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
di: Zhang, Jie, et al.
Pubblicazione: (2024)

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement
di: Liu, Yun, et al.
Pubblicazione: (2024)

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
di: Fang, Haipeng, et al.
Pubblicazione: (2025)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
di: Zheng, Haohan, et al.
Pubblicazione: (2025)

Disjoint Contrastive Regression Learning for Multi-Sourced Annotations
di: Ruan, Xiaoqian, et al.
Pubblicazione: (2021)

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs
di: Ding, Xuan, et al.
Pubblicazione: (2025)

TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
di: Zhang, Zijian, et al.
Pubblicazione: (2025)

Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes
di: Jeong, Seunghoon, et al.
Pubblicazione: (2026)

ORIDa: Object-centric Real-world Image Composition Dataset
di: Kim, Jinwoo, et al.
Pubblicazione: (2025)

Deep Learning on Object-centric 3D Neural Fields
di: Ramirez, Pierluigi Zama, et al.
Pubblicazione: (2023)

DynaHOI: Benchmarking Hand-Object Interaction for Dynamic Target
di: Hu, BoCheng, et al.
Pubblicazione: (2026)