Cover Image

D-Attn: Decomposed Attention for Large Vision-and-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kuo, Chia-Wen, Zhu, Sijie, Chen, Fan, Shen, Xiaohui, Wen, Longyin
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

Where do Large Vision-Language Models Look at when Answering Questions?
by: Xing, Xiaoying, et al.
Published: (2025)

VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing
by: Deng, Andong, et al.
Published: (2026)

Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
by: Xu, Lu, et al.
Published: (2024)

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
by: Li, Jiachen, et al.
Published: (2024)

Vidi: Large Multimodal Models for Video Understanding and Editing
by: Vidi Team, et al.
Published: (2025)

Multi-Reward as Condition for Instruction-based Image Editing
by: Gu, Xin, et al.
Published: (2024)

Edit3K: Universal Representation Learning for Video Editing Components
by: Gu, Xin, et al.
Published: (2024)

Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
by: Bui, Phuoc-Nguyen, et al.
Published: (2025)

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing
by: Li, Ming, et al.
Published: (2025)

Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning
by: Gu, Xin, et al.
Published: (2025)

DiTFastAttn: Attention Compression for Diffusion Transformer Models
by: Yuan, Zhihang, et al.
Published: (2024)

MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
by: Setyawan, Novendra, et al.
Published: (2025)

Vidi2.5: Large Multimodal Models for Video Understanding and Creation
by: Vidi Team, et al.
Published: (2025)

Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving
by: Setyawan, Novendra, et al.
Published: (2025)

DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions
by: Ates, Gorkem Can, et al.
Published: (2025)

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
by: You, Haoxuan, et al.
Published: (2023)

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
by: Chen, Jieneng, et al.
Published: (2024)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
by: Chen, Junjie, et al.
Published: (2025)

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
by: Zhang, Hanling, et al.
Published: (2025)

Accurate and Fast Compressed Video Captioning
by: Shen, Yaojie, et al.
Published: (2023)

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
by: Jiang, Zhangqi, et al.
Published: (2024)

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
by: Zhang, Hongyu, et al.
Published: (2025)

AttnMod: Attention-Based New Art Styles
by: Su, Shih-Chieh
Published: (2024)

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
by: Zhang, Hongyu, et al.
Published: (2026)

GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways
by: Ghoshal, Soudeep, et al.
Published: (2026)

One Last Attention for Your Vision-Language Model
by: Chen, Liang, et al.
Published: (2025)

Referring Layer Decomposition
by: Chen, Fangyi, et al.
Published: (2026)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
by: Liu, Xuewen, et al.
Published: (2025)

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
by: Zhu, Wenxuan, et al.
Published: (2025)

FlexAttention for Efficient High-Resolution Vision-Language Models
by: Li, Junyan, et al.
Published: (2024)

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
by: Jin, Hyundong, et al.
Published: (2026)

AttnRouter: Per-Category Attention Routing for Training-Free Image Editing on MMDiT
by: Li, Guandong, et al.
Published: (2026)

ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding
by: Setyawan, Novendra, et al.
Published: (2024)

MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers
by: Setyawan, Novendra, et al.
Published: (2026)

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models
by: Zhao, Qiyan, et al.
Published: (2025)

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
by: Yang, Jiabing, et al.
Published: (2025)

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
by: Lan, Mengcheng, et al.
Published: (2024)

FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device
by: Setyawan, Novendra, et al.
Published: (2025)

A Hierarchical Slice Attention Network for Appendicitis Classification in 3D CT Scans
by: Huang, Chia-Wen, et al.
Published: (2025)

ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning
by: Luo, Wen, et al.
Published: (2026)