Cover Image

Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	li, Bonan, Zhang, Zicheng, Liu, Songhua, Yu, Weihao, Wang, Xinchao
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

Control and Realism: Best of Both Worlds in Layout-to-Image without Training
by: Li, Bonan, et al.
Published: (2025)

LinFusion: 1 GPU, 1 Minute, 16K Image
by: Liu, Songhua, et al.
Published: (2024)

Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
by: Li, Bonan, et al.
Published: (2024)

Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching
by: Yu, Ruonan, et al.
Published: (2024)

Rethinking Large-scale Dataset Compression: Shifting Focus From Labels to Images
by: Xiao, Lingao, et al.
Published: (2025)

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
by: Liu, Songhua, et al.
Published: (2024)

CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
by: Zhou, Letian, et al.
Published: (2025)

MambaOut: Do We Really Need Mamba for Vision?
by: Yu, Weihao, et al.
Published: (2024)

Attention Prompting on Image for Large Vision-Language Models
by: Yu, Runpeng, et al.
Published: (2024)

One-shot Federated Learning via Synthetic Distiller-Distillate Communication
by: Zhang, Junyuan, et al.
Published: (2024)

Ultra-Resolution Adaptation with Ease
by: Yu, Ruonan, et al.
Published: (2025)

Vision Bridge Transformer at Scale
by: Tan, Zhenxiong, et al.
Published: (2025)

Understanding Dataset Distillation via Spectral Filtering
by: Bo, Deyu, et al.
Published: (2025)

Flash Sculptor: Modular 3D Worlds from Objects
by: Hu, Yujia, et al.
Published: (2025)

Instruction Tuning-free Visual Token Complement for Multimodal LLMs
by: Wang, Dongsheng, et al.
Published: (2024)

Distilled Datamodel with Reverse Gradient Matching
by: Ye, Jingwen, et al.
Published: (2024)

Heavy Labels Out! Dataset Distillation with Label Space Lightening
by: Yu, Ruonan, et al.
Published: (2024)

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
by: Yu, Ruonan, et al.
Published: (2026)

OminiControl2: Efficient Conditioning for Diffusion Transformers
by: Tan, Zhenxiong, et al.
Published: (2025)

Introducing Visual Perception Token into Multimodal Large Language Model
by: Yu, Runpeng, et al.
Published: (2025)

Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
by: Zhang, Taolin, et al.
Published: (2024)

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
by: Liu, Yuhe, et al.
Published: (2026)

MindBridge: A Cross-Subject Brain Decoding Framework
by: Wang, Shizun, et al.
Published: (2024)

NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
by: Ren, Lingfeng, et al.
Published: (2026)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
by: Zhu, Jiaying, et al.
Published: (2025)

Video-Infinity: Distributed Long Video Generation
by: Tan, Zhenxiong, et al.
Published: (2024)

Image Editing As Programs with Diffusion Models
by: Hu, Yujia, et al.
Published: (2025)

End-to-End Vision Tokenizer Tuning
by: Wang, Wenxuan, et al.
Published: (2025)

UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning
by: Guan, Jiajin, et al.
Published: (2025)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
by: Gao, Juntao, et al.
Published: (2025)

In-Video Instructions: Visual Signals as Generative Control
by: Fang, Gongfan, et al.
Published: (2025)

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
by: Endo, Mark, et al.
Published: (2024)

EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
by: Lu, Hongyu, et al.
Published: (2026)

Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding
by: Liu, Yang, et al.
Published: (2024)

Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View
by: Zhang, Zitong, et al.
Published: (2025)

Personalized Visual Instruction Tuning
by: Pi, Renjie, et al.
Published: (2024)

SpotEdit: Selective Region Editing in Diffusion Transformers
by: Qin, Zhibin, et al.
Published: (2025)

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

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)