V-CoLA: Vision Token Compression with Linear Attention

arXiv:2610.11251 · cs.CV, cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Hybrid Architectures — 11× in this paper · explained in 3 episodes
• Pruning — 10× in this paper · explained in 4 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Aggregation — 6× in this paper · explained in 1 episode
• Accuracy — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Multimodal Inputs — 3× in this paper · explained in 2 episodes
• Redundancy — 3× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Associative Memory — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes

Sources

• Simple linear attention language models balance the recall-throughput tradeoff
• Qwen3-VL Technical Report
• Token Merging: Your ViT But Faster
• AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
• Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers
• LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
• Repeat After Me: Transformers are Better than State Space Models at Copying
• SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
• Token Sequence Compression for Efficient Multimodal Computing
• Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
• OpenAI GPT-5 System Card
• InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
• Kimi Linear: An Expressive, Efficient Attention Architecture
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
• PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
• Gated Delta Networks: Improving Mamba2 with Delta Rule
• A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models