CoViST: Visual Token Compression via Composable States

arXiv:2609.33397 · cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Pruning — 45× in this paper · explained in 4 episodes
• Vision-language models — 13× in this paper · explained in 2 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• State-Conditioned Attention — 5× in this paper
• Generative AI — 4× in this paper · explained in 2 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Coupled State Composition — 2× in this paper
• Coverage-Guided State Initialization — 2× in this paper
• Frozen model — 2× in this paper · explained in 3 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• Training-Free Framework — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Semantic Drift — 1× in this paper · explained in 3 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• Qwen2.5-VL Technical Report
• ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
• STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models
• Stepwise Token Selection for Efficient Multimodal Large Language Models
• Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs
• TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
• OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
• Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs
• LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
• EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
• RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
• When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
• When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
• TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection