Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

arXiv:2608.21247 · cs.CV, cs.RO · Submitted 2026-08-21 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-08-21

Updated: 2026-09-21

Comments: 15 pages, 5 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Pruning — 89× in this paper · explained in 4 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• VLA Models — 14× in this paper · explained in 3 episodes
• KV cache — 13× in this paper · explained in 3 episodes
• Redundancy — 13× in this paper · explained in 2 episodes
• KV cache reuse — 10× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Closed-Loop Control — 8× in this paper · explained in 3 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Action Chunking — 2× in this paper · explained in 1 episode
• Semantic Understanding — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Kullback-Leibler (KL) Divergence — 1× in this paper · explained in 3 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
• Token Merging: Your ViT But Faster
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
• DMOFC: Discrimination Metric-Optimized Feature Compression
• Embodied Image Compression
• OpenVLA: An Open-Source Vision-Language-Action Model
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• Octo: An Open-Source Generalist Robot Policy
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
• SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
• The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
• Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
• SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
• Just Noticeable Difference for Large Multimodal Models
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

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