VLA-InfoEntropy accelerates Vision-Language-Action model inference by using visual entropy, attention entropy, and timestep cues to prune redundant tokens while preserving task-critical content.
The better you learn, the smarter you prune: Towards efficient vision- language-action models via differentiable token pruning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
OxyGen unifies KV cache management in MoT VLAs to enable cross-task KV sharing and cross-frame continuous batching, delivering up to 3.7x speedup with 200+ tokens/s language and 70 Hz action on on-device platforms.
ActDistill transfers action knowledge from heavy VLA teacher models to lightweight students via graph-encapsulated hierarchies and action-guided dynamic routing, delivering over 50% computation reduction and 1.67x speedup with comparable or better performance on embodied tasks.
LiteVLA-H delivers 19.74 Hz action tokens and 6 Hz semantic outputs on Jetson Orin via dual-rate scheduling and mixed fine-tuning, outperforming recent VLA baselines in edge action rate while preserving descriptive competence.
Parameter differences from two training runs on a small task set are treated as auxiliary capability vectors that are merged into a pretrained VLA model, yielding auxiliary-task gains at the cost of ordinary supervised finetuning plus a simple regularization term.
AVA-VLA reformulates VLA learning as a POMDP using recurrent states and active visual attention to achieve state-of-the-art results on LIBERO, CALVIN, and real dual-arm tasks.
citing papers explorer
-
VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success
VLA-InfoEntropy accelerates Vision-Language-Action model inference by using visual entropy, attention entropy, and timestep cues to prune redundant tokens while preserving task-critical content.
-
FASTER: Rethinking Real-Time Flow VLAs
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
-
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
OxyGen unifies KV cache management in MoT VLAs to enable cross-task KV sharing and cross-frame continuous batching, delivering up to 3.7x speedup with 200+ tokens/s language and 70 Hz action on on-device platforms.
-
ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
ActDistill transfers action knowledge from heavy VLA teacher models to lightweight students via graph-encapsulated hierarchies and action-guided dynamic routing, delivering over 50% computation reduction and 1.67x speedup with comparable or better performance on embodied tasks.
-
LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception
LiteVLA-H delivers 19.74 Hz action tokens and 6 Hz semantic outputs on Jetson Orin via dual-rate scheduling and mixed fine-tuning, outperforming recent VLA baselines in edge action rate while preserving descriptive competence.
-
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
Parameter differences from two training runs on a small task set are treated as auxiliary capability vectors that are merged into a pretrained VLA model, yielding auxiliary-task gains at the cost of ordinary supervised finetuning plus a simple regularization term.
-
AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
AVA-VLA reformulates VLA learning as a POMDP using recurrent states and active visual attention to achieve state-of-the-art results on LIBERO, CALVIN, and real dual-arm tasks.