arXiv AI
TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 25
TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning
Vision-language-action (VLA) models are increasingly used for robot manipulation because they map camera images and a language instruction directly to actions. Robots that cannot be tethered to a work...
arXiv AI
Jun 9
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
arXiv:2606. 08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.
arXiv Computer Vision
Aug 27
Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation
The paper introduces Interaction‑Aligned Pruning (IAprune), a training‑free method for visual token pruning in embodied manipulation tasks. IAprune jointly decides per‑frame budget and token selection, using semantic‑motion spatial agreement to choose between conservative and aggressive coverage, and applies geometric residual correction to focus on under‑represented boundaries. Experiments on four policies, three simulation benchmarks, and a real‑robot platform show that IAprune matches unpruned performance on LIBERO while achieving up to 1.54× speed‑up and 1.48× acceleration on a real robot.
arXiv Computer Vision
Oct 1
D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-actio...
arXiv AI
Jul 29
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.
arXiv AI
Oct 9
ActionCodec: What Makes for Good Action Tokenizers
The paper "ActionCodec: What Makes for Good Action Tokenizers" addresses the lack of design guidance for action tokenization in Vision‑Language‑Action (VLA) models. By deriving information‑theoretic principles—maximizing temporal token overlap, reducing vocabulary redundancy, boosting multimodal mutual information, and ensuring token independence—the authors propose ActionCodec, a tokenizer that improves training efficiency and VLA performance. Experiments show that a SmolVLM2‑2.2B fine‑tuned with ActionCodec reaches a 95.5 % success rate on LIBERO, rising to 97.4 % with architectural tweaks, setting a new state‑of‑the‑art for VLA models without robotics pre‑training.