DFM-VLA uses discrete flow matching to iteratively refine action tokens in VLA models, outperforming autoregressive and diffusion baselines with 4.44 average success length on CALVIN and 95.7% success on LIBERO.
arXiv preprint arXiv:2506.13725 (2025)
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
VLA-AD distills 7B VLA teachers into 158M students using offline VLM semantic guidance on task phases and directions, matching teacher performance on LIBERO with 44x size reduction and 3.28x speedup.
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 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.
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.
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.
OmniVLA-RL uses a mix-of-transformers architecture and flow-matching reformulated as SDE with group segmented policy optimization to surpass prior VLA models on LIBERO benchmarks.
citing papers explorer
-
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.