NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
Fabian Mentzer, David Minnen, Eirikur Agustsson, and Michael Tschannen
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 6years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
Discrete action tokenization in VLA models creates an information bottleneck that prevents vision encoder scaling from improving performance, unlike continuous policies, as validated on the LIBERO benchmark.
VQActFlow discretizes action chunks via vector quantization, generates code sequences with variational flow matching, and applies inference-time guidance to steer multi-task robot policies toward instructed and feasible modes.
Autoregressive VLA policies achieve real-time execution via tokenization horizon adjustment and constrained decoding, outperforming flow-matching policies in speed and performance across simulated and real environments.
citing papers explorer
-
NAC: Neural Action Codec for Vision-Language-Action Models
NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
-
ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
-
The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling
Discrete action tokenization in VLA models creates an information bottleneck that prevents vision encoder scaling from improving performance, unlike continuous policies, as validated on the LIBERO benchmark.
-
VQActFlow: Vector-Quantized Action Mode Steering for Multi-Task Robot Manipulation
VQActFlow discretizes action chunks via vector quantization, generates code sequences with variational flow matching, and applies inference-time guidance to steer multi-task robot policies toward instructed and feasible modes.
-
Real-Time Execution with Autoregressive Policies
Autoregressive VLA policies achieve real-time execution via tokenization horizon adjustment and constrained decoding, outperforming flow-matching policies in speed and performance across simulated and real environments.