Discrete diffusion policies support native asynchronous execution via unmasking for real-time chunking, delivering higher success rates and 0.7x inference cost versus flow-matching RTC on dynamic robotics benchmarks and real pick tasks.
Kinetix: Investigating the training of general agents through open-ended physics-based control tasks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
Controlled benchmarks show per-step residual correction (A2C2) as most effective for VLA asynchronous inference up to d=8 delays on Kinetix with over 90% solve rate, outperforming inpainting and conditioning while training-based simulation is most robust.
citing papers explorer
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies support native asynchronous execution via unmasking for real-time chunking, delivering higher success rates and 0.7x inference cost versus flow-matching RTC on dynamic robotics benchmarks and real pick tasks.
-
Goal-Conditioned Agents that Learn Everything All at Once
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
-
Real-Time Execution of Action Chunking Flow Policies
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
-
Understanding Asynchronous Inference Methods for Vision-Language-Action Models
Controlled benchmarks show per-step residual correction (A2C2) as most effective for VLA asynchronous inference up to d=8 delays on Kinetix with over 90% solve rate, outperforming inpainting and conditioning while training-based simulation is most robust.
- TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning