Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
RynnVLA-001: Using human demonstrations to improve robot manipulation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Adaptive Action Chunking uses action entropy to dynamically adjust chunk sizes in VLA models, improving performance on simulated and real robotic manipulation tasks.
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.
citing papers explorer
-
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
-
Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
Adaptive Action Chunking uses action entropy to dynamically adjust chunk sizes in VLA models, improving performance on simulated and real robotic manipulation tasks.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
-
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.