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.
A path towards autonomous machine intelligence version 0.9
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.
Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.
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.
-
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.
-
Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.