ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
The distracting con- trol suite–a challenging benchmark for reinforcement learning from pixels
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Factorizing pixel transitions into a learned codebook of patch-level motion primitives, then gating them into latent actions, transfers across morphologies and matches or beats monolithic latent-action baselines in distractor-heavy control tasks.
Extending linear LAMs to model exogenous state shows standard reconstruction encodes future exogenous info in latent actions, while endogenous-focused spaces and auxiliary objectives like action-supervision enforce consistency across noise.
ELVIS achieves state-of-the-art results on 14 visual control tasks and zero-shot real-world transfer by using ensemble-calibrated lambda-returns and Gaussian-mixture MPPI inside a latent RSSM planner.
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
citing papers explorer
-
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
-
Latent Actions from Factorized Transition Effects under Agent Ambiguity
Factorizing pixel transitions into a learned codebook of patch-level motion primitives, then gating them into latent actions, transfers across morphologies and matches or beats monolithic latent-action baselines in distractor-heavy control tasks.
-
Why Latent Actions Fail, and How to Prevent It
Extending linear LAMs to model exogenous state shows standard reconstruction encodes future exogenous info in latent actions, while endogenous-focused spaces and auxiliary objectives like action-supervision enforce consistency across noise.
-
ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
ELVIS achieves state-of-the-art results on 14 visual control tasks and zero-shot real-world transfer by using ensemble-calibrated lambda-returns and Gaussian-mixture MPPI inside a latent RSSM planner.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.