The Implicit Drifting Policy (IDP) is a novel one-step action generation framework that implicitly enforces trajectory correction constraints by analyzing local expert action geometry, overcoming the…

The paper proposes VERA, a decoupled policy that uses an action-free video world model combined with an embodiment-specific Inverse Dynamics Model (IDM) to achieve generalizable, zero-shot robot contr…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…

This paper studies how to scale robust robot policies by expanding physical domains in a recoverable way.

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significant…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

GLOVES is a flow-based adaptation method that selectively corrects non-expert robot actions by guiding them toward a task-specific expert action distribution, thereby improving performance while maint…

The paper introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse m…

ReSkill is an RL-in-the-loop framework that reconciles skill creation and policy optimization by automatically creating, testing, and refining modular skills alongside the agent's policy learning, lea…

This paper investigates the phenomenon of 'copying' in Distribution Matching Distillation (DMD), finding that high-dimensional distillation causes student models to spontaneously reproduce the teacher…

The paper introduces using frozen, generalist value functions as differentiable surrogates to efficiently optimize and analyze new multi-embodiment robot designs without requiring repeated reinforceme…

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

The paper proposes using distributional Reinforcement Learning (RL) to stabilize learning in chaotic dynamical systems by optimizing the smooth evolution of the return distribution rather than individ…

The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…