This paper investigates whether adults' struggles with conjunctive causal rules persist when they have agency through active exploration.

This paper studies failure modes of Direct Feedback Alignment (DFA) training and isolates two distinct gain mechanisms: activity conditioning and error conditioning.

Incorporating short-term synaptic plasticity (STP) into a PFC-inspired reservoir model significantly stabilizes goal-conditioned dynamics, particularly under state noise, suggesting STP dynamically mo…

This paper introduces a 'Sleep' paradigm for machine learning models to continually learn and transfer knowledge.

A new framework called subject-conditioned residual diffusion generates personalized lower-limb kinematics at unseen walking speeds from a subject's gait sequence at a single seen speed.

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 synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

ASPIRE is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm, discovering transferable skills and surpassing prior methods on various…

This paper proposes a new formulation of Bayesian experimental design (BED) based on expected future loss (EFL) on downstream actions, which can be optimized using stochastic gradients and does not re…

SPAR introduces a novel framework that rectifies action policies by performing local fine-tuning in a residual space anchored to a pure behavior cloning policy, achieving state-of-the-art performance…

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

This paper proposes grouping recorded actions in Programming by Demonstration (PbD) into labeled, hierarchical subgoals and evaluates the effect on plan quality.

The paper introduces DigitalCoach, a dataset of human expert-novice computer use coaching sessions, and evaluates the ability of state-of-the-art models to teach humans how to use computers.

This paper presents ABot-C0, a motion-control system for quadruped robots, which includes a scalable multi-source motion-data pipeline, robust policy learning, and a unified deployment stack for real-…

This paper introduces a proactive multi-modal assistant system and a large-scale dataset for procedural assistance.

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…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

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…

This paper proposes a method for hierarchically parsing long-form audio data into order-consistent Act-Sub-Event parse trees using Hierarchical Activity Grammar.