8 accepted papers
A key requirement for generalist robots is compositional generalization—the ability to combine atomic skills to solve complex, long-horizon tasks. While prior work has primarily focused on synthesizing a planner that sequences pre-learned skills, robust execution of the individual skills themselves …
This paper presents a simple, effective, and cost-efficient strategy, named ModelSwitch, to improve LLM performance by scaling test-time compute. ModelSwitch builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage the
We present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">generative predictive control</i> (GPC), a framework for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">inference-time</i> enhancement of pr
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we introduce \textbf{MAGIC}, a novel multi-turn multi-agent rei…
We initiate a study of the geometry of the visual representation space ---the information channel from the vision encoder to the action decoder--- in an image-based control pipeline learned from behavior cloning. Inspired by the phenomenon of *neural collapse* (NC) in image classification, we empiri…
We investigate uncertainty quantification of 6D pose estimation from learned noisy measurements (e.g., keypoints and pose hypotheses). Assuming unknown-but-bounded measurement noises, a pose uncertainty set (PURSE) is a subset of SE(3) that contains all possible 6D poses compatible with the measurem…
In this paper, we study the stochastic multi-armed bandit problem with graph feedback. Motivated by the clinical trials and recommendation problem, we assume that two arms are connected if and only if they are similar (i.e., their means are close enough). We establish a regret lower bound for this…
The goal in offline data-driven decision-making is synthesize decisions that optimize a black-box utility function, using a previously-collected static dataset, with no active interaction. These problems appear in many forms: offline reinforcement learning (RL), where we must produce actions that op…