arXiv:2606.10025v1 Announce Type: cross Abstract: We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution. GHOST factorizes control into (i) a high-level policy that predicts the next sub-goal as a distribution over 3D end-effector…
arXiv:2606.09873v1 Announce Type: new Abstract: Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer. Yet the internal structure of representation space when reasoning remains poorly understood: how do a model’s…
arXiv:2606.10237v1 Announce Type: cross Abstract: Genetic programming (GP) is based on two important insights. First, that any learning task can fundamentally be posed as a program induction problem, where the goal is to construct a symbolic hierarchical model that is…
arXiv:2606.09874v1 Announce Type: new Abstract: Reconstruction-based methods are widely used for time series anomaly detection, where models are trained to reconstruct subsequences, and anomalies are identified through reconstruction errors. However, reported results are often hard to compare due to heterogeneous…
arXiv:2606.10562v1 Announce Type: cross Abstract: We propose a new optimization method, the Nystr”om-enhanced relaxed scalar auxiliary variable method (N-RSAV), which incorporates curvature information into the RSAV framework to accelerate convergence while preserving an unconditional modified energy dissipation law. Existing RSAV-based…
arXiv:2606.09875v1 Announce Type: new Abstract: Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment. Existing methods rely predominantly on token-level signals, leaving the geometric structure of intermediate hidden states underused. In this paper, we take the…
arXiv:2606.10857v1 Announce Type: cross Abstract: We present a generalist position control policy capable of controlling arbitrary multirotor configurations of a certain rotor count (e.g., hexarotors or quadrotors) with a single set of network weights. The policy is conditioned on a…
arXiv:2606.09876v1 Announce Type: new Abstract: Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted confidence but also risking erosion of warranted confidence on correct…
arXiv:2606.11063v1 Announce Type: cross Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model’s trajectory. If the trusted model detects such an…
arXiv:2606.09877v1 Announce Type: new Abstract: LLM wiki systems compile knowledge into pre-filled KV caches for efficient inference, but assume a static corpus — an assumption that fails whenever the underlying information landscape evolves. We formalize Streaming Knowledge Compilation: given a…
