arXiv:2605.05026v1 Announce Type: cross Abstract: Diffusion models are prone to generating structural hallucinations – samples that match the statistical properties of the training data yet defy underlying structural rules, resulting in anomalies like hands with more than five fingers. Recent research studied this failure mode from several viewpoints, offering partial explanations to their occurrence, such […]
Quantile-Free Uncertainty Quantification in Graph Neural Networks
arXiv:2605.04847v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often relies on strong assumptions such as exchangeability, which are rarely satisfied in practice. Moreover, achieving reliable UQ typically requires costly resampling or post-hoc calibration. To address […]
Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models
arXiv:2605.05090v1 Announce Type: cross Abstract: We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models. Given a base model $M_1$ and an intervention model $M_2$, our method compares their free-form, multi-token generations across aligned prompt contexts and produces human-readable, statistically validated natural-language hypotheses describing how the models […]
MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis
arXiv:2604.15729v2 Announce Type: replace-cross Abstract: Whole Slide Image (WSI) analysis is pivotal in computational pathology, enabling cancer diagnosis by integrating morphological and architectural cues across magnifications. Multiple Instance Learning (MIL) serves as the standard framework for WSI analysis. Recently, Mamba has become a promising backbone for MIL, overtaking Transformers due to its efficiency and global […]
Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
arXiv:2605.05125v1 Announce Type: cross Abstract: Target trial emulation (TTE) enables causal questions to be studied with observational data when randomized controlled trials (RCTs) are infeasible. Yet treatment-effect methods often address causal estimation, missingness, and temporal structure separately, limiting their robustness in electronic health records (EHRs), where time-varying confounding and missing-not-at-random (MNAR) biomarkers can reach 50%–80%. […]
A Rational Account of Categorization Based on Information Theory
arXiv:2603.29895v3 Announce Type: replace Abstract: We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how well it can account for key findings from classic categorization experiments conducted by Hayes-Roth and Hayes-Roth (1977), Medin and Schaffer (1978), and Smith and Minda (1998). We find that it […]
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
arXiv:2605.05172v1 Announce Type: cross Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been collected. Existing offline-to-online learning methods often cause policies to replace previously learned good actions due to a distribution mismatch between offline data and online […]
Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
arXiv:2605.02740v2 Announce Type: replace Abstract: Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, […]
Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage
arXiv:2506.07548v2 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most methods train agents at a single fixed difficulty throughout the entire run. We term this static-difficulty regime environmental meta-stationarity and show that it caps policy generalization and steers learning toward shallow local optima. To […]
Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
arXiv:2605.05151v1 Announce Type: cross Abstract: Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time series data remains unexplored. The persistent competitiveness of simple linear models such as DLinear has fueled ongoing debate, but no mechanistic explanation for this phenomenon […]
High-fidelity robotic PCR amplification
arXiv:2512.23877v3 Announce Type: replace Abstract: Polymerase chain reaction (PCR) underpins modern molecular biology, yet its deployment in emerging domains such as DNA data storage and distributed diagnostics remains constrained by bulky thermocyclers, complex thermal hardware, and contamination-prone workflows. Here, we present an autonomous robotic PCR platform that redefines thermocycling as a motion-controlled process rather than […]
QHap: Quantum-Inspired Haplotype Phasing
arXiv:2603.25762v2 Announce Type: replace Abstract: Haplotype phasing, the process of resolving parental allele inheritance patterns in diploid genomes, is critical for precision medicine and population genetics, yet the underlying optimization is NP-hard, posing a scalability challenge. To address this, we introduce QHap, a haplotype phasing algorithm that leverages quantum-annealing-inspired optimization. By reformulating haplotype phasing as […]