New research may help scientists predict when a humid heat wave will break
As these events become more common at midlatitudes, a phenomenon called an atmospheric inversion will determine how long they last.
Archives AI News
The Curse of Depth in Large Language Models
arXiv:2502.05795v3 Announce Type: replace Abstract: In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in modern Large Language Models (LLMs) where nearly half of the layers are less effective than…
Flattening Hierarchies with Policy Bootstrapping
arXiv:2505.14975v3 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language…
Generative Conditional Missing Imputation Networks
arXiv:2601.00517v1 Announce Type: cross Abstract: In this study, we introduce a sophisticated generative conditional strategy designed to impute missing values within datasets, an area of considerable importance in statistical analysis. Specifically, we initially elucidate the theoretical underpinnings of the Generative…
Density-Based Algorithms for Corruption-Robust Contextual Search and Convex Optimization
arXiv:2206.07528v3 Announce Type: replace Abstract: We study the problem of contextual search, a generalization of binary search in higher dimensions, in the adversarial noise model. Let $d$ be the dimension of the problem, $T$ be the time horizon and $C$…
Support Vector Machine Kernels as Quantum Propagators
arXiv:2502.11153v3 Announce Type: replace-cross Abstract: Selecting optimal kernels for regression in physical systems remains a challenge, often relying on trial-and-error with standard functions. In this work, we establish a mathematical correspondence between support vector machine kernels and quantum propagators, demonstrating…
Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients
arXiv:2512.23090v2 Announce Type: replace-cross Abstract: Recent Reinforcement Learning (RL) advances for Large Language Models (LLMs) have improved reasoning tasks, yet their resource-constrained application to medical imaging remains underexplored. We introduce ChexReason, a vision-language model trained via R1-style methodology (SFT followed…
Reinforcement Learning with Function Approximation for Non-Markov Processes
arXiv:2601.00151v1 Announce Type: new Abstract: We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable ergodicity conditions on the underlying…
Information-Theoretic Quality Metric of Low-Dimensional Embeddings
arXiv:2512.23981v2 Announce Type: replace Abstract: In this work we study the quality of low-dimensional embeddings from an explicitly information-theoretic perspective. We begin by noting that classical evaluation metrics such as stress, rank-based neighborhood criteria, or Local Procrustes quantify distortions in…
Dynamic Bayesian Optimization Framework for Instruction Tuning in Partial Differential Equation Discovery
arXiv:2601.00088v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise for equation discovery, yet their outputs are highly sensitive to prompt phrasing, a phenomenon we term instruction brittleness. Static prompts cannot adapt to the evolving state of a multi-step…