Machine learning models have recently emerged to predict whether hypothetical solid-state materials can be synthesized. These models aim to circumvent direct first-principles modeling of solid-state phase transformations, instead learning from large databases of successfully synthesized materials. Here, we assess the alignment of several recently introduced synthesis prediction models with material and reaction thermodynamics, quantified by the energy with respect to the convex hull and a metric accounting for thermodynamic selectivity of enumerated synthesis reactions. A dataset of successful […]

Ver mais

arXiv:2602.10714v1 Announce Type: cross Abstract: Preconditioning is a common method applied to modify Markov chain Monte Carlo algorithms with the goal of making them more efficient. In practice it is often extremely effective, even when the preconditioner is learned from the chain. We analyse and compare the finite-time computational costs of schemes which learn a preconditioner based on the target covariance or the expected Hessian of the target potential with that of a corresponding scheme that does not […]

Ver mais

arXiv:2604.16954v1 Announce Type: new Abstract: Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a textbf{T}opology-Aware Learning with textbf{S}emantic textbf{M}amba for Category-Level textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation […]

Ver mais

arXiv:2601.00141v1 Announce Type: new Abstract: The rapid development of generative AI has made AI-generated images increasingly realistic and high-resolution. Most AI-generated image detection architectures typically downsample images before inputting them into models, risking the loss of fine-grained details. This paper presents GLASS (Global-Local Attention with Stratified Sampling), an architecture that combines a globally resized view with multiple randomly sampled local crops. These crops are original-resolution regions efficiently selected through spatially stratified sampling and aggregated using attention-based scoring. GLASS […]

Ver mais

Running a Rainbow DQN ablation on Snake (C51 + dueling + noisy nets). When I evaluated checkpoints with noise off (mean weights, sigma zeroed out, the standard approach), the scores were all over the place. Some checkpoints averaged 78, others averaged 18. Training curve at those same points was perfectly stable. First instinct was a bug. Checked everything. It wasn’t. The worst case was at ep450K. Deterministic eval produced a bimodal distribution: ~25% of episodes scored near zero, […]

Ver mais

Last month, I became aware of GitHub agentic workflows. I read the site carefully, but the use cases weren’t very exciting to me. I tried the continuous documentation It didn’t work out initially, and because of my lack of involvement, I left it as it was. However, I succeeded in another one that I want to describe in this post. Note: With lessons learned here, I managed to make the documentation workflow work! Every relevant change now creates […]

Ver mais

arXiv:2606.06772v1 Announce Type: new Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory. While recent advances, particularly works under the Neural Tangent Kernel (NTK) regime, have shed light on the behavior of shallow architectures, the statistical generalization properties of deep neural networks (DNNs), especially in regression tasks, remain far less understood. In this paper, we make significant progress toward closing this gap by providing a comprehensive generalization analysis of […]

Ver mais

arXiv:2604.18639v1 Announce Type: new Abstract: Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the substantial annotation cost and issues such as model collapse or reward hacking. To address these issues, we introduce a new perspective inspired by cognitive learning theory and propose a novel approach called EasyRL. The core of EasyRL is to simulate the human […]

Ver mais

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in […]

Ver mais