Stay updated with the latest research and technology news
arXiv:2602.04830v1 Announce Type: new Abstract: Software Engineering (SE) faces simultaneous pressure from AI automation (reducing code production costs) and hardware-energy constraints (amplifying failure costs). We...
arXiv:2602.04832v1 Announce Type: new Abstract: Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why...
arXiv:2602.04836v1 Announce Type: new Abstract: Rapidly increasing AI capabilities have substantial real-world consequences, ranging from AI safety concerns to labor market consequences. The Model Evaluation...
arXiv:2602.04837v1 Announce Type: new Abstract: Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined...
arXiv:2602.04838v1 Announce Type: new Abstract: With the advancement of 3D scanning technologies, point clouds have become fundamental for representing 3D spatial data, with applications that...
arXiv:2602.04841v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations...
arXiv:2602.04842v1 Announce Type: new Abstract: Matrix-vector algorithms, particularly Krylov subspace methods, are widely viewed as the most effective algorithms for solving large systems of linear...
arXiv:2602.04843v1 Announce Type: new Abstract: Reasoning language models, which generate long chains of thought, dramatically outperform non-reasoning language models on abstract problems. However, the internal...
arXiv:2602.04846v1 Announce Type: new Abstract: We introduce CSLib, an open-source framework for proving computer-science-related theorems and writing formally verified code in the Lean proof assistant....
arXiv:2602.04847v1 Announce Type: new Abstract: As computer systems continue to diversify across technologies, architectures, applications, and beyond, the relevant design space has become larger and...
arXiv:2602.04851v1 Announce Type: new Abstract: Pose and motion priors play a crucial role in humanoid robotics. Although such priors have been widely studied in human...
arXiv:2602.04852v1 Announce Type: new Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the state...
arXiv:2602.04853v1 Announce Type: new Abstract: Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed...
arXiv:2602.04856v1 Announce Type: new Abstract: From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the...
arXiv:2602.04861v1 Announce Type: new Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading...
arXiv:2602.04862v1 Announce Type: new Abstract: Low Earth orbit (LEO) satellite systems experience significant Doppler effects due to high mobility. While Doppler shifts can be largely...
arXiv:2602.04863v1 Announce Type: new Abstract: Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors,...
arXiv:2602.04864v1 Announce Type: new Abstract: Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in...
arXiv:2602.04868v1 Announce Type: new Abstract: Continual reinforcement learning (CRL) requires agents to learn from a sequence of tasks without forgetting previously acquired policies. In this...
arXiv:2602.04870v1 Announce Type: new Abstract: Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through...
arXiv:2602.04871v1 Announce Type: new Abstract: This study explores how EU integration, globalisation, and geopolitical disruptions have influenced scientific collaboration among European countries at different stages...
arXiv:2602.04873v1 Announce Type: new Abstract: Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than...
arXiv:2602.04876v1 Announce Type: new Abstract: We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works...
arXiv:2602.04877v1 Announce Type: new Abstract: Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art...