Stay updated with the latest research and technology news
arXiv:2602.03086v1 Announce Type: new Abstract: The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization,...
arXiv:2602.03087v1 Announce Type: new Abstract: Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly...
arXiv:2602.03089v1 Announce Type: new Abstract: Incels, or "involuntary celibates", are an extreme, misogynistic hate group that exists entirely online. Members of the community have been...
arXiv:2602.03090v1 Announce Type: new Abstract: The quality of a user's social media experience is determined both by the content they see and by the quality...
arXiv:2602.03092v1 Announce Type: new Abstract: Food choices shape both human and planetary health; yet, designing foods that are delicious, nutritious, and sustainable remains challenging. Here...
arXiv:2602.03093v1 Announce Type: new Abstract: The heterogeneity in the organization of software engineering (SE) research historically exists, i.e., funded research model and hands-on model, which...
arXiv:2602.03094v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable...
arXiv:2602.03095v1 Announce Type: new Abstract: The Kaiping Diaolou and Villages, a UNESCO World Heritage Site, exemplify hybrid Chinese and Western architecture shaped by migration culture....
arXiv:2602.03096v1 Announce Type: new Abstract: We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an...
arXiv:2602.03097v1 Announce Type: new Abstract: Professional job recommendation involves a complex bipartite matching process that must reconcile a candidate's subjective preference with an employer's objective...
arXiv:2602.03098v1 Announce Type: new Abstract: Expanding multimodal representations to novel modalities is constrained by reliance on large-scale paired datasets (e.g., text-image, text-audio, text-3D, text-molecule), which...
arXiv:2602.03100v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic harm....
arXiv:2602.03102v1 Announce Type: new Abstract: Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility...
arXiv:2602.03103v1 Announce Type: new Abstract: Instruction tuning is now the default way to train and adapt large language models, but many instruction--input--output pairs are only...
arXiv:2602.03104v1 Announce Type: new Abstract: Generative Artificial Intelligence (GenAI) is increasingly integrated into photo applications on personal devices, making editing photographs easier than ever while...
arXiv:2602.03105v1 Announce Type: new Abstract: Establishing correspondences between image pairs is a long studied problem in computer vision. With recent large-scale foundation models showing strong...
arXiv:2602.03107v1 Announce Type: new Abstract: From a pragmatic perspective, this study systematically evaluates the differences in performance among representative large language models (LLMs) in recognizing...
arXiv:2602.03108v1 Announce Type: new Abstract: We introduce ChemPro, a progressive benchmark with 4100 natural language question-answer pairs in Chemistry, across 4 coherent sections of difficulty...
arXiv:2602.03109v1 Announce Type: new Abstract: This paper introduces OMAR: One Model, All Roles, a reinforcement learning framework that enables AI to develop social intelligence through...
arXiv:2602.03112v1 Announce Type: new Abstract: End-to-end autonomous driving is increasingly adopting a multimodal planning paradigm that generates multiple trajectory candidates and selects the final plan,...
arXiv:2602.03114v1 Announce Type: new Abstract: Rapid innovations in AI and large language models (LLMs) have accelerated the adoption of digital learning, particularly beyond formal education....
arXiv:2602.03117v1 Announce Type: new Abstract: AI agents that autonomously interact with external tools and environments show great promise across real-world applications. However, the external data...
arXiv:2602.03118v1 Announce Type: new Abstract: According to Noether's theorem the presence of a continuous symmetry in a Hamiltonian systems is equivalent to the existence of...
arXiv:2602.03119v1 Announce Type: new Abstract: Bayesian deep learning (BDL) provides a principled framework for reliable uncertainty quantification by combining deep neural networks with Bayesian inference....