Stay updated with the latest research and technology news
arXiv:2602.20076v1 Announce Type: new Abstract: Solving safety-critical control problem has widely adopted the Control Barrier Function (CBF) method. However, the existence of a CBF is...
arXiv:2602.20078v1 Announce Type: new Abstract: Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise: when agents share a common reward, the actions...
arXiv:2602.20079v1 Announce Type: new Abstract: We present SemanticNVS, a camera-conditioned multi-view diffusion model for novel view synthesis (NVS), which improves generation quality and consistency by...
arXiv:2602.20080v1 Announce Type: new Abstract: Contemporary artificial intelligence (AI) policy suffers from a basic categorical error. Existing frameworks rely on analogizing AI to inherited technology...
arXiv:2602.20082v1 Announce Type: new Abstract: We report on using an agentic coding assistant (Claude Code, powered by Claude Opus 4.6) to mechanize a substantial Rocq...
arXiv:2602.20083v1 Announce Type: new Abstract: Deploying Retrieval-Augmented Generation (RAG) on edge devices is in high demand, but is hindered by the latency of massive data...
arXiv:2602.20084v1 Announce Type: new Abstract: Data visualization principles, derived from decades of research in design and perception, ensure proper visual communication. While prior work has...
arXiv:2602.20089v1 Announce Type: new Abstract: Edge-based representations are fundamental cues for visual understanding, a principle rooted in early vision research and still central today. We...
arXiv:2602.20091v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by conditioning generation on retrieved external documents, but the effect of retrieved...
arXiv:2602.20092v1 Announce Type: new Abstract: BabyLM aims to dissolve the boundaries between cognitive modeling and language modeling. We call for both workshop papers and for...
arXiv:2602.20093v1 Announce Type: new Abstract: Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning...
arXiv:2602.20094v1 Announce Type: new Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning...
arXiv:2602.20097v1 Announce Type: new Abstract: Error-bounded lossy compression has been regarded as a promising way to address the ever-increasing amount of scientific data in today's...
arXiv:2602.20100v1 Announce Type: new Abstract: The dependence on expert annotation has long constituted the primary rate-limiting step in the application of artificial intelligence to biomedicine....
arXiv:2602.20102v1 Announce Type: new Abstract: Despite the state-of-the-art performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content...
arXiv:2602.20104v1 Announce Type: new Abstract: In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet...
arXiv:2602.20105v1 Announce Type: new Abstract: Underwater Acoustic (UWA) networks are vital for remote sensing and ocean exploration but face inherent challenges such as limited bandwidth,...
arXiv:2602.20107v1 Announce Type: new Abstract: In this paper, we show how informativity and identifiability for networks of dynamical systems can be investigated using Gr\"obner bases....
arXiv:2602.20111v1 Announce Type: new Abstract: We study online learning in the adversarial injection model introduced by [Goel et al. 2017], where a stream of labeled...
arXiv:2602.20113v1 Announce Type: new Abstract: Voice style conversion aims to transform an input utterance to match a target speaker's timbre, accent, and emotion, with a...
arXiv:2602.20114v1 Announce Type: new Abstract: Research in machine unlearning (MU) has gained strong momentum: MU is now widely regarded as a critical capability for building...
arXiv:2602.20117v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging...
arXiv:2602.20119v1 Announce Type: new Abstract: Solving long-horizon tasks requires robots to integrate high-level semantic reasoning with low-level physical interaction. While vision-language models (VLMs) and video...
arXiv:2602.20120v1 Announce Type: new Abstract: Capstone projects are widely adopted by universities around the world as a culminating assessment in bachelor's degree programs. These projects...