Stay updated with the latest research and technology news
arXiv:2602.10529v1 Announce Type: new Abstract: When designing a program, both novice programmers and seasoned developers alike often sketch out -- or, perhaps more famously, whiteboard...
arXiv:2602.10535v1 Announce Type: new Abstract: To foster effective human-agent interactions, designers need to identify characteristics that could affect how agents are perceived and accepted, and...
arXiv:2602.10539v1 Announce Type: new Abstract: Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded...
arXiv:2602.10540v1 Announce Type: new Abstract: This paper introduces a Theory of Troubleshooting that is rooted in cognitive science. This theory helps software developers explain the...
arXiv:2602.10541v1 Announce Type: new Abstract: Recent random feature methods for solving partial differential equations (PDEs) reduce computational cost compared to physics-informed neural networks (PINNs) but...
arXiv:2602.10542v1 Announce Type: new Abstract: Shannon theory models communication as the reliable transfer of symbol sequences, with performance governed by capacity and rate-distortion limits. When...
arXiv:2602.10543v1 Announce Type: new Abstract: Modern security, infrastructure, and safety-critical systems increasingly operate in environments characterised by disruption, uncertainty, physical damage, and degraded communications. Conventional...
arXiv:2602.10544v1 Announce Type: new Abstract: Automated EEG monitoring requires clinician-level precision for seizure detection and reporting. Clinical EEG recordings exceed LLM context windows, requiring extreme...
arXiv:2602.10545v1 Announce Type: new Abstract: Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency,...
arXiv:2602.10546v1 Announce Type: new Abstract: The rapid advancement of generative AI has raised concerns about the authenticity of digital images, as highly realistic fake images...
arXiv:2602.10547v1 Announce Type: new Abstract: Multi-sensor fusion is central to robust robotic perception, yet most existing systems operate under static sensor configurations, collecting all modalities...
arXiv:2602.10548v1 Announce Type: new Abstract: The HCI community has called for renewed attention to labor issues and the political economy of computing. Yet much work...
arXiv:2602.10549v1 Announce Type: new Abstract: Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text...
arXiv:2602.10550v1 Announce Type: new Abstract: In this paper, we propose a robust and efficient numerical framework for simulating multicomponent gas flow in poroelastic media, with...
arXiv:2602.10551v1 Announce Type: new Abstract: Recent advances in 3D Large Multimodal Models (LMMs) built on Large Language Models (LLMs) have established the alignment of 3D...
arXiv:2602.10552v1 Announce Type: new Abstract: Whereas most brain-computer interface research has focused on decoding neural signals into behavior or intent, the reverse challenge-using controlled stimuli...
arXiv:2602.10553v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled the development of multimodal medical AI. While models such as MedGemini...
arXiv:2602.10555v1 Announce Type: new Abstract: In this paper, the concept of Dynamic Contextual Mission Data (DCMD) is introduced to develop an ontology-driven dynamic knowledge base...
arXiv:2602.10556v1 Announce Type: new Abstract: A long-standing goal in robotics is a generalist policy that can be deployed zero-shot on new robot embodiments without per-embodiment...
arXiv:2602.10559v1 Announce Type: new Abstract: We study the algorithmic decidability of the domination number in the Erdos-Renyi random graph model $G(n,p)$. We show that for...
arXiv:2602.10560v1 Announce Type: new Abstract: While reasoning over long context is crucial for various real-world applications, it remains challenging for large language models (LLMs) as...
arXiv:2602.10561v1 Announce Type: new Abstract: This paper presents a closed-loop automation framework for heterogeneous modular robots, covering the full pipeline from morphological construction to adaptive...
arXiv:2602.10564v1 Announce Type: new Abstract: Federated fine-tuning of on-device large language models (LLMs) mitigates privacy concerns by preventing raw data sharing. However, the intensive computational...
arXiv:2602.10565v1 Announce Type: new Abstract: We propose and study an online version of min-max optimization based on cumulative saddle points under a variety of performance...