Stay updated with the latest research and technology news
arXiv:2603.02017v1 Announce Type: new Abstract: Federated Learning (FL) was initially proposed as a privacy-preserving machine learning paradigm. However, FL has been shown to be susceptible...
arXiv:2603.02019v1 Announce Type: new Abstract: Selection as Power argued that upstream selection authority, rather than internal objective misalignment, constitutes a primary source of risk in...
arXiv:2603.02022v1 Announce Type: new Abstract: Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech. Existing methods often rely on...
arXiv:2603.02023v1 Announce Type: new Abstract: Test-time scaling has shown that allocating more additional computation at inference can improve generation quality, motivating a natural follow-up question:...
arXiv:2603.02024v1 Announce Type: new Abstract: Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks...
arXiv:2603.02025v1 Announce Type: new Abstract: Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the...
arXiv:2603.02028v1 Announce Type: new Abstract: Vision transformers have demonstrated outstanding performance on image generation applications, but their adoption in scientific disciplines, like fluid dynamics, has...
arXiv:2603.02029v1 Announce Type: new Abstract: Moving beyond evaluations that collapse performance across heterogeneous prompts toward fine-grained evaluation at the prompt level, or within relatively homogeneous...
arXiv:2603.02031v1 Announce Type: new Abstract: Forward Error Correction (FEC) is used ubiquitously in the communication pipeline. We explore noncooperative decoding where we aim to recover...
arXiv:2603.02032v1 Announce Type: new Abstract: The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA). While causality-based RCA methods have...
arXiv:2603.02035v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) provide advanced reasoning for autonomous driving, translating their discrete semantic knowledge into continuous trajectories...
arXiv:2603.02041v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly trained on English-centric data, resulting in uneven performance for smaller languages. We study whether...
arXiv:2603.02043v1 Announce Type: new Abstract: Leave-one-out (LOO) prediction provides a principled, data-dependent measure of generalization, yet guarantees in fully transductive settings remain poorly understood beyond...
arXiv:2603.02045v1 Announce Type: new Abstract: Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer...
arXiv:2603.02047v1 Announce Type: new Abstract: The nicotine addiction public health crisis continues to be pervasive. In this century alone, the tobacco industry has released and...
arXiv:2603.02048v1 Announce Type: new Abstract: Heat-induced air turbulence produces complex, depth-dependent image distortions that are challenging to reproduce interactively because thermally driven flow must be...
arXiv:2603.02049v1 Announce Type: new Abstract: Recent advances in foundational Video Diffusion Models (VDMs) have yielded significant progress. Yet, despite the remarkable visual quality of generated...
arXiv:2603.02050v1 Announce Type: new Abstract: Human collaborators coordinate dynamically through process visibility and workspace awareness, yet AI agents typically either provide only final outputs or...
arXiv:2603.02052v1 Announce Type: new Abstract: Teenagers are avid users of Discord, a fast growing platform for synchronous communication where they often interact with strangers. Because...
arXiv:2603.02055v1 Announce Type: new Abstract: Personal AI assistants have changed how people use institutional and professional advice. We study this new strategic setting in which...
arXiv:2603.02056v1 Announce Type: new Abstract: Understanding how people allocate visual attention is central to Human-Computer Interaction (HCI), yet existing computational models of attention are often...
arXiv:2603.02057v1 Announce Type: new Abstract: Large language model (LLM) services have become an integral part of search, assistance, and decision-making applications. However, unlike traditional web...
arXiv:2603.02061v1 Announce Type: new Abstract: Accurate signal-to-interference-plus-noise ratio (SINR) estimation is essential for resource allocation in wireless systems, yet it is often hindered by limited...
arXiv:2603.02062v1 Announce Type: new Abstract: The rapid developments in artificial intelligence (AI) research in radiology have produced numerous models that are scattered across various platforms...