Stay updated with the latest research and technology news
arXiv:2602.22108v1 Announce Type: new Abstract: In the One-Fast-Many-Slow decision problem, introduced by Sheffield and Westover (ITCS '25), a scheduler, with access to one fast machine...
arXiv:2602.22110v1 Announce Type: new Abstract: We consider the robust permutation flowshop problem under the budgeted uncertainty model, where at most a given number of job...
arXiv:2602.22115v1 Announce Type: new Abstract: Neural networks (NNs) are pervasive across various domains but often lack interpretability. To address the growing need for explanations, logic-based...
arXiv:2602.22120v1 Announce Type: new Abstract: Text-to-image (T2I) models are rapidly gaining popularity, yet their outputs often lack geographical diversity, reinforce stereotypes, and misrepresent regions. Given...
arXiv:2602.22124v1 Announce Type: new Abstract: Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models...
arXiv:2602.22125v1 Announce Type: new Abstract: Instruction-following benchmarks remain predominantly English-centric, leaving a critical evaluation gap for the hundreds of millions of Indic language speakers. We...
arXiv:2602.22130v1 Announce Type: new Abstract: We study the basic task of mean estimation in the presence of mean-shift contamination. In the mean-shift contamination model, an...
arXiv:2602.22131v1 Announce Type: new Abstract: Augmentative and Alternative Communication (AAC) technologies are categorized into two forms: aided AAC, which uses external devices like speech-generating systems...
arXiv:2602.22132v1 Announce Type: new Abstract: Speculative design uses provocative "what if?" scenarios to explore possible sociotechnical futures, yet lacks rigorous criteria for assessing the quality...
arXiv:2602.22133v1 Announce Type: new Abstract: Accurate and efficient uncertainty quantification is essential for resilience assessment of modern power systems under high impact and low probability...
arXiv:2602.22134v1 Announce Type: new Abstract: Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this AI-native architecture also introduces new...
arXiv:2602.22136v1 Announce Type: new Abstract: Deep neural networks (DNNs) are essential for performing advanced tasks on edge or mobile devices, yet their deployment is often...
arXiv:2602.22142v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline...
arXiv:2602.22143v1 Announce Type: new Abstract: Medical vision-language pretraining increasingly relies on medical reports as large-scale supervisory signals; however, raw reports often exhibit substantial stylistic heterogeneity,...
arXiv:2602.22144v1 Announce Type: new Abstract: Object hallucination is a critical issue in Large Vision-Language Models (LVLMs), where outputs include objects that do not appear in...
arXiv:2602.22145v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to ``professionalize'' workplace communication, often at the cost of linguistic identity. We introduce...
arXiv:2602.22146v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) plays a significant role in aligning Large Language Models (LLMs) with human preferences. While...
arXiv:2602.22149v1 Announce Type: new Abstract: Cardiovascular disease (CVD) remains one of the leading global health challenges, accounting for more than 19 million deaths worldwide. To...
arXiv:2602.22150v1 Announce Type: new Abstract: Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for...
arXiv:2602.22152v1 Announce Type: new Abstract: Most contemporary neural learning systems rely on epoch-based optimization and repeated access to historical data, implicitly assuming reversible computation. In...
arXiv:2602.22154v1 Announce Type: new Abstract: Coordinated collective motion in bird flocks and fish schools inspires algorithms for cohesive swarm robotics. This paper presents a position-based...
arXiv:2602.22157v1 Announce Type: new Abstract: The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their...
arXiv:2602.22158v1 Announce Type: new Abstract: Checkpointing is essential for fault tolerance in training large language models (LLMs). However, existing methods, regardless of their I/O strategies,...
arXiv:2602.22159v1 Announce Type: new Abstract: Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur,...