Stay updated with the latest research and technology news
arXiv:2601.23183v1 Announce Type: new Abstract: We introduce JobResQA, a multilingual Question Answering benchmark for evaluating Machine Reading Comprehension (MRC) capabilities of LLMs on HR-specific tasks...
arXiv:2601.23184v1 Announce Type: new Abstract: While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent...
arXiv:2601.23185v1 Announce Type: new Abstract: In the context of training neural network-based approximations of solutions of parameter-dependent PDEs, we investigate the effect of preconditioning via...
arXiv:2601.23188v1 Announce Type: new Abstract: Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution....
arXiv:2601.23193v1 Announce Type: new Abstract: Network structure and its role in prediction are examined in competitive basketball at the team and player levels. Adversarial game...
arXiv:2601.23198v1 Announce Type: new Abstract: We study the complexity of counting (weighted) planar graph homomorphism problem $\tt{Pl\text{-}GH}(M)$ parametrized by an arbitrary symmetric non-negative real valued...
arXiv:2601.23200v1 Announce Type: new Abstract: Patent classification into CPC codes underpins large scale analyses of technological change but remains challenging due to its hierarchical, multi...
arXiv:2601.23204v1 Announce Type: new Abstract: Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science. While recent...
arXiv:2601.23206v1 Announce Type: new Abstract: Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and...
arXiv:2601.23207v1 Announce Type: new Abstract: Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge....
arXiv:2601.23209v1 Announce Type: new Abstract: Additive models of interaction performance, such as the Keystroke-Level Model (KLM), are tools that allow designers to compare and optimize...
arXiv:2601.23211v1 Announce Type: new Abstract: Consider a multi-agent systems setup in which a principal (a supervisor agent) assigns subtasks to specialized agents and aggregates their...
arXiv:2601.23213v1 Announce Type: new Abstract: Entropies are fundamental measures of uncertainty with central importance in information theory and statistics and applications across all the quantitative...
arXiv:2601.23215v1 Announce Type: new Abstract: Air pollution is a chronic problem in large cities worldwide and awareness is rising as the long-term health implications become...
arXiv:2601.23216v1 Announce Type: new Abstract: Sensing privacy and communication confidentiality play fundamentally different but interconnected roles in adversarial wireless environments. Capturing this interplay within a...
arXiv:2601.23219v1 Announce Type: new Abstract: In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to...
arXiv:2601.23220v1 Announce Type: new Abstract: Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a...
arXiv:2601.23221v1 Announce Type: new Abstract: As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical...
arXiv:2601.23222v1 Announce Type: new Abstract: While dense pixel-wise annotations remain the gold standard for medical image segmentation, they are costly to obtain and limit scalability....
arXiv:2601.23223v1 Announce Type: new Abstract: Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise...
arXiv:2601.23224v1 Announce Type: new Abstract: Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to...
arXiv:2601.23225v1 Announce Type: new Abstract: Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) -...
arXiv:2601.23226v1 Announce Type: new Abstract: Three-dimensional integrated circuit (3D IC) pack-aging and heterogeneous integration have emerged as central pillars of contemporary semiconductor scaling. Yet, the...
arXiv:2601.23228v1 Announce Type: new Abstract: While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges:...