Stay updated with the latest research and technology news
arXiv:2602.03051v1 Announce Type: new Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a high demand for efficient compression...
arXiv:2602.03052v1 Announce Type: new Abstract: Federated learning enables collaborative model training across decentralized clients under privacy constraints. Quantum computing offers potential for alleviating computational and...
arXiv:2602.03053v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which...
arXiv:2602.03054v1 Announce Type: new Abstract: Co-design is essential for grounding embodied artificial intelligence (AI) systems in real-world contexts, especially high-stakes domains such as healthcare. While...
arXiv:2602.03059v1 Announce Type: new Abstract: We introduce Speech-to-Spatial, a referent disambiguation framework that converts verbal remote-assistance instructions into spatially grounded AR guidance. Unlike prior systems...
arXiv:2602.03060v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when...
arXiv:2602.03061v1 Announce Type: new Abstract: Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and...
arXiv:2602.03064v1 Announce Type: new Abstract: Real-world scenes are inherently crowded. Hence, estimating 3D poses of all nearby humans, tracking their movements over time, and understanding...
arXiv:2602.03066v1 Announce Type: new Abstract: One of the chronic problems of deep-learning models is shortcut learning. In a case where the majority of training data...
arXiv:2602.03067v1 Announce Type: new Abstract: Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at...
arXiv:2602.03068v1 Announce Type: new Abstract: Simulation-based theory development has yielded powerful insights into collective performance by linking social structure to emergent outcomes, yet it has...
arXiv:2602.03069v1 Announce Type: new Abstract: The advancement of data-driven materials science is currently constrained by a fundamental bottleneck: the vast majority of historical experimental data...
arXiv:2602.03070v1 Announce Type: new Abstract: Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging...
arXiv:2602.03071v1 Announce Type: new Abstract: Weakly supervised temporal video grounding aims to localize query-relevant segments in untrimmed videos using only video-sentence pairs, without requiring ground-truth...
arXiv:2602.03072v1 Announce Type: new Abstract: The logic of definitions is a family of logics for encoding and reasoning about judgments, which are atomic predicates specified...
arXiv:2602.03073v1 Announce Type: new Abstract: Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on...
arXiv:2602.03074v1 Announce Type: new Abstract: Coded polynomial aggregation (CPA) in distributed computing systems enables the master to directly recover a weighted aggregation of polynomial computations...
arXiv:2602.03075v1 Announce Type: new Abstract: Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for...
arXiv:2602.03076v1 Announce Type: new Abstract: Artificial intelligence (AI) has shown promise in detecting and characterizing musculoskeletal diseases from radiographs. However, most existing models remain task-specific,...
arXiv:2602.03081v1 Announce Type: new Abstract: Dynamic scheduling of task graphs is often addressed without revisiting prior task allocations, with a primary focus on minimizing makespan....
arXiv:2602.03082v1 Announce Type: new Abstract: Preserving geometric structure is important in learning. We propose a unified class of geometry-aware architectures that interleave geometric updates between...
arXiv:2602.03083v1 Announce Type: new Abstract: We propose a novel error analysis framework for scaled generalized Laguerre and generalized Hermite approximations.This framework can be regarded as...
arXiv:2602.03084v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved significant success in complex reasoning but remain bottlenecked by reliance on expert-annotated data and...
arXiv:2602.03085v1 Announce Type: new Abstract: Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a...