Stay updated with the latest research and technology news
arXiv:2602.07774v2 Announce Type: replace Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and...
arXiv:2602.07794v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured, human-like conceptual representations...
arXiv:2602.07837v2 Announce Type: replace Abstract: Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world...
arXiv:2602.07853v2 Announce Type: replace Abstract: In this paper, we introduce MPM Lite, a new hybrid Lagrangian/Eulerian method that eliminates the need for particle-based quadrature at...
arXiv:2602.07868v2 Announce Type: replace Abstract: This paper presents a new deterministic algorithm for single-source shortest paths (SSSP) on real non-negative edge-weighted directed graphs, with running...
arXiv:2602.07870v2 Announce Type: replace Abstract: Movable antenna (MA) has emerged as a promising technology for future wireless systems. Compared with traditional fixed-position antennas, MA improves...
arXiv:2602.07872v2 Announce Type: replace Abstract: Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured...
arXiv:2602.07999v2 Announce Type: replace Abstract: In this paper, we propose a novel class of change of measure inequalities via a unified framework based on the...
arXiv:2602.08023v2 Announce Type: replace Abstract: Real-world offensive security operations are inherently open-ended: attackers explore unknown attack surfaces, revise hypotheses under uncertainty, and operate without guaranteed...
arXiv:2602.08030v2 Announce Type: replace Abstract: Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance...
arXiv:2602.08060v2 Announce Type: replace Abstract: LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety...
arXiv:2602.08146v2 Announce Type: replace Abstract: Software testing is a critical, yet resource-intensive phase of the software development lifecycle. Over the years, various automated tools have...
arXiv:2602.08224v2 Announce Type: replace Abstract: Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its...
arXiv:2602.08268v2 Announce Type: replace Abstract: Personal data centralization among dominant platform providers including search engines, social networking services, and e-commerce has created siloed ecosystems that...
arXiv:2602.08296v2 Announce Type: replace Abstract: We present MonkeyTree, the first system to mitigate network congestion in multi-tenant GPU clusters through job-migration based defragmentation rather than...
arXiv:2602.08321v2 Announce Type: replace Abstract: Solving open-ended science questions remains challenging for large language models, particularly due to inherently unreliable supervision and evaluation. The bottleneck...
arXiv:2602.08355v2 Announce Type: replace Abstract: E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal...
arXiv:2602.08425v2 Announce Type: replace Abstract: Bimanual manipulation is imperative yet challenging for robots to execute complex tasks, requiring coordinated collaboration between two arms. However, existing...
arXiv:2602.08491v2 Announce Type: replace Abstract: Food segmentation models trained on static images have achieved strong performance on benchmark datasets; however, their reliability in video settings...
arXiv:2602.08528v2 Announce Type: replace Abstract: Image reconstruction in X-ray tomography is an ill-posed inverse problem, particularly with limited available data. Regularization is thus essential, but...
arXiv:2602.08533v2 Announce Type: replace Abstract: Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations:...
arXiv:2602.08586v2 Announce Type: replace Abstract: Multi-agent collaboration has emerged as a promising paradigm for enhancing reasoning capabilities of Large Language Models (LLMs). However, existing approaches...
arXiv:2602.08658v2 Announce Type: replace Abstract: Deduction, induction, and abduction are fundamental reasoning paradigms, core for human logical thinking. Although improving Large Language Model (LLM) reasoning...
arXiv:2602.08668v2 Announce Type: replace Abstract: Hybrid Retrieval-Augmented Generation (RAG) pipelines combine vector similarity search with knowledge graph expansion for multi-hop reasoning. We show that this...