Stay updated with the latest research and technology news
arXiv:2602.07729v2 Announce Type: replace Abstract: Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs)...
arXiv:2602.07906v2 Announce Type: replace Abstract: Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show...
arXiv:2602.08274v3 Announce Type: replace Abstract: Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations....
arXiv:2602.08550v3 Announce Type: replace Abstract: Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and...
arXiv:2602.09448v2 Announce Type: replace Abstract: Prior synthetic query generation for dense retrieval produces one query per document, focusing on quality. We systematically study multi-query synthesis,...
arXiv:2602.10693v2 Announce Type: replace Abstract: Training stability remains a central challenge in reinforcement learning (RL) for large language models (LLMs). Policy staleness, asynchronous training, and...
arXiv:2602.10720v2 Announce Type: replace Abstract: The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the...
arXiv:2602.11184v2 Announce Type: replace Abstract: Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert...
arXiv:2602.11776v2 Announce Type: replace Abstract: In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of...
arXiv:2602.12194v2 Announce Type: replace Abstract: In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user installs the...
arXiv:2602.12656v2 Announce Type: replace Abstract: Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In...
arXiv:2602.13301v2 Announce Type: replace Abstract: Recent advances towards End-to-End Autonomous Driving (E2E-AD) have been often devoted on integrating modular designs into a unified framework for...
arXiv:2602.13314v3 Announce Type: replace Abstract: Millimeter-wave (mmWave) radar provides reliable perception in visually degraded indoor environments (e.g., smoke, dust, and low light), but learning-based radar...
arXiv:2602.13813v2 Announce Type: replace Abstract: We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained...
arXiv:2602.13932v2 Announce Type: replace Abstract: We introduce and study the Joint Task Assistance Planning problem which generalizes prior work on optimizing assistance in robotic collaboration....
arXiv:2602.14044v2 Announce Type: replace Abstract: Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While...
arXiv:2602.14281v3 Announce Type: replace Abstract: The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security...
arXiv:2602.14462v2 Announce Type: replace Abstract: Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter...
arXiv:2602.14495v2 Announce Type: replace Abstract: Scaling laws can be understood from ground-up numerical analysis, where traditional function approximation theory can explain shifts in model architecture...
arXiv:2602.14681v3 Announce Type: replace Abstract: LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among...
arXiv:2602.14733v2 Announce Type: replace Abstract: Large language models (LLMs) have been increasingly adopted to support patients' healthcare-seeking in recent years. While prior patient-centered studies have...
arXiv:2602.15997v3 Announce Type: replace Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across five model scales (405K--85M parameters),...
arXiv:2602.16042v2 Announce Type: replace Abstract: As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical...
arXiv:2602.16705v2 Announce Type: replace Abstract: Visual loco-manipulation of arbitrary objects in the wild with humanoid robots requires accurate end-effector (EE) control and a generalizable understanding...