Stay updated with the latest research and technology news
arXiv:2602.06799v1 Announce Type: new Abstract: Ambiguity poses persistent challenges in natural language understanding for large language models (LLMs). To better understand how lexical ambiguity can...
arXiv:2602.06800v1 Announce Type: new Abstract: Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine...
arXiv:2602.06801v1 Announce Type: new Abstract: Activation steering methods, such as persona vectors, are widely used to control large language model behavior and increasingly interpreted as...
arXiv:2602.06805v1 Announce Type: new Abstract: In this technical note, we derive a closed-form expression for the affine transformation mapping local image patches between two calibrated...
arXiv:2602.06806v1 Announce Type: new Abstract: Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work...
arXiv:2602.06807v1 Announce Type: new Abstract: We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids...
arXiv:2602.06808v1 Announce Type: new Abstract: In this paper, we propose a dynamical low-rank (DLR) approximation framework for solving the semiclassical Schrodinger equation with uncertainties. The...
arXiv:2602.06810v1 Announce Type: new Abstract: Tabular anomaly detection (TAD) remains challenging due to the heterogeneity of tabular data: features lack natural relationships, vary widely in...
arXiv:2602.06811v1 Announce Type: new Abstract: Flapping-wing micro air vehicles (FWMAVs) have demonstrated remarkable bio-inspired agility, yet tailless two-winged configurations remain largely unexplored due to their...
arXiv:2602.06817v1 Announce Type: new Abstract: In this paper, we present a generic parametrization of generically zero-dimensional parametric polynomial systems. More specifically, we study the specialization...
arXiv:2602.06818v1 Announce Type: new Abstract: Human concept learning is typically active: learners choose which instances to query or test in order to reduce uncertainty about...
arXiv:2602.06820v1 Announce Type: new Abstract: Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce,...
arXiv:2602.06822v1 Announce Type: new Abstract: Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during inference,...
arXiv:2602.06823v1 Announce Type: new Abstract: AI music generators have advanced to the point where their outputs are often indistinguishable from human compositions. While detection methods...
arXiv:2602.06825v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as...
arXiv:2602.06827v1 Announce Type: new Abstract: In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component...
arXiv:2602.06830v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting simplification methods commonly use importance scores, such as blending weights or sensitivity, to identify redundant Gaussians....
arXiv:2602.06831v1 Announce Type: new Abstract: Ensuring software quality in embedded firmware is critical, especially in safety-critical domains where compliance with functional safety standards (ISO 26262)...
arXiv:2602.06834v1 Announce Type: new Abstract: Visual servoing is fundamental to robotic applications, enabling precise positioning and control. However, applying it to textureless objects remains a...
arXiv:2602.06836v1 Announce Type: new Abstract: We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash...
arXiv:2602.06837v1 Announce Type: new Abstract: Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial...
arXiv:2602.06838v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity, non-independent,...
arXiv:2602.06841v1 Announce Type: new Abstract: Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs...
arXiv:2602.06842v1 Announce Type: new Abstract: Deep learning-based hybrid iterative methods (DL-HIMs) integrate classical numerical solvers with neural operators, utilizing their complementary spectral biases to accelerate...