Stay updated with the latest research and technology news
arXiv:2602.16455v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide...
arXiv:2602.16456v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and...
arXiv:2602.16459v1 Announce Type: new Abstract: In this letter, we develop a continuous fluid antenna (FA) framework for uplink channel estimation in cell-free massive multiple-input and...
arXiv:2602.16462v1 Announce Type: new Abstract: Reactive motion generation in dynamic and unstructured scenarios is typically subject to essentially static perception and system dynamics. Reliably modeling...
arXiv:2602.16467v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) necessitates evaluation frameworks that reflect real-world academic rigor and multilingual complexity. This...
arXiv:2602.16468v1 Announce Type: new Abstract: In long-term multivariate time series forecasting, effectively capturing both periodic patterns and residual dynamics is essential. To address this within...
arXiv:2602.16469v1 Announce Type: new Abstract: Machine-translated data is widely used in multilingual NLP, particularly when native text is scarce. However, translated text differs systematically from...
arXiv:2602.16473v1 Announce Type: new Abstract: C-RASP is a simple programming language that was recently shown to capture concepts expressible by transformers. In this paper, we...
arXiv:2602.16475v1 Announce Type: new Abstract: We present a framework to \emph{certify} Hamilton--Jacobi (HJ) reachability learned by reinforcement learning (RL). Building on a discounted initial time...
arXiv:2602.16480v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without exposing clients' private data, and has been widely adopted in privacy-sensitive scenarios....
arXiv:2602.16481v1 Announce Type: new Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the...
arXiv:2602.16485v1 Announce Type: new Abstract: Existing Multi-Agent Systems (MAS) typically rely on static, homogeneous model configurations, limiting their ability to exploit the distinct strengths of...
arXiv:2602.16488v1 Announce Type: new Abstract: Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in...
arXiv:2602.16489v1 Announce Type: new Abstract: With the rise of artificial intelligence and machine learning, a new wave of private information is being flushed into applications....
arXiv:2602.16490v1 Announce Type: new Abstract: Looping, reusing a block of layers across depth, and depth growing, training shallow-to-deep models by duplicating middle layers, have both...
arXiv:2602.16493v1 Announce Type: new Abstract: Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger...
arXiv:2602.16494v1 Announce Type: new Abstract: Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to...
arXiv:2602.16498v1 Announce Type: new Abstract: Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes posterior...
arXiv:2602.16499v1 Announce Type: new Abstract: The Asset Administration Shell (AAS) is an emerging technology for the implementation of digital twins in the field of manufacturing....
arXiv:2602.16500v1 Announce Type: new Abstract: Soft prompt tuning leverages continuous embeddings to capture task-specific information in large pre-trained language models (LLMs), achieving competitive performance in...
arXiv:2602.16502v1 Announce Type: new Abstract: Recent advances in garment pattern generation have shown promising progress. However, existing feed-forward methods struggle with diverse poses and viewpoints,...
arXiv:2602.16503v1 Announce Type: new Abstract: Generalized additive models (GAMs) offer interpretability through independent univariate feature effects but underfit when interactions are present in data. GA$^2$Ms...
arXiv:2602.16507v1 Announce Type: new Abstract: One of the central challenges in the computational analysis of liquid chromatography-tandem mass spectrometry (LC-MS/MS) data is to identify the...
arXiv:2602.16508v1 Announce Type: new Abstract: We consider a stochastic heat equation with nonlinear multiplicative finite-dimensional noise that admits a unique nonnegative solution when given nonnegative...