⚡ AI-Lesson Articles

arXiv:2603.23524v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enabl

arXiv:2603.23529v1 Announce Type: cross Abstract: Large Language Models (LLMs) consistently under perform in low-resource linguistic contexts such as Konkani. T

arXiv:2603.23530v1 Announce Type: cross Abstract: Large language models often fail to satisfy formatting instructions when they must simultaneously perform dema

arXiv:2603.23532v1 Announce Type: cross Abstract: This paper investigates whether structured representations can preserve the meaning of scientific sentences. T

arXiv:2603.23533v1 Announce Type: cross Abstract: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic unit

arXiv:2603.23543v1 Announce Type: cross Abstract: We explore the capabilities of Large Language Models (LLMs) by comparing the way they gather data with the way

arXiv:2603.23554v1 Announce Type: cross Abstract: Textual graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing

arXiv:2603.23558v1 Announce Type: cross Abstract: Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifyin

arXiv:2603.23559v1 Announce Type: cross Abstract: GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs

arXiv:2603.23562v1 Announce Type: cross Abstract: Synthetic data augmentation helps language models learn new knowledge in data-constrained domains. However, na

arXiv:2603.23565v1 Announce Type: cross Abstract: Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-wor

arXiv:2603.23566v1 Announce Type: cross Abstract: AscendC (Ascend C) operator optimization on Huawei Ascend neural processing units (NPUs) faces a two-fold know

arXiv:2603.23571v1 Announce Type: cross Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sust

arXiv:2603.23573v1 Announce Type: cross Abstract: Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances increme

arXiv:2603.23574v1 Announce Type: cross Abstract: Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in impr

arXiv:2603.23575v1 Announce Type: cross Abstract: Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code g

arXiv:2603.23576v1 Announce Type: cross Abstract: Understanding wafer-level spatial variations from in-situ process signals is essential for advanced plasma etc

arXiv:2603.23582v1 Announce Type: cross Abstract: Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliab

arXiv:2603.23584v1 Announce Type: cross Abstract: Anti-money laundering (AML) systems are important for protecting the global economy. However, conventional rul

arXiv:2603.23611v1 Announce Type: cross Abstract: Automated testing is essential for evaluating and improving the reliability of Large Language Models (LLMs), y

arXiv:2603.23613v1 Announce Type: cross Abstract: Large Language Models (LLMs) are showing remarkable performance in generating source code, yet the generated c

arXiv:2603.23626v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fun

arXiv:2603.23627v1 Announce Type: cross Abstract: This study presents a benchmark for evaluating the Visual Word Sense Disambiguation (Visual-WSD) task in Ukrai

arXiv:2603.23646v1 Announce Type: cross Abstract: While recent work has benchmarked large language models on Swiss legal translation (Niklaus et al., 2025) and