⚡ AI-Lesson Articles

arXiv:2603.23059v1 Announce Type: new Abstract: Recent advances in game AI, such as AlphaZero and Ath\'enan, have achieved superhuman performance across a wide

arXiv:2603.23085v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with

arXiv:2603.23114v1 Announce Type: new Abstract: A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed

arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. Whi

arXiv:2603.23178v1 Announce Type: new Abstract: Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity

arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolv

arXiv:2603.23234v1 Announce Type: new Abstract: Large language model (LLM)-based agents rely on memory mechanisms to reuse knowledge from past problem-solving e

arXiv:2603.23244v1 Announce Type: new Abstract: When learning a novel complex task, people often form efficient reusable abstractions that simplify future work,

arXiv:2603.23292v1 Announce Type: new Abstract: Benchmarks and leaderboards are how NLP most often communicates progress, but in the LLM era they are increasing

arXiv:2603.23346v1 Announce Type: new Abstract: Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end sp

arXiv:2603.23406v1 Announce Type: new Abstract: While large language models simulate social behaviors, their capacity for stable stance formation and identity n

arXiv:2603.23420v1 Announce Type: new Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We take this

arXiv:2603.23433v1 Announce Type: new Abstract: Nudges are subtle changes to the way choices are presented to human decision-makers (e.g., opt-in vs. opt-out by

arXiv:2502.04188v1 Announce Type: cross Abstract: Documenting software architecture is essential to preserve architecture knowledge, even though it is frequentl

arXiv:2603.22287v1 Announce Type: cross Abstract: Large language model (LLM) families are improving rapidly, yet it remains unclear how quickly multimodal capab

arXiv:2603.22288v1 Announce Type: cross Abstract: Prompting strategies affect LLM reasoning performance, but their role in chart-based QA remains underexplored.

arXiv:2603.22289v1 Announce Type: cross Abstract: Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a

arXiv:2603.22292v1 Announce Type: cross Abstract: Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-bas

arXiv:2603.22293v1 Announce Type: cross Abstract: Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong re

arXiv:2603.22294v1 Announce Type: cross Abstract: Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and bro

arXiv:2603.22295v1 Announce Type: cross Abstract: Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion ne

arXiv:2603.22299v1 Announce Type: cross Abstract: Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essentia

arXiv:2603.22300v1 Announce Type: cross Abstract: Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing

arXiv:2603.22301v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete to