📰 AI News

arXiv:2604.04485v1 Announce Type: cross Abstract: ECG biometrics has been studied mainly on small cohorts and short inter-session intervals, leaving open how id

arXiv:2604.04490v1 Announce Type: cross Abstract: This paper presents RAVEN, a computationally efficient deep learning architecture for FMCW radar perception. T

arXiv:2604.04493v1 Announce Type: cross Abstract: The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massi

arXiv:2604.04497v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulne

arXiv:2604.04516v1 Announce Type: cross Abstract: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new di

arXiv:2604.04518v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and auto

arXiv:2604.04527v1 Announce Type: cross Abstract: We present Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation,

arXiv:2604.04532v1 Announce Type: cross Abstract: Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show th

arXiv:2604.04552v1 Announce Type: cross Abstract: Ensemble methods are widely used to improve predictive performance, but their effectiveness often comes at the

arXiv:2604.04561v1 Announce Type: cross Abstract: LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not know

arXiv:2604.04562v1 Announce Type: cross Abstract: The accelerating pace of scientific publishing makes it increasingly difficult for researchers to stay current

arXiv:2604.04563v1 Announce Type: cross Abstract: Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyz

arXiv:2604.04565v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in question answering and retrieval-augmented ge

arXiv:2604.04593v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds large language models in external medical knowledge, yet standard

arXiv:2604.04603v1 Announce Type: cross Abstract: In this work, we address the problem of cardinality estimation for similarity search in high-dimensional space

arXiv:2604.04604v1 Announce Type: cross Abstract: AI agents - i.e. AI systems that autonomously plan, invoke external tools, and execute multi-step action chain

arXiv:2604.04614v1 Announce Type: cross Abstract: Deep learning-based modeling of multimodal Electronic Health Records (EHRs) has become an important approach f

arXiv:2604.04634v1 Announce Type: cross Abstract: The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media,

arXiv:2604.04646v1 Announce Type: cross Abstract: Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of

arXiv:2604.04655v1 Announce Type: cross Abstract: Neural network grokking -- the abrupt memorization-to-generalization transition -- challenges our understandin

arXiv:2604.04664v1 Announce Type: cross Abstract: The integration of large language models (LLMs) with embodied agents has improved high-level reasoning capabil

arXiv:2604.04670v1 Announce Type: cross Abstract: The rapid rise of LLMs over the last few years has promoted growing experimentation with LLM-driven AI tutors.

arXiv:2604.04690v1 Announce Type: cross Abstract: Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the hig

arXiv:2604.04692v1 Announce Type: cross Abstract: Automated fact-checking is a crucial task not only in journalism but also across web platforms, where it suppo