Learn and Unlearn: Addressing Misinformation in Multilingual LLMs
9月 4, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2406.13748v3 Announce Type: replace Abstract: This paper investigates the propagation of harmful information in multilingual...
Lean4: How the theorem prover works and why it’s the new competitive edge in AI
11月 23, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Large language models (LLMs) have astounded the world with their capabilities, yet they remain plagued...
LeakDojo: Decoding the Leakage Threats of RAG Systems
5月 8, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2605.05818v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage...
LayerNorm and RMS Norm in Transformer Models
6月 28, 2025admin NUAI,Committee,ニュース,Uncategorized(0)This post is divided into five parts; they are: • Why Normalization is Needed in...
Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
7月 4, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2503.00958v2 Announce Type: replace Abstract: We propose a new approach for the authorship attribution task...
Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
8月 15, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2508.10404v1 Announce Type: new Abstract: With the rapid proliferation of Natural Language Processing (NLP), especially...
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations
9月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.15655v1 Announce Type: new Abstract: Transformer-based speech language models (SLMs) have significantly improved neural speech...
Launching youth entrepreneurship
8月 26, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Even as a teenager, Laurie Stach ’06 says, she had a “crazy ambition to take...
Latent Visual Reasoning
9月 30, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.24251v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved notable gains in...
