Localmax dynamics for attention in transformers and its asymptotic behavior
September 22, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2509.15958v1 Announce Type: new Abstract: We introduce a new discrete-time attention model, termed the localmax...
Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning
September 25, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2506.00236v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, offer compact and...
LLMs Struggle with Real Conversations: Microsoft and Salesforce Researchers Reveal a 39% Performance Drop in Multi-Turn Underspecified Tasks
Mai 18, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)Conversational artificial intelligence is centered on enabling large language models (LLMs) to engage in dynamic...
LLMs for Customized Marketing Content Generation and Evaluation at Scale
Juni 24, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2506.17863v1 Announce Type: new Abstract: Offsite marketing is essential in e-commerce, enabling businesses to reach...
LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models
Juni 9, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2506.05385v1 Announce Type: new Abstract: Semantic role labeling (SRL) is a crucial task of natural...
LLMs are stuck in a groupthink groove. This startup is trying to get them out.
Juli 1, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Let’s start with a game. Open up your chatbot of choice—Claude, ChatGPT, Gemini—and type “Give...
LLM-Pruning Collection: A JAX Based Repo For Structured And Unstructured LLM Compression
Januar 5, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Zlab Princeton researchers have released LLM-Pruning Collection, a JAX based repository that consolidates major pruning...
LLM-Independent Adaptive RAG: Let the Question Speak for Itself
Mai 8, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2505.04253v1 Announce Type: new Abstract: Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation...
LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm
September 15, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2509.09707v1 Announce Type: cross Abstract: Integrating Large Language Models (LLMs) within metaheuristics opens a novel...
