Do LLMs Truly Understand When a Precedent Is Overruled?
Ottobre 27, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2510.20941v1 Announce Type: new Abstract: Large language models (LLMs) with extended context windows show promise...
DNACHUNKER: Learnable Tokenization for DNA Language Models
Gennaio 7, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2601.03019v1 Announce Type: cross Abstract: DNA language models have emerged as powerful tools for decoding...
Diversity or Precision? A Deep Dive into Next Token Prediction
Dicembre 30, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2512.22955v1 Announce Type: new Abstract: Recent advancements have shown that reinforcement learning (RL) can substantially...
Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models
Settembre 19, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2505.16245v3 Announce Type: replace Abstract: Diverse language model responses are crucial for creative generation, open-ended...
DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier
Gennaio 8, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2601.03605v1 Announce Type: new Abstract: Despite the significant advancements of Large Language Models (LLMs), their...
DiTTO-LLM: Framework for Discovering Topic-based Technology Opportunities via Large Language Model
Settembre 15, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2509.09724v1 Announce Type: new Abstract: Technology opportunities are critical information that serve as a foundation...
Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Ottobre 14, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2509.15888v3 Announce Type: replace Abstract: Adapting billion-parameter language models to a downstream task is still...
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
Gennaio 9, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2512.21002v2 Announce Type: replace Abstract: Distilling the capabilities from a large reasoning model (LRM) to...
Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
Ottobre 31, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2510.26271v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit uneven performance across languages, a problem...
