Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation
juin 26, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2506.19998v1 Announce Type: new Abstract: REST APIs play important roles in enriching the action space...
Do reasoning models really “think” or not? Apple research sparks lively debate, response
juin 14, 2025admin NUAI,Committee,Actualités,Uncategorized(0)Ultimately, the big takeaway for ML researchers is that before proclaiming an AI milestone—or obituary—make...
Do Not Change Me: On Transferring Entities Without Modification in Neural Machine Translation — a Multilingual Perspective
mai 12, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2505.06010v1 Announce Type: new Abstract: Current machine translation models provide us with high-quality outputs in...
Do Multilingual LLMs have specialized language heads?
février 10, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2602.08625v1 Announce Type: new Abstract: Multilingual large language models (LLMs) have gained significant popularity for...
Do LLMs Truly Understand When a Precedent Is Overruled?
octobre 27, 2025admin NUAI,Committee,Actualités,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
janvier 7, 2026admin NUAI,Committee,Actualités,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
décembre 30, 2025admin NUAI,Committee,Actualités,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
septembre 19, 2025admin NUAI,Committee,Actualités,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
janvier 8, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2601.03605v1 Announce Type: new Abstract: Despite the significant advancements of Large Language Models (LLMs), their...
