Prefix-RFT: A Unified Machine Learning Framework to blend Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT)
สิงหาคม 24, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)Large language models are typically refined after pretraining using either supervised fine-tuning (SFT) or reinforcement...
Predicting the Performance of Black-box LLMs through Self-Queries
พฤศจิกายน 19, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2501.01558v3 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly relied on in...
Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
ตุลาคม 15, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2510.12121v1 Announce Type: cross Abstract: Precise attribute intensity control–generating Large Language Model (LLM) outputs with...
Pre-trained Transformer-Based Approach for Arabic Question Answering : A Comparative Study
สิงหาคม 6, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2111.05671v2 Announce Type: replace Abstract: Question answering(QA) is one of the most challenging yet widely...
Pragmatic Reasoning improves LLM Code Generation
พฤศจิกายน 7, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2502.15835v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated impressive potential in translating...
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
มกราคม 28, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2601.19895v1 Announce Type: cross Abstract: Large language model (LLM) scaling is hitting a wall. Widening...
Position: The Real Barrier to LLM Agent Usability is Agentic ROI
กุมภาพันธ์ 6, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2505.17767v2 Announce Type: replace Abstract: Large Language Model (LLM) agents represent a promising shift in...
Pose-Based Sign Language Appearance Transfer
เมษายน 30, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2410.13675v2 Announce Type: replace-cross Abstract: We introduce a method for transferring the signer’s appearance in...
PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response
กรกฎาคม 31, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)PolyAI has introduced Dialog-RSN-1, a dialog model that perceives the caller’s audio directly instead of...
