Vocabulary Customization for Efficient Domain-Specific LLM Deployment
10月 1, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.26124v1 Announce Type: new Abstract: When using an LLM to process text outside the training...
VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
7月 29, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2507.19995v1 Announce Type: new Abstract: The advent of large language models (LLMs) has led to...
vLLM vs TensorRT-LLM vs HF TGI vs LMDeploy, A Deep Technical Comparison for Production LLM Inference
11月 20, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Production LLM serving is now a systems problem, not a generate() loop. For real workloads...
VL-Cogito: Advancing Multimodal Reasoning with Progressive Curriculum Reinforcement Learning
8月 9, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Multimodal reasoning, where models integrate and interpret information from multiple sources such as text, images...
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
9月 30, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.15235v4 Announce Type: replace-cross Abstract: Speculative decoding is a widely adopted technique for accelerating inference...
Visa launches ‘Intelligent Commerce’ platform, letting AI agents swipe your card—safely, it says
5月 5, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Visa launches Intelligent Commerce platform enabling AI assistants to make secure purchases with your credit...
Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
9月 18, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2405.19988v3 Announce Type: replace-cross Abstract: Natural language is often the easiest and most convenient modality...
VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents
6月 30, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2506.21582v1 Announce Type: new Abstract: Text analytics has traditionally required specialized knowledge in Natural Language...
VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline
6月 20, 2026admin NUAI,Committee,ニュース,Uncategorized(0)While recent breakthroughs in AI reasoning have largely been driven by massive scale, pouring in...
