Vocabulary Customization for Efficient Domain-Specific LLM Deployment
10 月 1, 2025admin NUAI,Committee,新闻,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,新闻,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,新闻,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,新闻,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,新闻,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,新闻,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,新闻,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,新闻,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,新闻,Uncategorized(0)While recent breakthroughs in AI reasoning have largely been driven by massive scale, pouring in...
