Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
1 月 26, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2601.16400v1 Announce Type: new Abstract: Real-world visual question answering (VQA) is often context-dependent: an image-question...
CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation
6 月 30, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.21805v1 Announce Type: cross Abstract: Modeling human behavior in urban environments is fundamental for social...
Cisco Foundation AI Releases Antares: 350M and 1B Open-Weight Models That Localize Known Vulnerabilities Inside Real Codebases
7 月 22, 2026admin NUAI,Committee,新闻,Uncategorized(0)Cisco Foundation AI has released Antares, a family of security small language models (SLMs) built...
Chunking vs. Tokenization: Key Differences in AI Text Processing
8 月 31, 2025admin NUAI,Committee,新闻,Uncategorized(0)Table of contents Introduction What is Tokenization? What is Chunking? The Key Differences That Matter...
ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
10 月 22, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2510.18455v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) systems are increasingly vital in dynamic...
Chronicals: A High-Performance Framework for LLM Fine-Tuning with 3.51x Speedup over Unsloth
1 月 7, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2601.02609v1 Announce Type: cross Abstract: Large language model fine-tuning is bottlenecked by memory: a 7B...
Chroma Releases Context-1: A 20B Agentic Search Model for Multi-Hop Retrieval, Context Management, and Scalable Synthetic Task Generation
3 月 29, 2026admin NUAI,Committee,新闻,Uncategorized(0)In the current AI landscape, the ‘context window’ has become a blunt instrument. We’ve been...
Choosing the Right AI Agent Memory Strategy: A Decision-Tree Approach
7 月 12, 2026admin NUAI,Committee,新闻,Uncategorized(0)In this article, you will learn how to choose the right memory strategy for an...
