Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
ตุลาคม 9, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2510.07239v1 Announce Type: new Abstract: Automated red-teaming has emerged as a scalable approach for auditing...
Recursive Language Models (RLMs): From MIT’s Blueprint to Prime Intellect’s RLMEnv for Long Horizon LLM Agents
มกราคม 3, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)Recursive Language Models aim to break the usual trade off between context length, accuracy and...
Recognizing Limits: Investigating Infeasibility in Large Language Models
สิงหาคม 27, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2408.05873v3 Announce Type: replace Abstract: Large language models (LLMs) have shown remarkable performance in various...
Rebuilding the data stack for AI
เมษายน 27, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)Artificial intelligence may be dominating boardroom agendas, but many enterprises are discovering that the biggest...
Reasoning Promotes Robustness in Theory of Mind Tasks
มกราคม 26, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2601.16853v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown strong performance on...
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
ธันวาคม 25, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2512.20634v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning for...
READoc: A Unified Benchmark for Realistic Document Structured Extraction
กรกฎาคม 15, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2409.05137v3 Announce Type: replace Abstract: Document Structured Extraction (DSE) aims to extract structured content from...
Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
มกราคม 22, 2026admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2510.06605v2 Announce Type: replace-cross Abstract: The substantial investment required to develop Large Language Models (LLMs)...
Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers
ตุลาคม 17, 2025admin NUAI,Committee,ข่าว,Uncategorized(0)arXiv:2510.13939v1 Announce Type: new Abstract: The use of copyrighted books for training AI models has...
