Harvey Introduces Harvey Tenet: A Kimi K3 Base Post-Trained with Fireworks for Long-Horizon Legal Agent Work
8 月 24, 2026admin NUAI,Committee,新闻,Uncategorized(0)Harvey has released Harvey Tenet, its first post-trained model, as a research preview as of...
Harnessing human-AI collaboration for an AI roadmap that moves beyond pilots
12 月 6, 2025admin NUAI,Committee,新闻,Uncategorized(0)The past year has marked a turning point in the corporate AI conversation. After a...
HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization
8 月 7, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.04010v1 Announce Type: new Abstract: Large language models enable agents to autonomously perform tasks in...
Handling Numeric Expressions in Automatic Speech Recognition
6 月 24, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2408.00004v2 Announce Type: replace-cross Abstract: This paper addresses the problem of correctly formatting numeric expressions...
HalluClean: A Unified Framework to Combat Hallucinations in LLMs
11 月 13, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2511.08916v1 Announce Type: new Abstract: Large language models (LLMs) have achieved impressive performance across a...
Hacking the atmosphere: Geoengineering gets a reality check
6 月 17, 2026admin NUAI,Committee,新闻,Uncategorized(0)Jim Franke pulls away the cover page of a presentation on the wraparound desk in...
Hackers made death threats against this security researcher. Big mistake.
2 月 16, 2026admin NUAI,Committee,新闻,Uncategorized(0)The threats started in spring. In April 2024, a mysterious someone using the online handles...
GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
7 月 10, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2502.16903v2 Announce Type: replace Abstract: Despite the growing interest in jailbreak methods as an effective...
Guided Self-Evolving LLMs with Minimal Human Supervision
12 月 3, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.02472v1 Announce Type: cross Abstract: AI self-evolution has long been envisioned as a path toward...
