ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
7 月 2, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2507.00898v1 Announce Type: cross Abstract: Recent Large Vision-Language Models (LVLMs) have introduced a new paradigm...
Online-PVLM: Advancing Personalized VLMs with Online Concept Learning
11 月 26, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2511.20056v1 Announce Type: new Abstract: Personalized Visual Language Models (VLMs) are gaining increasing attention for...
Online harassment is entering its AI era
3 月 5, 2026admin NUAI,Committee,新闻,Uncategorized(0)Scott Shambaugh didn’t think twice when he denied an AI agent’s request to contribute to...
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
10 月 1, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2509.26313v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is the predominant method for adapting large...
One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
8 月 5, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.07167v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been extensively used across diverse...
One Token Is Enough: Improving Diffusion Language Models with a Sink Token
2 月 23, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2601.19657v3 Announce Type: replace Abstract: Diffusion Language Models (DLMs) have emerged as a compelling alternative...
One Joke to Rule them All? On the (Im)possibility of Generalizing Humor
8 月 28, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.19402v1 Announce Type: new Abstract: Humor is a broad and complex form of communication that...
On the Reliability of Large Language Models for Causal Discovery
10 月 13, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2407.19638v2 Announce Type: replace Abstract: This study investigates the efficacy of Large Language Models (LLMs)...
On the generalization of language models from in-context learning and finetuning: a controlled study
5 月 8, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.00661v2 Announce Type: replace Abstract: Large language models exhibit exciting capabilities, yet can show surprisingly...
