ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #数学辅导 Clear filters
LLMs & Foundation Models· 2026-10-27#M³#Multi-Turn Adversarial Testing#LLM Safety#arXiv
By Mr.Xu1 views0 discussions
arXiv introduces M³, a novel automated red-teaming framework that formalizes multi-turn ad…
LLMs & Foundation Models· 2026-10-27
Mr.Xu1 views0 discussions
arXiv has released a new study on Multimodal Sentiment Analysis (MSA), introducing ConsMSA…
LLMs & Foundation Models· 2026-10-27
Mr.Xu1 views0 discussions
arXiv has released a study on enhancing the monitorability of Chain-of-Thought (CoT) reaso…
LLMs & Foundation Models· 2026-10-27
Mr.Xu1 views0 discussions
This research delves into the preconditioning mechanisms of the Muon optimizer in large la…
Agentic· 2026-10-27
Mr.Xu0 views0 discussions
A new arXiv study investigates how Large Language Model (LLM) agents can leverage trust es…
LLMs & Foundation Models· 2026-10-27
Mr.Xu1 views0 discussions
arXiv introduces a novel hierarchical agent distillation framework that addresses the chal…
Agentic· 2026-10-27
Mr.Xu1 views0 discussions
arXiv introduces TACS-RF, a framework that leverages a large language model (Claude Opus 4…
Agentic· 2026-10-27
Mr.Xu1 views0 discussions
Qwen has introduced Self-Direction, a novel mechanism that enables intelligent agents to l…
Agentic· 2026-10-27
Mr.Xu1 views0 discussions
Phronix introduces a novel capability-centric learning paradigm designed to overcome the l…
Agentic· 2026-10-27
Mr.Xu0 views0 discussions
arXiv introduces a novel training framework that leverages simulated Cognitively Constrain…
LLMs & Foundation Models· 2026-10-27
Mr.Xu0 views0 discussions
arXiv introduces LLMMAD, a novel autoregressive multimodal anomaly detection framework des…
Research & Papers· 2026-10-27
Mr.Xu1 views0 discussions
arXiv introduces Differentiable Diffusion Conditioning (D2C), a novel approach for offline…
