ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #Constraint Satisfaction Clear filters
Research & Papers· 2026-11-10#Data Poisoning#Backdoor Attacks#Supervised Fine-Tuning#Model Safety#Feature Attribution
By Mr.Xu0 views0 discussions
A new study identifies “homeopathic learning”: a model trained only on poisoned fine-tunin…
Industry & Trends· 2026-11-10
Mr.Xu2 views0 discussions
Researchers used an open-source large language model and a Chain-of-Stance prompting frame…
Research & Papers· 2026-11-10
Mr.Xu1 views0 discussions
META-IR is a meta-introspective reasoning framework for adapting LLM safety policies to ev…
LLMs & Foundation Models· 2026-11-10
Mr.Xu0 views0 discussions
AYO (AI Youth Open Science) is an open-source research platform for studying how children …
Compute & Architecture· 2026-11-10
Mr.Xu0 views0 discussions
LoRazor is a multi-LoRA serving framework designed for shared-backbone deployments. It all…
LLMs & Foundation Models· 2026-11-10
Mr.Xu2 views0 discussions
A study evaluated LLM-based annotation of crisis severity in veteran-related social media …
Research & Papers· 2026-11-10
Mr.Xu0 views0 discussions
A study spanning three model families, three benchmarks, and nine model-benchmark combinat…
LLMs & Foundation Models· 2026-11-10
Mr.Xu1 views0 discussions
CulturalCrosswords is a multilingual benchmark built from crowdsourced cultural riddles in…
Research & Papers· 2026-11-10
Mr.Xu0 views0 discussions
Researchers use Qwen3.5-27B as a model organism for studying evaluation awareness. Through…
Agentic· 2026-11-10
Mr.Xu1 views0 discussions
Clinical agents can solve routine tasks yet still make unsafe decisions when tools return …
Research & Papers· 2026-11-10
Mr.Xu0 views0 discussions
Multimodal large language models can memorize and reproduce sensitive information from bot…
LLMs & Foundation Models· 2026-11-10
Mr.Xu0 views0 discussions
DramaGrow introduces a regime-aware benchmark and audit protocol for LLM judges evaluating…
