ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #大模型推理 Clear filters
Research & Papers· 2026-11-02#Distribution Grid#Bayesian Inference#Deep Learning#State Estimation#arXiv
By Mr.Xu0 views0 discussions
arXiv has released a new research paper introducing PoSE (Posterior Sampling for State Est…
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
arXiv has released BILAL-BENCH, a new benchmark designed to evaluate large language models…
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
A new arXiv study demonstrates that pruning a substantial fraction of redundant attention …
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
A new arXiv study exposes critical flaws in current conversational RAG benchmarks, particu…
Agentic· 2026-11-02
Mr.Xu0 views0 discussions
A new arXiv study introduces 'Adaptive Personalization Under Preference Epistemic Uncertai…
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
arXiv has recently introduced CoFiBreak, a novel method designed to enhance the diversity …
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
The newly released Qistas protocol by arXiv aims to address the social and cultural biases…
Research & Papers· 2026-11-02
Mr.Xu0 views0 discussions
The latest arXiv research delves into the performance differences between Continuous Diffu…
Agentic· 2026-11-02
Mr.Xu0 views0 discussions
Mage-VL-Cowork is a 4B parameter hybrid AI agent developed by Mage-CUA-Forge, designed to …
Research & Papers· 2026-11-02
Mr.Xu0 views0 discussions
A new arXiv study delves into the controllability of Chain-of-Thought (CoT) reasoning in A…
LLMs & Foundation Models· 2026-11-02
Mr.Xu0 views0 discussions
arXiv introduces DiRAFT, a novel method for generating privacy-aware financial transcripts…
Agentic· 2026-11-02
Mr.Xu0 views0 discussions
A new research paper from arXiv introduces Agentic World Modeling (AWM), a novel approach …
