ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #多GPU推理 Clear filters
Research & Papers· 2026-11-10#TopoBench#Graph Neural Networks#Topological Neural Networks#Structural Learning#GraphUniverse
By Mr.Xu0 views0 discussions
The 2026 Topological Deep Learning Challenge placed graph neural networks and topological …
Agentic· 2026-11-10
Mr.Xu0 views0 discussions
Causal-Discovery-Bench is a verifiable sandbox for evaluating whether LLM agents can auton…
Research & Papers· 2026-11-10
Mr.Xu0 views0 discussions
MAGE is a multi-timescale foundation model for electroencephalography. Rather than encodin…
LLMs & Foundation Models· 2026-11-10
Mr.Xu0 views0 discussions
BIBIMBAP evaluates language-driven Building Information Modeling as an executable Text-to-…
Research & Papers· 2026-11-10
Mr.Xu1 views0 discussions
This study traces the modality gap in vision-language models to the embedding layer. Text …
LLMs & Foundation Models· 2026-11-10
Mr.Xu2 views0 discussions
A study of overloaded vLLM deployments finds that client- and proxy-side retries can keep …
Research & Papers· 2026-11-10
Mr.Xu0 views0 discussions
This paper recasts backtracking counterfactual inference in structural causal models as an…
LLMs & Foundation Models· 2026-11-10
Mr.Xu1 views0 discussions
ChainFlow introduces a speculative-decoding drafter conditioned on the target model's hidd…
Agentic· 2026-11-10
Mr.Xu3 views0 discussions
The paper isolates the effect of an interactive debugger by holding the coding-agent scaff…
Agentic· 2026-11-10
Mr.Xu1 views0 discussions
Forge Decision Context (forge_dc) addresses a central limitation of LLM agents: correction…
LLMs & Foundation Models· 2026-11-10
Mr.Xu1 views0 discussions
The paper introduces Aspect-wise Pairwise Tournaments (APT), replacing absolute scoring of…
Agentic· 2026-11-10
Mr.Xu0 views0 discussions
NormGym is an interactive benchmark for normative competence in multi-agent communities. A…
