ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #ADIndex Clear filters
Research & Papers· 2026-11-11#LLM Fingerprinting#Model Provenance#Black-Box Auditing#Training-Free#Training Data Attribution
By Mr.Xu0 views0 discussions
SetPrint introduces a training-free fingerprinting method for determining whether a target…
LLMs & Foundation Models· 2026-11-11
Mr.Xu0 views0 discussions
A new benchmark re-evaluates TabPFN-2.5, TabPFN-3.5, TabPFN-3.5-Fast, TabICL v2, and three…
Research & Papers· 2026-11-11
Mr.Xu0 views0 discussions
An arXiv preprint introduces the “competence circuit” (IKC + KC + C), a framework that dec…
Research & Papers· 2026-11-11
Mr.Xu2 views0 discussions
A controlled study evaluates six vision-language models on 1,500 WebQSP and CWQ questions,…
Research & Papers· 2026-11-11
Mr.Xu1 views0 discussions
This study evaluates 14 Llama 3 and Qwen 2.5 model variants using psychometric responses f…
Research & Papers· 2026-11-11
Mr.Xu2 views0 discussions
LandslideFM is a domain-specific vision-language foundation model designed to connect land…
Research & Papers· 2026-11-11
Mr.Xu2 views0 discussions
Mercity AI introduces TopicScope, a causal topic classifier trained on sparse autoencoder …
Agentic· 2026-11-11
Mr.Xu2 views0 discussions
EarthRecord is a new benchmark for evaluating multimodal agents on long-term land-change a…
LLMs & Foundation Models· 2026-11-11
Mr.Xu1 views0 discussions
HavonAI quantified token inflation across nine public tokenizers, all 25 Indian languages …
LLMs & Foundation Models· 2026-11-11
Mr.Xu2 views0 discussions
STO moves the optimization of LLM knowledge edits upstream, from weight modification to ta…
LLMs & Foundation Models· 2026-11-11
Mr.Xu0 views0 discussions
IntentTwin identifies a candidate-support confound in offline web-behavior benchmarks. Whe…
LLMs & Foundation Models· 2026-11-11
Mr.Xu0 views0 discussions
Brasilidade introduces a standardized evaluation methodology for assessing large language …
