ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #Synthetic Dataset Clear filters
LLMs & Foundation Models· 2026-11-11#Tokenizer#Multilingual Models#Indian Languages#Token Economics#Morphological Segmentation
By 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 …
LLMs & Foundation Models· 2026-11-11
Mr.Xu0 views0 discussions
This work examines how clinician edits can be mined as supervision for clinical documentat…
Research & Papers· 2026-11-11
Mr.Xu0 views0 discussions
Context compression can remove the evidence needed to justify an answer while preserving t…
Research & Papers· 2026-11-11
Mr.Xu2 views0 discussions
TimeOmni-o1 connects a pretrained time-series foundation model (TSFM) and a large language…
Research & Papers· 2026-11-11
Mr.Xu1 views0 discussions
StepRefine introduces a plug-and-play decoding strategy for multimodal diffusion language …
Agentic· 2026-11-11
Mr.Xu1 views0 discussions
Researchers used coding-agent infrastructure to conduct three rounds of closed-loop synchr…
Research & Papers· 2026-11-11
Mr.Xu1 views0 discussions
SREE is an evidence-grounded pipeline for inferring standardized depression questionnaire …
Research & Papers· 2026-11-11
Mr.Xu0 views0 discussions
The One Table Benchmark evaluates tabular generation, missing-value imputation, and superv…
Research & Papers· 2026-11-11
Mr.Xu0 views0 discussions
This study separates four claims often conflated by linear-probe analysis: decodability, g…
