ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #3D Code Generation Clear filters
Research & Papers· 2026-11-09#QMAC#Data Selection#Distribution Matching#Instruction Tuning#Multimodal Models
By Mr.Xu0 views0 discussions
QMAC frames instruction-tuning data selection for large language models and large vision-l…
LLMs & Foundation Models· 2026-11-09
Mr.Xu0 views0 discussions
A controlled study of vLLM under overload reveals that client-side retries can keep an LLM…
Research & Papers· 2026-11-09
Mr.Xu0 views0 discussions
The paper formulates backtracking counterfactual inference in structural causal models as …
LLMs & Foundation Models· 2026-11-09
Mr.Xu0 views0 discussions
ChainFlow introduces a speculative-decoding drafter conditioned on the target model's hidd…
Agentic· 2026-11-09
Mr.Xu0 views0 discussions
This study isolates the effect of the debugging interface by keeping the coding-agent scaf…
Research & Papers· 2026-11-09
Mr.Xu0 views0 discussions
IWIBench introduces a controlled benchmark for evaluating whether a large language model c…
Agentic· 2026-11-09
Mr.Xu0 views0 discussions
Forge Decision Context (forge_dc) introduces persistent behavioral learning for LLM agents…
Compute & Architecture· 2026-11-09
Mr.Xu0 views0 discussions
NVIDIA has released Dynamo-optimized deployment recipes for A.X K2, K-EXAONE 2.0, Solar Op…
Research & Papers· 2026-11-09
Mr.Xu0 views0 discussions
This work embeds a customized Consistent RNN (ConsRNN) as a Fortran damage criterion insid…
Agentic· 2026-11-09
Mr.Xu0 views0 discussions
NormGym is an interactive benchmark for evaluating whether agents can acquire previously u…
Agentic· 2026-11-09
Mr.Xu0 views0 discussions
This paper turns the procedural knowledge encoded in Agent Skills—operations, tools, and f…
LLMs & Foundation Models· 2026-11-09
Mr.Xu0 views0 discussions
A study of nine generations of recursive self-training with GPT-2 reveals that Rényi entro…
