Proxy-KD 도입을 통한 Black-Box LLM의 지식 전이 효율 극대화
Knowledge Distillation of Black-Box Large Language Models
Knowledge Distillation of Black-Box Large Language Models
AI 품질검사의 한계를 베테랑 엔지니어 350명 재고용으로 극복하여 JD Power 1위 달성
Chinese cybersecurity company claims it’s built a better-than-Mythos bug finder
0.22B 파라미터로 10B급 성능 구현 및 추론 속도 15배 가속
Enterprise AI Image Generation: The Custom Edge in 2026
Top AI Papers on Hugging Face - 2026-06-22
The Whole Paper Fits in One Sigmoid: Implementing the SDAR Gate
Claude Code에 SKILL.md 기반 자기개선 루프를 구현한 Hermes Agent식 플러그인
Single-tenant memory is the wrong default for agents
Job Searcher
Launch HN: General Instinct (YC P26) – Frontier models on edge devices
MAI-Thinking-1: Microsoft's New Reasoning Model and What It Means for Developers
NVIDIA Put Petaflop Compute on Your Desk — And It Changes the AI Cost Equation
I distilled a 7B vision model into a 2B one for screenshots — and the 7B teacher scored worse
Flux vs SDXL vs SD 1.5: Real Cost-per-Image Across GPUs (2026)
Serving AI Models: Balancing Cost and Performance
전처리 없는 Zero-shot 추론으로 정형 데이터 분석 파이프라인 최적화
From 99 Traders to One Signal: Implementing a Distilled KOL Consensus Strategy on FMZ
Needle and the Return of the Tiny Specialist Model
Gemini 증류 기반 26M 파라미터의 초경량 Tool Use 모델 Needle 분석