-
엔비디아 네모트론 3 울트라가 최고 성능 개방형 미국 모델로 부상, 하지만 중국이 여전히 앞서
Nvidia's Nemotron 3 Ultra becomes the smartest open US model, but China still leads
<p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2025/12/nvidia_logo_wall_cb-1.jpeg" style="height: auto;…
-
Granite 임베딩 다국어 R2: Apache 2.0 오픈소스 32K 컨텍스트를 갖춘 다국어 임베딩 — 100M 이하 모델 중 최고의 검색 품질
Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
-
QIMMA قِمّة ⛰: 품질 우선 아랍어 LLM 리더보드
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
-
25개 종의 mRNA 언어 모델을 $165로 학습하기
Training mRNA Language Models Across 25 Species for $165
-
TRL v1.0: 분야와 함께 성장하는 포스트-트레이닝 라이브러리
TRL v1.0: Post-Training Library Built to Move with the Field
-
봄날의 꿈: 2026년 1-2월 오픈웨이트 LLM 10가지 아키텍처
A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026
A Round Up And Comparison of 10 Open-Weight LLM Releases in Spring 2026
-
LLM 추론 개선을 위한 추론 시간 스케일링의 카테고리
Categories of Inference-Time Scaling for Improved LLM Reasoning
And an Overview of Recent Inference-Scaling Papers
-
의미 ID를 활용한 제어 가능 추천을 위한 LLM-RecSys 하이브리드 훈련
Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
An LLM that can converse in English & item IDs, and make recommendations w/o retrieval or tools.
-
Qwen3을 처음부터 이해하고 구현하기
Understanding and Implementing Qwen3 From Scratch
A Detailed Look at One of the Leading Open-Source LLMs
-
주요 LLM 아키텍처 비교
The Big LLM Architecture Comparison
From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design
-
LLM 연구 논문: 2025년 목록 (1월~6월)
LLM Research Papers: The 2025 List (January to June)
A topic-organized collection of 200+ LLM research papers from 2025
-
LLM 추론을 위한 강화학습의 현황
The State of Reinforcement Learning for LLM Reasoning
Understanding GRPO and New Insights from Reasoning Model Papers
-
LLM 평가자의 효율성 평가 (LLM-as-Judge)
Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)
Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.
-
도메인 외 파인튜닝을 통한 환각 탐지 부트스트래핑
Out-of-Domain Finetuning to Bootstrap Hallucination Detection
How to use open-source, permissive-use data and collect less labeled samples for our tasks.
-
Claude의 생물정보학 연구 능력을 BioMysteryBench로 평가하기
Apr 29, 2026 Science Evaluating Claude’s bioinformatics research capabilities with BioMysteryBench
-
자연어 오토인코더: Claude의 생각을 텍스트로 변환하기
Natural Language Autoencoders: Turning Claude’s thoughts into text Interpretability May 7, 2026 AI models like Claude talk in words but think in numbers. In this study, we train Claude to translate its thoughts into human-readable text.