본문으로 건너뛰기

#Data Curation

54개의 포스트

[논문리뷰] Watch Before You Answer: Learning from Visually Grounded Post-Training

본 논문은 오직 Visually Grounded 질문만을 사용하여 모델을 post-training하는 VidGround 프레임워크를 제안한다. 저자들은 GPT-5-mini와 같은 강력한 언어 모델을 사용하여 텍스트만으로 답변 가능한 TA 질문을 필터링하고, 나머지 VG 질문만을 학습 데이터로 선별하였다.
#Review#Vision-Language Models#Video Understanding#Post-Training#Linguistic Bias#Reinforcement Learning#Data Curation#Visually Grounded Reasoning
댓글 수 로딩 중

[논문리뷰] DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

arXiv에 게시된 'DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation' 논문에 대한 자세한 리뷰입니다.
#Review#Reinforcement Learning with Verifiable Reward#Competitive Programming#Code Generation#Data Curation#Curriculum Learning#Supervised Fine-tuning#Entropy Expansion
댓글 수 로딩 중

[논문리뷰] ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature

arXiv에 게시된 'ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature' 논문에 대한 자세한 리뷰입니다.
#Review#Multi-agent Systems#Large Language Models (LLMs)#Information Extraction#Scientific Literature#Materials Science#Data Curation#Piezoelectric Materials#RAG (Retrieval-Augmented Generation)
댓글 수 로딩 중

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

Zhijie Sang이 arXiv에 게시한 'InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities' 논문에 대한 자세한 리뷰입니다.
#Review#LLM Alignment#Reasoning#Data Curation#Supervised Fine-tuning (SFT)#Direct Preference Optimization (DPO)#Sample Efficiency#Scalability#Multi-dimensional Filtering
댓글 수 로딩 중