al-folio

a simple whitespace theme for academics

SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories

논문 리뷰 - Autonomous-Agents, Code Generation 관련 연구

10 min read · September 23, 2024

2024 · autonomous-agents bert code generation fine-tuning gpt llm paper-review reasoning transformer · paper-reviews
Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

논문 리뷰 - Knowledge Distillation, LLM, Limited Budget 관련 연구

11 min read · September 09, 2024

2024 · knowledge distillation language-model limited budget llm paper-review reasoning · paper-reviews
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

논문 리뷰 - VLM, Safety 관련 연구

11 min read · September 09, 2024

2024 · alignment bert embedding generative gpt language-model llm paper-review safety vision vlm · paper-reviews
Many-shot jailbreaking

논문 리뷰 - ICL, Safety 관련 연구

11 min read · September 02, 2024

2024 · alignment fine-tuning gpt icl llm paper-review safety · paper-reviews
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

논문 리뷰 - Embeddings, LLM 관련 연구

8 min read · September 02, 2024

2024 · attention bert classification embedding embeddings gpt language-model llm paper-review · paper-reviews