Daily Papers of 2023-10-25

1. In-Context Learning Creates Task Vectors 43 upvotes, #1 of 2023-10-25
2. SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding 24 upvotes, #2 of 2023-10-25
3. Woodpecker: Hallucination Correction for Multimodal Large Language Models 18 upvotes, #3 of 2023-10-25
4. Inject Semantic Concepts into Image Tagging for Open-Set Recognition 6 upvotes, #4 of 2023-10-25
5. Dissecting In-Context Learning of Translations in GPTs 6 upvotes, #4 of 2023-10-25
6. KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval 5 upvotes, #6 of 2023-10-25
7. TRAMS: Training-free Memory Selection for Long-range Language Modeling 2 upvotes, #7 of 2023-10-25
8. Moral Foundations of Large Language Models 1 upvotes, #8 of 2023-10-25

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.