Daily Papers of 2023-10-17

1. Llemma: An Open Language Model For Mathematics 56 upvotes, #1 of 2023-10-17
2. In-Context Pretraining: Language Modeling Beyond Document Boundaries 29 upvotes, #2 of 2023-10-17
3. MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning 21 upvotes, #3 of 2023-10-17
4. Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams 13 upvotes, #4 of 2023-10-17
5. Interactive Task Planning with Language Models 12 upvotes, #5 of 2023-10-17
6. Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model 11 upvotes, #6 of 2023-10-17
7. Video Language Planning 11 upvotes, #6 of 2023-10-17
8. Farzi Data: Autoregressive Data Distillation 9 upvotes, #8 of 2023-10-17
9. Microscaling Data Formats for Deep Learning 7 upvotes, #9 of 2023-10-17
10. Improving Large Language Model Fine-tuning for Solving Math Problems 6 upvotes, #10 of 2023-10-17
11. Ranking LLM-Generated Loop Invariants for Program Verification 3 upvotes, #11 of 2023-10-17
12. When can transformers reason with abstract symbols? 3 upvotes, #11 of 2023-10-17

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.