Daily Papers of 2024-05-14

1. What matters when building vision-language models? 81 upvotes, #1 of 2024-05-14
2. RLHF Workflow: From Reward Modeling to Online RLHF 54 upvotes, #2 of 2024-05-14
3. SUTRA: Scalable Multilingual Language Model Architecture 34 upvotes, #3 of 2024-05-14
4. SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts 21 upvotes, #4 of 2024-05-14
5. Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training 15 upvotes, #5 of 2024-05-14
6. LogoMotion: Visually Grounded Code Generation for Content-Aware Animation 15 upvotes, #5 of 2024-05-14
7. Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots 15 upvotes, #5 of 2024-05-14
8. MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels 14 upvotes, #8 of 2024-05-14
9. Large Language Models as Planning Domain Generators 8 upvotes, #9 of 2024-05-14

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.