Daily Papers of 2023-09-20

1. Language Modeling Is Compression 85 upvotes, #1 of 2023-09-20
2. Multimodal Foundation Models: From Specialists to General-Purpose Assistants 41 upvotes, #2 of 2023-09-20
3. Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions 24 upvotes, #3 of 2023-09-20
4. Baichuan 2: Open Large-scale Language Models 21 upvotes, #4 of 2023-09-20
5. OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch 17 upvotes, #5 of 2023-09-20
6. Stabilizing RLHF through Advantage Model and Selective Rehearsal 10 upvotes, #6 of 2023-09-20
7. SlimPajama-DC: Understanding Data Combinations for LLM Training 10 upvotes, #6 of 2023-09-20
8. FoleyGen: Visually-Guided Audio Generation 8 upvotes, #8 of 2023-09-20
9. 360^circ Reconstruction From a Single Image Using Space Carved Outpainting 5 upvotes, #9 of 2023-09-20

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.