Daily Papers of 2023-11-23

1. GAIA: a benchmark for General AI Assistants 253 upvotes, #1 of 2023-11-23
2. FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline 58 upvotes, #2 of 2023-11-23
3. LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes 53 upvotes, #3 of 2023-11-23
4. Diffusion Model Alignment Using Direct Preference Optimization 48 upvotes, #4 of 2023-11-23
5. ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs 46 upvotes, #5 of 2023-11-23
6. Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model 28 upvotes, #6 of 2023-11-23
7. PG-Video-LLaVA: Pixel Grounding Large Video-Language Models 18 upvotes, #7 of 2023-11-23
8. Visual In-Context Prompting 18 upvotes, #7 of 2023-11-23
9. Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models 15 upvotes, #9 of 2023-11-23

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.