Daily Papers of 2024-03-19

1. Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation 54 upvotes, #1 of 2024-03-19
2. PERL: Parameter Efficient Reinforcement Learning from Human Feedback 47 upvotes, #2 of 2024-03-19
3. Larimar: Large Language Models with Episodic Memory Control 25 upvotes, #3 of 2024-03-19
4. SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion 16 upvotes, #4 of 2024-03-19
5. Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm 15 upvotes, #5 of 2024-03-19
6. LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images 13 upvotes, #6 of 2024-03-19
7. LightIt: Illumination Modeling and Control for Diffusion Models 12 upvotes, #7 of 2024-03-19
8. Generic 3D Diffusion Adapter Using Controlled Multi-View Editing 12 upvotes, #7 of 2024-03-19
9. MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data 11 upvotes, #9 of 2024-03-19
10. DiPaCo: Distributed Path Composition 9 upvotes, #10 of 2024-03-19
11. VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding 9 upvotes, #10 of 2024-03-19
12. LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation 8 upvotes, #12 of 2024-03-19
13. VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models 5 upvotes, #13 of 2024-03-19

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.