Daily Papers of 2024-03-26

1. LLM Agent Operating System 56 upvotes, #1 of 2024-03-26
2. Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation 23 upvotes, #2 of 2024-03-26
3. SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions 19 upvotes, #3 of 2024-03-26
4. FlashFace: Human Image Personalization with High-fidelity Identity Preservation 17 upvotes, #4 of 2024-03-26
5. Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression 13 upvotes, #5 of 2024-03-26
6. TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models 12 upvotes, #6 of 2024-03-26
7. RakutenAI-7B: Extending Large Language Models for Japanese 9 upvotes, #7 of 2024-03-26
8. VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation 6 upvotes, #8 of 2024-03-26

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.