Daily Papers of 2024-05-24

  1. Not All Language Model Features Are Linear 32 upvotes, #1 of 2024-05-24
  2. DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data 27 upvotes, #2 of 2024-05-24
  3. Dense Connector for MLLMs 20 upvotes, #3 of 2024-05-24
  4. ReVideo: Remake a Video with Motion and Content Control 19 upvotes, #4 of 2024-05-24
  5. Distributed Speculative Inference of Large Language Models 14 upvotes, #5 of 2024-05-24
  6. LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models 14 upvotes, #5 of 2024-05-24
  7. Thermodynamic Natural Gradient Descent 12 upvotes, #7 of 2024-05-24
  8. Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation 10 upvotes, #8 of 2024-05-24
  9. Improved Distribution Matching Distillation for Fast Image Synthesis 10 upvotes, #8 of 2024-05-24
  10. AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability 9 upvotes, #10 of 2024-05-24
  11. DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis 8 upvotes, #11 of 2024-05-24
  12. RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance 8 upvotes, #11 of 2024-05-24
  13. Semantica: An Adaptable Image-Conditioned Diffusion Model 7 upvotes, #13 of 2024-05-24
  14. CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers 6 upvotes, #14 of 2024-05-24
  15. Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling 6 upvotes, #14 of 2024-05-24
  16. NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections 6 upvotes, #14 of 2024-05-24
  17. Tele-Aloha: A Low-budget and High-authenticity Telepresence System Using Sparse RGB Cameras 5 upvotes, #17 of 2024-05-24

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.