Daily Papers of 2023-05-19

  1. Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold 42 upvotes, #1 of 2023-05-19
  2. Tree of Thoughts: Deliberate Problem Solving with Large Language Models 15 upvotes, #2 of 2023-05-19
  3. LDM3D: Latent Diffusion Model for 3D 13 upvotes, #3 of 2023-05-19
  4. OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding 7 upvotes, #4 of 2023-05-19
  5. SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities 5 upvotes, #5 of 2023-05-19
  6. Learning the Visualness of Text Using Large Vision-Language Models 4 upvotes, #6 of 2023-05-19
  7. Discriminative Diffusion Models as Few-shot Vision and Language Learners 4 upvotes, #6 of 2023-05-19
  8. CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training 4 upvotes, #6 of 2023-05-19
  9. TextDiffuser: Diffusion Models as Text Painters 4 upvotes, #6 of 2023-05-19
  10. UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild 4 upvotes, #6 of 2023-05-19
  11. VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks 4 upvotes, #6 of 2023-05-19
  12. GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework 2 upvotes, #12 of 2023-05-19
  13. mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences 2 upvotes, #12 of 2023-05-19
  14. TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models 2 upvotes, #12 of 2023-05-19
  15. Going Denser with Open-Vocabulary Part Segmentation 2 upvotes, #12 of 2023-05-19
  16. Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models 1 upvotes, #16 of 2023-05-19
  17. MolXPT: Wrapping Molecules with Text for Generative Pre-training 1 upvotes, #16 of 2023-05-19
  18. VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation 1 upvotes, #16 of 2023-05-19
  19. A Generalist Dynamics Model for Control 1 upvotes, #16 of 2023-05-19

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.