Daily Papers of 2023-05-31

  1. Faith and Fate: Limits of Transformers on Compositionality 9 upvotes, #1 of 2023-05-31
  2. HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance 7 upvotes, #2 of 2023-05-31
  3. LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus 6 upvotes, #3 of 2023-05-31
  4. What indeed can GPT models do in chemistry? A comprehensive benchmark on eight tasks 5 upvotes, #4 of 2023-05-31
  5. PaLI-X: On Scaling up a Multilingual Vision and Language Model 5 upvotes, #4 of 2023-05-31
  6. Real-World Image Variation by Aligning Diffusion Inversion Chain 5 upvotes, #4 of 2023-05-31
  7. GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction 5 upvotes, #4 of 2023-05-31
  8. StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation 5 upvotes, #4 of 2023-05-31
  9. Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation 4 upvotes, #9 of 2023-05-31
  10. Controllable Text-to-Image Generation with GPT-4 4 upvotes, #9 of 2023-05-31
  11. Grammar Prompting for Domain-Specific Language Generation with Large Language Models 4 upvotes, #9 of 2023-05-31
  12. Geometric Algebra Transformers 3 upvotes, #12 of 2023-05-31
  13. LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images 2 upvotes, #13 of 2023-05-31
  14. AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation 2 upvotes, #13 of 2023-05-31
  15. KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models 1 upvotes, #15 of 2023-05-31
  16. Nested Diffusion Processes for Anytime Image Generation 1 upvotes, #15 of 2023-05-31

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.