Daily Papers of 2023-09-29

  1. Vision Transformers Need Registers 86 upvotes, #1 of 2023-09-29
  2. AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model 56 upvotes, #2 of 2023-09-29
  3. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation 48 upvotes, #3 of 2023-09-29
  4. Qwen Technical Report 39 upvotes, #4 of 2023-09-29
  5. Text-to-3D using Gaussian Splatting 33 upvotes, #5 of 2023-09-29
  6. Effective Long-Context Scaling of Foundation Models 31 upvotes, #6 of 2023-09-29
  7. Deep Geometrized Cartoon Line Inbetweening 25 upvotes, #7 of 2023-09-29
  8. Demystifying CLIP Data 20 upvotes, #8 of 2023-09-29
  9. AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models 18 upvotes, #9 of 2023-09-29
  10. MotionLM: Multi-Agent Motion Forecasting as Language Modeling 17 upvotes, #10 of 2023-09-29
  11. RealFill: Reference-Driven Generation for Authentic Image Completion 15 upvotes, #11 of 2023-09-29
  12. GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond 13 upvotes, #12 of 2023-09-29
  13. Language models in molecular discovery 10 upvotes, #13 of 2023-09-29
  14. Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation 10 upvotes, #13 of 2023-09-29
  15. ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning 10 upvotes, #13 of 2023-09-29
  16. CCEdit: Creative and Controllable Video Editing via Diffusion Models 9 upvotes, #16 of 2023-09-29

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.