Daily Papers of 2023-12-05

  1. Magicoder: Source Code Is All You Need 83 upvotes, #1 of 2023-12-05
  2. VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models 39 upvotes, #2 of 2023-12-05
  3. The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning 31 upvotes, #3 of 2023-12-05
  4. DeepCache: Accelerating Diffusion Models for Free 23 upvotes, #4 of 2023-12-05
  5. VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence 22 upvotes, #5 of 2023-12-05
  6. Segment and Caption Anything 21 upvotes, #6 of 2023-12-05
  7. Nash Learning from Human Feedback 18 upvotes, #7 of 2023-12-05
  8. DiffiT: Diffusion Vision Transformers for Image Generation 15 upvotes, #8 of 2023-12-05
  9. GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis 14 upvotes, #9 of 2023-12-05
  10. Object Recognition as Next Token Prediction 13 upvotes, #10 of 2023-12-05
  11. GIVT: Generative Infinite-Vocabulary Transformers 12 upvotes, #11 of 2023-12-05
  12. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback 11 upvotes, #12 of 2023-12-05
  13. Segment Any 3D Gaussians 10 upvotes, #13 of 2023-12-05
  14. Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models 10 upvotes, #13 of 2023-12-05
  15. Style Aligned Image Generation via Shared Attention 10 upvotes, #13 of 2023-12-05
  16. Fast View Synthesis of Casual Videos 10 upvotes, #13 of 2023-12-05
  17. VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams 8 upvotes, #17 of 2023-12-05
  18. SANeRF-HQ: Segment Anything for NeRF in High Quality 7 upvotes, #18 of 2023-12-05
  19. Generative Powers of Ten 7 upvotes, #18 of 2023-12-05
  20. Rejuvenating image-GPT as Strong Visual Representation Learners 6 upvotes, #20 of 2023-12-05
  21. TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents 5 upvotes, #21 of 2023-12-05
  22. Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments 5 upvotes, #21 of 2023-12-05
  23. Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training 5 upvotes, #21 of 2023-12-05

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.