Daily Papers of 2023-12-20

  1. LLM in a flash: Efficient Large Language Model Inference with Limited Memory 265 upvotes, #1 of 2023-12-20
  2. Gemini: A Family of Highly Capable Multimodal Models 50 upvotes, #2 of 2023-12-20
  3. StarVector: Generating Scalable Vector Graphics Code from Images 38 upvotes, #3 of 2023-12-20
  4. 3D-LFM: Lifting Foundation Model 15 upvotes, #4 of 2023-12-20
  5. A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise 14 upvotes, #5 of 2023-12-20
  6. HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles 13 upvotes, #6 of 2023-12-20
  7. Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model 13 upvotes, #6 of 2023-12-20
  8. Tracking Any Object Amodally 12 upvotes, #8 of 2023-12-20
  9. MixRT: Mixed Neural Representations For Real-Time NeRF Rendering 11 upvotes, #9 of 2023-12-20
  10. FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline 8 upvotes, #10 of 2023-12-20
  11. Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior 7 upvotes, #11 of 2023-12-20
  12. Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation 6 upvotes, #12 of 2023-12-20
  13. TIP: Text-Driven Image Processing with Semantic and Restoration Instructions 6 upvotes, #12 of 2023-12-20
  14. Text-Conditioned Resampler For Long Form Video Understanding 6 upvotes, #12 of 2023-12-20
  15. Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method 5 upvotes, #15 of 2023-12-20

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.