Daily Papers of 2024-12-05

  1. PaliGemma 2: A Family of Versatile VLMs for Transfer 109 upvotes, #1 of 2024-12-05
  2. SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance 105 upvotes, #2 of 2024-12-05
  3. TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation 29 upvotes, #3 of 2024-12-05
  4. Imagine360: Immersive 360 Video Generation from Perspective Anchor 26 upvotes, #4 of 2024-12-05
  5. Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion 25 upvotes, #5 of 2024-12-05
  6. VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding 22 upvotes, #6 of 2024-12-05
  7. VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models 19 upvotes, #7 of 2024-12-05
  8. One Shot, One Talk: Whole-body Talking Avatar from a Single Image 18 upvotes, #8 of 2024-12-05
  9. NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images 18 upvotes, #8 of 2024-12-05
  10. NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training 17 upvotes, #10 of 2024-12-05
  11. Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding 15 upvotes, #11 of 2024-12-05
  12. U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs 14 upvotes, #12 of 2024-12-05
  13. MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation 14 upvotes, #12 of 2024-12-05
  14. Mimir: Improving Video Diffusion Models for Precise Text Understanding 12 upvotes, #14 of 2024-12-05
  15. CleanDIFT: Diffusion Features without Noise 12 upvotes, #14 of 2024-12-05
  16. Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models 11 upvotes, #16 of 2024-12-05
  17. Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning 11 upvotes, #16 of 2024-12-05
  18. LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting 7 upvotes, #18 of 2024-12-05
  19. Weighted-Reward Preference Optimization for Implicit Model Fusion 7 upvotes, #18 of 2024-12-05

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.