Daily Papers of 2024-12-12

  1. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints 49 upvotes, #1 of 2024-12-12
  2. LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations 42 upvotes, #2 of 2024-12-12
  3. POINTS1.5: Building a Vision-Language Model towards Real World Applications 38 upvotes, #3 of 2024-12-12
  4. Learning Flow Fields in Attention for Controllable Person Image Generation 31 upvotes, #4 of 2024-12-12
  5. Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation 20 upvotes, #5 of 2024-12-12
  6. The BrowserGym Ecosystem for Web Agent Research 18 upvotes, #6 of 2024-12-12
  7. Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction 18 upvotes, #6 of 2024-12-12
  8. StyleMaster: Stylize Your Video with Artistic Generation and Translation 18 upvotes, #6 of 2024-12-12
  9. StreamChat: Chatting with Streaming Video 17 upvotes, #9 of 2024-12-12
  10. 3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark 12 upvotes, #10 of 2024-12-12
  11. Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation 11 upvotes, #11 of 2024-12-12
  12. FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models 11 upvotes, #11 of 2024-12-12
  13. KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models 7 upvotes, #13 of 2024-12-12
  14. I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token 7 upvotes, #13 of 2024-12-12
  15. StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements 7 upvotes, #13 of 2024-12-12
  16. Video Creation by Demonstration 7 upvotes, #13 of 2024-12-12
  17. MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation 5 upvotes, #17 of 2024-12-12
  18. Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel 5 upvotes, #17 of 2024-12-12

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.