Weijie Wang

Weijie Wang on Hugging Face Daily Papers: 18 papers, 3 in the top 3 of their day, 609 upvotes.

  1. SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue 100 upvotes, #1 of 2026-09-24
  2. ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes 25 upvotes, #13 of 2026-09-03
  3. Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion 33 upvotes, #7 of 2026-08-25
  4. WorldOlympiad: Can Your World Model Survive a Triathlon? 31 upvotes, #13 of 2026-06-10
  5. Latent Spatial Memory for Video World Models 66 upvotes, #4 of 2026-06-09
  6. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction 51 upvotes, #5 of 2026-05-26
  7. Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization 36 upvotes, #9 of 2026-05-18
  8. Diffusion Model as a Generalist Segmentation Learner 4 upvotes, #17 of 2026-05-07
  9. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 34 upvotes, #2 of 2026-04-28
  10. Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective 14 upvotes, #16 of 2026-04-15
  11. Less Detail, Better Answers: Degradation-Driven Prompting for VQA 13 upvotes, #23 of 2026-04-07
  12. CoV: Chain-of-View Prompting for Spatial Reasoning 8 upvotes, #15 of 2026-01-09
  13. PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation 2 upvotes, #24 of 2025-12-04
  14. DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion 1 upvotes, #28 of 2025-10-20
  15. VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction 23 upvotes, #8 of 2025-09-24
  16. Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting 11 upvotes, #22 of 2025-06-06
  17. Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning 45 upvotes, #2 of 2025-06-05
  18. ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS 4 upvotes, #49 of 2025-05-30

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.