Dan Xu

Dan Xu on Hugging Face Daily Papers: 19 papers, 2 in the top 3 of their day, 469 upvotes.

  1. WildActor: Unconstrained Identity-Preserving Video Generation 35 upvotes, #4 of 2026-03-09
  2. VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection 35 upvotes, #8 of 2026-03-03
  3. N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models 19 upvotes, #14 of 2025-12-19
  4. Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation 42 upvotes, #3 of 2025-12-12
  5. FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention 3 upvotes, #32 of 2025-12-03
  6. One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control 10 upvotes, #16 of 2025-11-25
  7. FullPart: Generating each 3D Part at Full Resolution 5 upvotes, #18 of 2025-10-31
  8. Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos 4 upvotes, #27 of 2025-10-22
  9. Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction 9 upvotes, #17 of 2025-10-13
  10. HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis 7 upvotes, #13 of 2025-09-24
  11. Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning 38 upvotes, #5 of 2025-07-29
  12. From One to More: Contextual Part Latents for 3D Generation 17 upvotes, #11 of 2025-07-14
  13. Taming LLMs by Scaling Learning Rates with Gradient Grouping 36 upvotes, #4 of 2025-06-03
  14. Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation 36 upvotes, #7 of 2025-04-04
  15. I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models 27 upvotes, #5 of 2025-02-18
  16. MM-Ego: Towards Building Egocentric Multimodal LLMs 19 upvotes, #12 of 2024-10-10
  17. 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection 14 upvotes, #9 of 2024-10-03
  18. Interactive3D: Create What You Want by Interactive 3D Generation 17 upvotes, #4 of 2024-04-26
  19. Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors 17 upvotes, #3 of 2023-12-11

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.