Mark Boss

Mark Boss on Hugging Face Daily Papers: 13 papers, 1 in the top 3 of their day, 159 upvotes.

  1. SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation 11 upvotes, #55 of 2026-10-02
  2. 4Director: Controlling Video World Models with Rigid 3D Geometry 34 upvotes, #33 of 2026-10-02
  3. Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation 3 upvotes, #38 of 2026-06-23
  4. Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning 5 upvotes, #28 of 2026-06-04
  5. OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization 9 upvotes, #24 of 2026-05-21
  6. ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination 2 upvotes, #30 of 2026-03-23
  7. SViM3D: Stable Video Material Diffusion for Single Image 3D Generation 4 upvotes, #40 of 2025-10-10
  8. ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction 2 upvotes, #29 of 2025-10-02
  9. MARBLE: Material Recomposition and Blending in CLIP-Space 2 upvotes, #37 of 2025-06-06
  10. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images 16 upvotes, #10 of 2025-01-09
  11. SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement 24 upvotes, #3 of 2024-08-02
  12. SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion 16 upvotes, #4 of 2024-03-19
  13. SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild 14 upvotes, #8 of 2024-01-19

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.