MMLab@NTU

MMLab@NTU on Hugging Face Daily Papers: 19 papers, 4 in the top 3 of their day, 0 paper of the day.

  1. From Pixels to Actions - Towards Native Vision-Language-Action Policies 60 upvotes, #2 of 2026-11-05
  2. Probing Spatial State Representations in Visual Foundation Models 19 upvotes, #12 of 2026-11-02
  3. MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting 18 upvotes, #18 of 2026-10-28
  4. PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation 10 upvotes, #44 of 2026-10-21
  5. ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning 7 upvotes, #46 of 2026-10-12
  6. DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency 7 upvotes, #50 of 2026-10-07
  7. Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning 49 upvotes, #13 of 2026-09-29
  8. Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence 43 upvotes, #9 of 2026-07-21
  9. Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion 21 upvotes, #10 of 2026-06-17
  10. Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models 12 upvotes, #22 of 2026-03-24
  11. MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction 36 upvotes, #8 of 2026-03-20
  12. Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer 41 upvotes, #7 of 2026-03-20
  13. Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation 68 upvotes, #7 of 2026-03-18
  14. HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions 149 upvotes, #3 of 2026-03-17
  15. VLANeXt: Recipes for Building Strong VLA Models 52 upvotes, #3 of 2026-02-24
  16. 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere 1 upvotes, #15 of 2026-02-23
  17. Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition 28 upvotes, #15 of 2026-02-10
  18. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation 68 upvotes, #4 of 2026-01-30
  19. Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation 114 upvotes, #2 of 2025-10-13

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.