MMLab@NTU · 8 records

dateidtitleauthorsvenue↑
2026-11-042611.06918From Pixels to Actions - Towards Native Vision-Language-Action PoliciesWeichen Fan et al.arXiv58
2026-11-022610.40636Probing Spatial State Representations in Visual Foundation ModelsBaiqiao Yin et al.arXiv18
2026-10-282610.35724MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video MattingShuyun Wang et al.arXiv19
2026-10-212610.07609PhysLDM: Latent Diffusion for High-Fidelity Deformable SimulationYu Zhang et al.arXiv6
2026-10-122610.13316ThinkDrag: Semantic Drag-Based Image Editing with Visual ReasoningArmando Fortes et al.arXiv7
2026-09-292609.35767Learning Native Reflection in Unified Models with Interleaved Reinforcement LearningYijia Fan et al.arXiv46
2026-07-212607.16401Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical IntelligenceRunmao Yao et al.arXiv25
2026-06-172606.15236Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space DiffusionWeichen Fan et al.arXiv21