Probing Spatial State Representations in Visual Foundation Models
Paper • 2610.40636 • Published • 21
AI & ML interests
Computer Vision and Deep Learning
Recent Activity
View all activity
Papers
From Pixels to Actions - Towards Native Vision-Language-Action Policies
Probing Spatial State Representations in Visual Foundation Models
yinbq
submitted a
paper to Daily Papers 4 days ago
jcenaa
submitted a
paper to Daily Papers 4 days ago
yslan
authored 17
papers 6 days ago
OmniVGGT: Omni-Modality Driven Visual Geometry Grounded
Paper • 2511.10560 • Published • 4
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Paper • 2508.10893 • Published • 31
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Paper • 2512.03040 • Published • 7
VFMF: World Modeling by Forecasting Vision Foundation Model Features
Paper • 2512.11225 • Published
ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
Paper • 2510.21432 • Published • 1
IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
Paper • 2510.22706 • Published • 42
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
Paper • 2605.27852 • Published • 1
PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
Paper • 2602.03533 • Published
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
Paper • 2606.06601 • Published • 26
4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere
Paper • 2602.10094 • Published • 5
PhysiFormer: Learning to Simulate Mechanics in World Space
Paper • 2606.27364 • Published • 12
Syn4D: A Multiview Synthetic 4D Dataset
Paper • 2605.05207 • Published • 1
SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
Paper • 2411.16856 • Published • 13
3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
Paper • 2412.18565 • Published • 1
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Paper • 2502.14316 • Published • 1
WORLDMEM: Long-term Consistent World Simulation with Memory
Paper • 2504.12369 • Published • 36
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Paper • 2610.25276 • Published • 6
yslan
submitted a
paper to Daily Papers 6 days ago