Today's newsletter is out:. Alibaba’s AI Surge, ChatGPT’s Explosive Growth, Meta’s Massive Business Push, Broadcom’s Chip Boom, the Rise of AI Apps, and more!. Let me know what you think!.

Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction.

Structured-Noise Masked Modeling for Video, Audio and Beyond.

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation.

SynCity: Training-Free Generation of 3D Worlds. Project page:

SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation.

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation. Project page:

M3: 3D-Spatial MultiModal Memory. Project page: #ICLR2025 🎉

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior. Project page: #CVPR2025 🎉

Cube: A Roblox View of 3D Intelligence. Project page:

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities. Project page:

Temporal Regularization Makes Your Video Generator Stronger. Project page:

Visual Persona: Foundation Model for Full-Body Human Customization. Project page: #CVPR2025 🎉

Object-Centric Pretraining via Target Encoder Bootstrapping. #ICLR2025 🎉. Code repository: (coming soon)

TULIP: Towards Unified Language-Image Pretraining. Project page:

When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning. Project page: #CVPR2025 🎉

Humanoid Policy ~ Human Policy. Project page:

Stable Virtual Camera: Generative View Synthesis with Diffusion Models. Project page

Impossible Videos. Project page:

Bolt3D: Generating 3D Scenes in Seconds. Project page:

MusicInfuser: Making Video Diffusion Listen and Dance. Project page: