Archive - So Essentially

December 2024

Apollo for Video Understanding

Apollo for Video Understanding Using LMMs

Dec 18, 2024

3D World Generation

GenEx generates fictional 3D environments

Dec 17, 2024

PIGs are Physics-Informed Gaussian models for Partial Differential Equations

Dec 15, 2024

Coconut Thinking

Chain of thought in latent space is better than chain of thought of tokens

Dec 13, 2024

Around the world in 80 steps

Plonk model will predict location based on picture

Dec 11, 2024

Longer is NOT better for VLMs

VisionZip compresses tokens for better VLM performance

Dec 10, 2024

Universal Soccer Understanding

Soccer model by Alibaba is better than FIFA

Dec 7, 2024

SOLAMI enters the chat

SOLAMI basically understands body language in 3D

Dec 5, 2024

Video without depth has Depth

We get 3d depth data from videos directly now

Dec 2, 2024

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts