Training and evaluation datasets collected for Solaris: Building a Multiplayer Video World Model in Minecraft
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding
Collection for "Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders"
VSI-SUPER benchmark proposed in Cambrian-S
Collection for Diffusion Transformers with Representation Autoencoders
-
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 63 -
nyu-visionx/cambrian-8b
Text Generation • Updated • 1.13k • 63 -
nyu-visionx/cambrian-13b
Text Generation • 13B • Updated • 40 • 19 -
nyu-visionx/cambrian-34b
Text Generation • 35B • Updated • 28 • 27
Training and evaluation datasets collected for Solaris: Building a Multiplayer Video World Model in Minecraft
Model weights for Solaris: Building a Multiplayer Video World Model in Minecraft
Collection for "Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders"
Data used during Cambrian-S's 4-stage training
VSI-SUPER benchmark proposed in Cambrian-S
Collection for Diffusion Transformers with Representation Autoencoders
-
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 63 -
nyu-visionx/cambrian-8b
Text Generation • Updated • 1.13k • 63 -
nyu-visionx/cambrian-13b
Text Generation • 13B • Updated • 40 • 19 -
nyu-visionx/cambrian-34b
Text Generation • 35B • Updated • 28 • 27