nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation • 67B • Updated 2 days ago • 226k • 151
RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models Paper • 2509.21243 • Published Sep 25, 2025 • 1
RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models Paper • 2509.21243 • Published Sep 25, 2025 • 1
SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation Paper • 2601.17657 • Published Jan 25
Inference Optimized Checkpoints (with Model Optimizer) Collection A collection of generative models quantized and optimized for inference with Model Optimizer. • 54 items • Updated 4 days ago • 118