• 2
• 0
• 0

ml-predict

• 2
• 0
• 0

ml-selfreflect

• 2
• 0
• 0

ml-diffucoder

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

• 2
• 0
• 0

embedding-atlas

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embed...

• 2
• 0
• 0

ml-isqoe

Official implementation of the paper "What Makes for a Good Stereoscopic Image" CVPRW 2025

• 2
• 0
• 0

dmel

• 2
• 0
• 0

ml-fastvlm

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

• 2
• 0
• 0

ml-ui-jepa

• 2
• 0
• 0

ml-space-benchmark

Code and data for "Does Spatial Cognition Emerge in Frontier Models?"

• 2
• 0
• 0

ml-comotion

• 2
• 0
• 0

ml-matrix3d

[CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One

• 2
• 0
• 0

ml-tic-lm

• 2
• 0
• 0

visatronic-demo

Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis

• 2
• 0
• 0

ml-flextok

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

• 2
• 0
• 0

ml-cubifyanything

• 2
• 0
• 0

ml-uncertainty-llms-instruction-following

• 2
• 0
• 0

ml-internal-llms-instruction-following

• 2
• 0
• 0

ml-reversal-blessing

• 2
• 0
• 0

ml-sage-dialog-gen

A pipeline for state-augmented dialogue training

• 2
• 0
• 0

parameterized-transforms

torchvision-based transforms that provide access to parameterization