Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
- codebook
- codeformer
- face-enhancement
- face-restoration
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
TripoSR: Fast 3D Object Reconstruction from a Single Image
- 3d-assets
- 3d-reconstruction
- feed-forward-3d
- generative-3d
Towards Human-Sounding Speech
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving
- autonomous-driving
- end-to-end-autonomous-driving
- motion-prediction
- multi-object-tracking
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
- audio-driven-portrait-animations
- audio-driven-talking-face
- human-animation
- talking-face-generation
Data augmentation for NLP
Feedforward style transfer
DeepSeek-VL: Towards Real-World Vision-Language Understanding
- vision-language-model
- vision-language-pretraining
- foundation-models
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
- image-enhancement
- image-restoration
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- 3d-reconstruction
- ai
- calibration
- depth-completion
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
- pruning
- model-compression
- efficient-deep-learning
- llm
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
- monocular-depth-estimation
- diffusion
- in-the-wild
- zero-shot
[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- robotic-manipulation
- vision-language-action-model
- pretraining-for-robotics
- robotic-foundation-model