Menagerie of models trained on SAYCam (and more)

Fast and memory-efficient exact attention

3D Visualization of an GPT-style LLM

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Code for the paper "A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification"

[ECCV'24] Kalman-Inspired Feature Propagation for Video Face Super-Resolution

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

[CVPR 2024] Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding

[CVPR2024] 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"

SEA is an automated paper review framework capable of generating comprehensive and high-quality review feedback with high consistency for papers, thereby assisting researchers in improving the qual…

A native PyTorch Library for large model training

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

The n-gram Language Model

[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

Grounding Image Matching in 3D with MASt3R

[CVPR 2024] Code for "Improved Visual Grounding through Self-Consistent Explanations".

daily update NeRF releated paper on arxiv

[ICCV 2023] Multi3DRefer: Grounding Text Description to Multiple 3D Objects

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

Use commands in English to control Blender with OpenAI's GPT-4

[CVPR 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Repository for the ACL 2024 conference website