Zhihao Zhang

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

WildDet3D. Allen Institute for AI: WildDet3D: Scaling Promptable 3D Detection in the Wild

Awesome-World-Action-Model. A curated list of academic papers and resources on Vision-Language-Action (VLA) and World Action Models (WAM)

3DThinker. [CVPR 2026] Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

MonoIA. [CVPR 2026] MonoIA: Towards Intrinsic-Aware Monocular 3D Object Detection

Awesome-PhD-CV. Curated academic CV templates and guidelines for PhD students, researchers, and faculty job applicants.

LabelAny3D. [NeurIPS 2025] LabelAny3D: Label Any Object 3D in the Wild

MonoCoP. [CVPR 2026 Highlight] MonoCoP: Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection

Spatial-SSRL. [CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

3DFACENet. This is the code of 3DFACENet, which achieves 3D facial attractiveness computation and enhancement efficiently. Our work is accepted by IEEE Transactions on Image Processing and we will release our code soon

CUHKSZ-3D-2DFaces. Python

DetAny3D. [ICCV 2025] Detect Anything 3D in the Wild

phi-Decoding. [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling

CHARM3R. [ICCV 2025] Official PyTorch Code of CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector

describe-anything. [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

QME_ICCV25. [ICCV 2025] Repository for A Quality-Guided Mixture of Score-fusion Experts Framework for Human Recognition

ovmono3d. [3DV 2026] Open Vocabulary Monocular 3D Object Detection

kitti-object-eval-python. Fast kitti object detection eval in python(finish eval in less than 10 second)

EchoShot. The official code of EchoShot: Multi-Shot Portrait Video Generation (NeurIPS 2025)

DINOv. [CVPR 2024] Official implementation of the paper "Visual In-context Learning"

DriveGEN. This is the official project repository for "DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation" (CVPR 2025)

Tamm_Code. [CVPR 2024] TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding

Unlearn-Trace. [ICLR26] Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

M2F2_Det. 🔥Deepfake + LLM (CVPR25 Oral)

ChatGen. [CVPR 2025] ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting

VLM-Safety-Unlearn. [ICLR26] Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

MonoDGP. [CVPR 2025] The offical implementation of 'MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors'

torch_packages_builder. Builder and index for PyTorch packages

MM-Det. Diffusion Generated Video Detection (NeurIPS2024)

SkelNet_motion_prediction. Motion Prediction Work (AAAI2019)

Dense-Face. Face Generation Work (Preprint)

LL3DA. [CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Language 3D Assistant.

OpenDlign. [NeurIPS 2024] OpenDlign: Enhancing Open-World 3D Learning with Depth-Aligned Images

MonoDETR. [ICCV 2023] The first DETR model for monocular 3D object detection with depth-guided transformer

LUVLi. [CVPR 2020] Re-hosting of the LUVLi Face Alignment codebase. Please download the codebase from the original MERL website by agreeing to all terms and conditions. By using this code, you agree to MERL's research-only licensing terms.

groomed_nms. [CVPR 2021] Official PyTorch Code of GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

omni3d. Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

DEVIANT. [ECCV 2022] Official PyTorch Code of DEVIANT: Depth Equivariant Network for Monocular 3D Object Detection

Multi-domain-learning-FAS. MD-FAS with SiW-Mv2 dataset (ECCV22 Oral)

HiFi_IFDL. 🔥Hierarchical Fine-Grained Image Forgery Detection and Localization (CVPR23 + IJCV24)

relationformer. A Unified Framework for Image-to-Graph Generation. Paper accepted @ ECCV22.

ENVISIONS. [ACL 2025] A Neural-Symbolic Self-Training Framework

COSTELLO. Jupyter Notebook

Occlusion_HPR. Code for "Reconstructing 3D Human Pose from RGB-D Data with Occlusions" (PG 2023)

Symbol-LLM. [ACL 2024] The project of Symbol-LLM

ShapeLLM. [ECCV 2024] ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

XJTU_Thesis_LaTeX_2021. Master and PhD Thesis LaTeX Template of Xi'an Jiaotong University :page_facing_up:

MFTR. Python

ULIP. Python

acad-homepage.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

I2P-MAE. [CVPR 2023] Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders

OpenRooms. This is the dataset and code release of the OpenRooms Dataset. For more information, please refer to our webpage below. Thanks a lot for your interest in our research!

SegmentAnything3D. [ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

3D-Box-Segment-Anything. We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Learning-Deep-Learning. Paper reading notes on Deep Learning and Machine Learning

Autoformer. About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

Graduate_Application. Documents used for grad school application

locov. Localized Vision-Language Matching for Open-vocabulary Object Detection

Awesome-Trajectory-Motion-Prediction-Papers.

longformer. Longformer: The Long-Document Transformer

Informer2020. The GitHub repository for the paper "Informer" accepted by AAAI 2021.

pytorch-seq2seq. Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

DeepLearning_LHY21_Notes. 深度学习 李宏毅 2021 学习笔记

Valiant360. An in-browser 360 degree panorama video player.

pytorch-handbook. pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行