
- College Station, TX
- https://vztu.github.io
- @_vztu
- in/zhengzhongtu
Highlights
- Pro
Starred repositories
AutoTrust, a groundbreaking benchmark designed to assess the trustworthiness of DriveVLMs. This work aims to enhance public safety by ensuring DriveVLMs operate reliably across critical dimensions.
Wan: Open and Advanced Large-Scale Video Generative Models
CARLA2Real is a tool that enhances the photorealism of the CARLA simulator in real-time, leveraging the Enhancing Photorealism Enhancement model proposed by Intel Labs.
FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs
A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.
[ICLR'25] Official Implementation of STAMP: Scalable Task And Model-agnostic Collaborative Perception
OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.
Official released code for VQA² series models
Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
TrustEval: A modular and extensible toolkit for comprehensive trust evaluation of generative foundation models (GenFMs)
The Most Comprehensive Survey of Video Quality Assessment to Date.
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
A fork to add multimodal model training to open-r1
[TIP2024] MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
Janus-Series: Unified Multimodal Understanding and Generation Models
Fully open reproduction of DeepSeek-R1
The official implementation of "ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration" [NeurIPS 2024]
Driver Attention Prediction in Accidental Scenarios
[ACM MM 2020] CCD dataset for traffic accident anticipation.
[CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving
Pretraining a foundation model for generalizable fluorescence microscopy-based image restoration
HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection
🏆 [CVPRW 2024] COVER: A Comprehensive Video Quality Evaluator. 🥇 Winner solution for Video Quality Assessment Challenge at the 1st AIS 2024 workshop @ CVPR 2024
Python Library to evaluate VLM models' robustness across diverse benchmarks