zhanwenchen
Data Science Ph.D. student at University of Virginia.
University of VirginiaCharlottesville, VA
Pinned Repositories
beam_nn
Convolutional Neural Networks for Ultrasound Imaging. A pipeline to create, train, and deploy models to denoise ultrasound data
blog
New Personal Website/Blog Built with React and Firebase
Boids
A 2D boids model in Matlab
decord
An efficient video loader for deep learning with smart shuffling that's super easy to digest
eoa
nn_numpy
Neural networks with NumPy
relaug
vtom
"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
zhanwenchen's Repositories
zhanwenchen/relaug
zhanwenchen/vtom
"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
zhanwenchen/AgentBoard
An Analytical Evaluation Board of Multi-turn LLM Agents
zhanwenchen/AskVideos-VideoCLIP
zhanwenchen/Awesome-Coreset-Selection
Awesome coreset/core-set/subset/sample selection works.
zhanwenchen/awesome-llm-plaza
awesome llm plaza: daily tracking all sorts of awesome topics of llm, e.g. llm for coding, robotics, reasoning, multimod etc.
zhanwenchen/builder
Continuous builder and binary build scripts for pytorch
zhanwenchen/Cradle
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
zhanwenchen/cutlass
CUDA Templates for Linear Algebra Subroutines
zhanwenchen/DataEnvGym
A testbed for agents and environments that can automatically improve models through data generation.
zhanwenchen/DeepSpeed-Native
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
zhanwenchen/flash-attention
Fast and memory-efficient exact attention
zhanwenchen/FLEUR
[ACL 2024] FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model
zhanwenchen/generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
zhanwenchen/LESS
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
zhanwenchen/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
zhanwenchen/make-it-count
Official implemention of "Make It Count: Text-to-Image Generation with an Accurate Number of Objects"
zhanwenchen/Master-Template
Template and style files for ICLR
zhanwenchen/MorphTokens
zhanwenchen/MovieChat
[CVPR 2024] 🎬💭 chat with over 10K frames of video!
zhanwenchen/OLMo
Modeling, training, eval, and inference code for OLMo
zhanwenchen/opencv-python
Automated CI toolchain to produce precompiled opencv-python, opencv-python-headless, opencv-contrib-python and opencv-contrib-python-headless packages.
zhanwenchen/PLLaVA
Official repository for the paper PLLaVA
zhanwenchen/PySceneDetect
:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.
zhanwenchen/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
zhanwenchen/stable-diffusion-webui
Stable Diffusion web UI
zhanwenchen/trl
Train transformer language models with reinforcement learning.
zhanwenchen/VideoGPT-plus
Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
zhanwenchen/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
zhanwenchen/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.