Haoxiang-Wang

multi-task-learning

Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

Bloqade.jl

Package for the quantum computation and quantum simulation based on the neutral-atom architecture.

Compositional-Feature-Alignment

Code of Compositional Feature Alignment for Finetuning CLIP and DINOv2

Cosmos-Tokenizer

A suite of image and video neural tokenizers

DeepLearningImplementations

Implementation of recent Deep Learning papers

FedADG

Federated Adversarial Domain Generalization

gradual-domain-adaptation

Code for Gradual Domain Adaptation

Directional-Preference-Alignment

Directional Preference Alignment

RLHF-Reward-Modeling

Recipes to train reward model for RLHF.

ISR

Invariant-feature Subspace Recovery (ISR)

Haoxiang-Wang/Compositional-Feature-Alignment

Code of Compositional Feature Alignment for Finetuning CLIP and DINOv2

Haoxiang-Wang/FedADG

Federated Adversarial Domain Generalization

Haoxiang-Wang/gradual-domain-adaptation

Code for Gradual Domain Adaptation

Haoxiang-Wang/Cosmos-Tokenizer

A suite of image and video neural tokenizers

Haoxiang-Wang/DeepLearningImplementations

Implementation of recent Deep Learning papers

Haoxiang-Wang/Bloqade.jl

Package for the quantum computation and quantum simulation based on the neutral-atom architecture.

Haoxiang-Wang/dev-axolotl

Go ahead and axolotl questions

Haoxiang-Wang/Gradient_Starvation

Gradient Starvation: A Learning Proclivity in Neural Networks

Haoxiang-Wang/Haoxiang-Wang.github.io

Haoxiang Wang's Personal Website

Haoxiang-Wang/higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Haoxiang-Wang/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Haoxiang-Wang/Mixup-Data-Dependency

Code associated with the paper "Towards Understanding the Data Dependency of Mixup-style Training".

Haoxiang-Wang/models

Models built with TensorFlow

Haoxiang-Wang/neural-tangents

Fast and Easy Infinite Neural Networks in Python

Haoxiang-Wang/reward-bench

RewardBench: the first evaluation tool for reward models.

Haoxiang-Wang/huggingface.js

Utilities to use the Hugging Face Hub API

Haoxiang-Wang/tensorboard-aggregator

Aggregate multiple tensorboard runs to new summary or csv files

Haoxiang-Wang/tensorflow

Computation using data flow graphs for scalable machine learning

Haoxiang-Wang/UIUC-CS225

Machine problems for UIUC data structures

Haoxiang-Wang/wise-ft

Haoxiang-Wang/write-rnn-tensorflow

Generative Handwriting using LSTM Mixture Density Network with TensorFlow