JingxuanKang

RLCF

[ICLR 2024] Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models. :rocket::rocket::rocket:

AI-Math-Teacher

An-Erudite-FGVC-Model

Code release for Your “An Erudite Fine-Grained Visual Classification Model (CVPR 2023)"

img2img-turbo

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

FAMix

[CVPR 2024] Official repository of "A Simple Recipe for Language-guided Domain Generalized Segmentation"

chrome-plugin-demo

《Chrome插件开发全攻略》配套完整Demo，欢迎clone体验

geekai

AI 助手全套开源解决方案，自带运营管理后台，开箱即用。集成了 ChatGPT, Azure, ChatGLM,讯飞星火，文心一言等多个平台的大语言模型。支持 MJ AI 绘画，Stable Diffusion AI 绘画，微博热搜等插件工具。采用 Go + Vue3 + element-plus 实现。

Neural-Network-Parameter-Diffusion

We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

Debiased-Self-Training

Code release of paper Debiased Self-Training for Semi-Supervised Learning (NeurIPS 2022 Oral)

VideoTogether

Browser Extension to Watch Videos Together on All Platforms / 一起看视频浏览器插件，兼容所有平台

LifeReloaded

A life simulation Game powered by GPT-4's “Advanced Data Analysis” function , offering you a second chance at life. 由GPT4的Advanced Data Analysis功能驱动的人生重来模拟器，给您人生第二春。

Tune-A-Video

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

PromptSRC

[ICCV'23 Main Track, WECIA'23 Oral] Official repository of paper titled "Self-regulating Prompts: Foundational Model Adaptation without Forgetting".

ISDA-for-Deep-Networks

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

DomainDrop

The official implementation for DomainDrop (ICCV 2023).

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

MultiObjectiveOptimization

Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"

APE

[ICCV 2023] Code for "Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement"

Subspace-Prompt-Learning

Official code for "Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models" (TCSVT'2023)

TPT

Test-time Prompt Tuning (TPT) for zero-shot generalization in vision-language models (NeurIPS 2022))

CHILS

Code and results accompanying our paper titled CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

FLYP

Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models

wise-ft

Robust fine-tuning of zero-shot models

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

ZSCL

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

TOAST

Official code for "TOAST: Transfer Learning via Attention Steering"

aidea

AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。

cross_modal_adaptation

Cross-modal few-shot adaptation with CLIP

CLIPood

About Code Release for "CLIPood: Generalizing CLIP to Out-of-Distributions" (ICML 2023), https://arxiv.org/abs/2302.00864

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.