sanqingqu

ZipIt

A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training

manipulation

Course notes for MIT manipulation class

ChatTTS

A generative speech model for daily dialogue.

Awesome-Novel-Class-Discovery

A list of papers that studies Novel Class Discovery

MRT-release

Official implementation of paper: Masked Retraining Teacher-student Framework for domain adaptive object detection. (ICCV2023)

Vision-AGI-Survey

A temporary webpage for our survey in AGI for computer vision

OrthogonalDet

[CVPR 2024] Exploring Orthogonality in Open World Object Detection

Single-DGOD

ICLR24

Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"

LISA

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

GLC-plus

Mix-of-Show

NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

LEAD

[CVPR 2024] The official repository of our paper "LEAD: Learning Decomposition for Source-free Universal Domain Adaptation"

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

LAVIS

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

BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

CVinW_Readings

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

learning_research

本人的科研经验

chatgpt-prompts-for-academic-writing

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

KnowledgeEditingPapers

[知识编辑] Must-read Papers on Knowledge Editing for Large Language Models.

NOPS

Official implementation of the CVPR 2023 paper "Novel Class Discovery for 3D Point Cloud Semantic Segmentation"

test-time-adaptation

A repository and benchmark for online test-time adaptation.

LAE

A Unified Continual Learning Framework with General Parameter-Efficient Tuning, ICCV 2023 [PyTorch Code]

all-seeing

[ICLR 2024] This is the official implementation of the paper "The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World"

hamlet

Source code for "To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation", ICCV 2023

Benchmark-TTA

online-da

Official Pytorch Codebase for Towards Online Domain Adaptive Object Detection [WACV 2023]

DiffPure

A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.

visprog

Official code for VisProg (CVPR 2023 Best Paper!)

mlc-llm

Universal LLM Deployment Engine with ML Compilation