SolidShen

SolidShen's Stars

• openai/CLIP

  CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

  Language:Jupyter Notebook26.7k3254053.4k

• haotian-liu/LLaVA

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

  Language:Python20.8k1581.6k2.3k

• jacobgil/pytorch-grad-cam

  Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

  Language:Python10.8k454201.6k

• mlfoundations/open_clip

  An open source implementation of CLIP.

  Language:Python10.6k805041k

• voxel51/fiftyone

  Refine high-quality datasets and visual AI models

  Language:Python9k631.6k583

• IDEA-Research/GroundingDINO

  [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

  Language:Python7.1k44310712

• ondyari/FaceForensics

  Github of the FaceForensics dataset

  Language:Python2.4k7187543

• microsoft/GLIP

  Grounded Language-Image Pre-training

  Language:Python2.3k45171196

• hendrycks/test

  Measuring Massive Multitask Language Understanding | ICLR 2021

  Language:Python1.3k182096

• tylin/coco-caption

  Language:Jupyter Notebook1.1k2456545

• SunzeY/AlphaCLIP

  [CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

  Language:Jupyter Notebook740135446

• mlfoundations/wise-ft

  Robust fine-tuning of zero-shot models

  Language:Python66362666

• SCLBD/DeepfakeBench

  A comprehensive benchmark of deepfake detection

  Language:Python6212312990

• mapooon/SelfBlendedImages

  [CVPR 2022 Oral] Detecting Deepfakes with Self-Blended Images https://arxiv.org/abs/2204.08376

  Language:Python21775335

• akoksal/LongForm

  Reverse Instructions to generate instruction tuning data with corpus examples

  2073210

• ethz-spylab/rlhf_trojan_competition

  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.

  Language:Python109479

• reds-lab/Narcissus

  The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.

  Language:Python10521012

• anthropics/sleeper-agents-paper

  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

  913110

• AllanYangZhou/nfn

  NF-Layers for constructing neural functionals.

  Language:Python774105

• Unispac/Circumventing-Backdoor-Defenses

  Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)

  Language:Python34116

• nctu-eva-lab/AntifakePrompt

  This is the official implementation of AntifakePrompt.

  Language:Jupyter Notebook26221

• SolidShen/RIPPLE_official

  Language:Python20103

• KaiyuanZh/OrthogLinearBackdoor

  [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks

  Language:Python19121

• Lyz1213/BadEdit

  Language:Python19132

• RU-System-Software-and-Security/BppAttack

  Language:Python18124

• Reality-Defender/Research-DD-VQA

  16130

• DPamK/BadAgent

  Language:Python14141

• ZhangZhuoSJTU/LINT

  Language:Python14100

• Megum1/ODSCAN

  [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models

  Language:Python11200

• reds-lab/BEEAR

  This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models".

  Language:HTML10111