Gyungin's starred repositories
NeuralRecon
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
Tracking-Anything-with-DEVA
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
awesome-llm-security
A curation of awesome tools, documents and projects about LLM Security.
KnowledgeEditingPapers
[知识编辑] Must-read Papers on Knowledge Editing for Large Language Models.
awesome-3d-reconstruction-papers
A collection of 3D reconstruction papers in the deep learning era.
Panoptic-SegFormer
This is the official repo of Panoptic SegFormer [CVPR'22]
LLMs-Finetuning-Safety
We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.
exaggerated-safety
Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
SLAG-Belief-Updating
Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"
vos-benchmark
Fast and general video object segmentation evaluation.
howtocaption
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
probable-motion
Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns