UCSB ML&NLP Group

Pinned Repositories

CoPaint
Implementation of paper 'Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models'
Language:Python64 3 86
DiffSTE
Language:Python88 4 237
Diffusion-SpaceTime-Attn
Official implementation of the paper "Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis"
Language:Jupyter Notebook88 5 83
diffusion_resampling
Implementation for "Correcting Diffusion Generation through Resampling" [CVPR 2024]
Language:Python32 2 12
DiffusionDisentanglement
Official implementation of the paper "Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Language:Jupyter Notebook162 5 99
Fairness-Reprogramming
Language:Python15 3 34
llm_uncertainty
Language:Python26 1 12
PromptBoosting
Language:Python15 1 04
TextGrad
Language:Python20 1 12
ULD
Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24]
Language:Python15 3 10

UCSB ML&NLP Group's Repositories

UCSB-NLP-Chang/DiffusionDisentanglement
Official implementation of the paper "Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Language:Jupyter Notebook162 5 99
UCSB-NLP-Chang/DiffSTE
Language:Python88 4 237
UCSB-NLP-Chang/Diffusion-SpaceTime-Attn
Official implementation of the paper "Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis"
Language:Jupyter Notebook88 5 83
UCSB-NLP-Chang/CoPaint
Implementation of paper 'Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models'
Language:Python64 3 86
UCSB-NLP-Chang/diffusion_resampling
Implementation for "Correcting Diffusion Generation through Resampling" [CVPR 2024]
Language:Python32 2 12
UCSB-NLP-Chang/llm_uncertainty
Language:Python26 1 12
UCSB-NLP-Chang/TextGrad
Language:Python20 1 12
UCSB-NLP-Chang/Fairness-Reprogramming
Language:Python15 3 34
UCSB-NLP-Chang/PromptBoosting
Language:Python15 1 04
UCSB-NLP-Chang/ULD
Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24]
Language:Python15 3 10
UCSB-NLP-Chang/causal_unlearn
[EMNLP 2024] "Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective"
Language:Python12 1 0
UCSB-NLP-Chang/SelfDenoise
Language:Python12 4 22
UCSB-NLP-Chang/SemanticSmooth
Implementation of paper 'Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing'
Language:Python12 3 33
UCSB-NLP-Chang/Augment_tableQA
Language:Python9 1 00
UCSB-NLP-Chang/Prereq_tune
Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"
6
UCSB-NLP-Chang/Visual-Spatial-Planning
Official release of the benchmark in paper "VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs"
Language:Python6 1 0
UCSB-NLP-Chang/BTProp