sail-sg / D-TRAKLinks
Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
☆30Updated last year
Alternatives and similar repositories for D-TRAK
Users that are interested in D-TRAK are comparing it to the libraries listed below
Sorting:
- [TMLR 2025] On Memorization in Diffusion Models☆26Updated last year
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆22Updated last year
- What do we learn from inverting CLIP models?☆54Updated last year
- ☆34Updated 5 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆85Updated 7 months ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Updated 2 years ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆39Updated 6 months ago
- ☆54Updated 2 years ago
- PDM-based Purifier☆20Updated 7 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆18Updated last year
- ☆19Updated 10 months ago
- ☆27Updated last month
- [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders☆24Updated 3 weeks ago
- ☆14Updated last year
- ☆19Updated 3 weeks ago
- Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24…☆17Updated 11 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆78Updated 7 months ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆17Updated 2 weeks ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆37Updated last year
- ☆14Updated 2 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆102Updated last year
- ☆40Updated 9 months ago
- Discover and Cure: Concept-aware Mitigation of Spurious Correlation (ICML 2023)☆41Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 7 months ago
- Code for Debiasing Vision-Language Models via Biased Prompts☆57Updated 2 years ago
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆34Updated last month
- ☆22Updated 10 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated last month
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Updated last month
- ☆15Updated last month