sail-sg / GDPO
Graph Diffusion Policy Optimization
☆24Updated 6 months ago
Related projects: ⓘ
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆93Updated last month
- ☆57Updated last week
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆22Updated 7 months ago
- GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations☆43Updated 2 weeks ago
- Official Code for paper "Towards Efficient and Effective Unlearning of Large Language Models for Recommendation" (Frontiers of Computer S…☆34Updated 2 months ago
- [Arxiv 2024] Adversarial attacks on multimodal agents☆33Updated 2 months ago
- "Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?"☆55Updated this week
- ☆24Updated 2 weeks ago
- Code for the paper - ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning☆13Updated last month
- Parsimonious Concept Engineering (PaCE) uses sparse coding on a large-scale concept dictionary to effectively improve the trustworthiness…☆25Updated 3 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆43Updated last month
- Privacy backdoors☆41Updated 4 months ago
- [ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆78Updated 5 months ago
- On Memorization in Diffusion Models☆22Updated 11 months ago
- Decomposing and Editing Predictions by Modeling Model Computation☆97Updated 3 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆14Updated 2 weeks ago
- 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆52Updated 3 weeks ago
- Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models☆67Updated this week
- Code for the paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆21Updated 6 months ago
- ☆23Updated 2 months ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆47Updated last month
- A task generation and model evaluation system.☆51Updated 2 weeks ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆25Updated last month
- Official Repository of Multi-Object Hallucination in Vision-Language Models☆19Updated last month
- [CCS 2024] "BadMerging: Backdoor Attacks Against Model Merging": official code implementation.☆17Updated 3 weeks ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆89Updated 3 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆34Updated 2 months ago
- Official implementation of Goldfish Loss: Mitigating Memorization in Generative LLMs☆68Updated 2 months ago
- The official implementation of Self-Exploring Language Models (SELM)☆55Updated 3 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆59Updated 3 months ago