198 citations · 481 across the 31 of their papers we have counts for
32 papers
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
Zinan Lin, Tadas Baltrusaitis, Wenyu Wang +1
Differentially private (DP) synthetic data enables the use of sensitive datasets while providing strong privacy guarantees. Recently, Private Evolution (PE) has emerged as a promis…
GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
Kaiyi Huang, Yukun Huang, Xuefei Ning +3
Text-to-video generation models have shown significant progress in the recent years. However, they still struggle with generating complex dynamic scenes based on compositional text…
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Enshu Liu, Xuefei Ning, Yu Wang +1
Autoregressive (AR) models have achieved state-of-the-art performance in text and image generation but suffer from slow generation due to the token-by-token process. We ask an ambi…
Statistic Maximal Leakage
Shuaiqi Wang, Zinan Lin, Giulia Fanti
We introduce a privacy measure called statistic maximal leakage that quantifies how much a privacy mechanism leaks about a specific secret, relative to the adversary's prior inform…
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie +5
With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant ba…
Inferentially-Private Private Information
Shuaiqi Wang, Shuran Zheng, Zinan Lin +2
Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privac…
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin +6
The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their subst…
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Xuefei Ning, Zifu Wang, Shiyao Li +7
Teaching to improve student models (e.g., knowledge distillation) is an extensively studied methodology in LLMs. However, for humans, teaching improves not only students but also t…
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Haofeng Huang +10
Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, la…
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang +6
Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-con…
Improving the Training of Rectified Flows
Sangyun Lee, Zinan Lin, Giulia Fanti
Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. On…
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin +8
Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate we…
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
Lin Zhao, Tianchen Zhao, Zinan Lin +4
In recent years, there has been significant progress in the development of text-to-image generative models. Evaluating the quality of the generative models is one essential step in…
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi +2
Many methods in differentially private model training rely on computing the similarity between a query point (such as public or synthetic data) and private data. We abstract out th…
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs +9
Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is priva…
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Ronghao Ni, Zinan Lin, Shuaiqi Wang +1
Long-term time series forecasting (LTSF) aims to predict future values of a time series given the past values. The current state-of-the-art (SOTA) on this problem is attained in so…
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A. Inan +6
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the priv…
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou +3
This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding ap…
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin +2
Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains. Despite the promise, one major…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni +2
Generating differentially private (DP) synthetic data that closely resembles the original private data is a scalable way to mitigate privacy concerns in the current data-driven wor…
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…
Summary Statistic Privacy in Data Sharing
Zinan Lin, Shuaiqi Wang, Vyas Sekar +1
We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e.g., mean, standard deviation).…
On the Privacy Properties of GAN-generated Samples
Zinan Lin, Vyas Sekar, Giulia Fanti
The privacy implications of generative adversarial networks (GANs) are a topic of great interest, leading to several recent algorithms for training GANs with privacy guarantees. By…