8 papers
Difficulty-Aware Semantic-ID Optimization for Generative Recommendation
Xin Yu, Stephen Li, Sina Aghaei +6
Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, ye…
Composition for Pufferfish Privacy
Jiamu Bai, Guanlin He, Xin Gu +2
When creating public data products out of confidential datasets, inferential/posterior-based privacy definitions, such as Pufferfish, provide compelling privacy semantics for data…
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
Jiaming Hu, Jiamu Bai, Haoyu Wang +2
Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct…
Accurate and Scalable Matrix Mechanisms via Divide and Conquer
Guanlin He, Yingtai Xiao, Jiamu Bai +4
Matrix mechanisms are often used to provide unbiased differentially private query answers when publishing statistics or creating synthetic data. Recent work has developed matrix me…
Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Xin Gu, Yingtai Xiao, Guanlin He +3
Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a l…
FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
Yan Gao, Massimo Roberto Scamarcia, Javier Fernandez-Marques +18
Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data, raisin…