43 citations · 249 across the 65 of their papers we have counts for
7 papers · 1 filter
StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers
Xujun Che, Depeng Xu, Xintao Wu
Differentially private (DP) training of text-conditioned generative models suffers a utility cliff at strong privacy. We revisit this problem through the geometry of rectified flow…
BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials
An Vuong, Chen Zhao, Jin Hu +2
Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals interactions. The…
MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models
Dong Li, Yanchi Liu, Xujiang Zhao +6
Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments. However, directly updating their li…
Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis
Dong Li, Yanchi Liu, Xujiang Zhao +6
Although structured workflows empower Large Language Models (LLMs) to tackle complex problems, automating their creation is severely hindered by a vast combinatorial search space,…
Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach
An Vuong, Minh-Hao Van, Chen Zhao +1
AI for materials science is a critical topic within AI for science, aiming to accelerate materials discovery and produce accurate property predictions. Bilayer 2D material stacking…
Leveraging Foundation Models for Causal Generative Modeling
Aneesh Komanduri, Xintao Wu
Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causa…
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
Eduardo Tenorio, Karuna Bhaila, Xintao Wu
Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a princip…