🏢 Duke University

Diffusion guidance, a common generative modeling technique, is shown to not sample from its intended distribution; instead, it heavily biases samples towards the boundary of the conditional distributi…

Unlocking the speed and efficiency of Mixture-of-Expert models, this research unveils novel optimization techniques, achieving dramatic improvements in inference throughput and resource usage.

Provably efficient randomized exploration in cooperative MARL is achieved via a novel unified algorithm framework, CoopTS, using Thompson Sampling with PHE and LMC exploration strategies.

DNNs are powerful but lack the clear semantics of PGMs. This paper innovatively constructs infinite tree-structured PGMs that exactly correspond to DNNs, revealing that DNN forward propagation approxi…

ParamRepulsor, a novel parametric dimensionality reduction method, achieves state-of-the-art local structure preservation by mining hard negatives and using a tailored loss function.

Minimax-optimal, computationally efficient algorithms are proposed for distributionally robust offline reinforcement learning, addressing challenges posed by function approximation and model uncertain…

M-GAM: Interpretable additive models handling missing data with superior accuracy & sparsity!

Calibrated Bayesian inference achieved via novel diffusion models uniquely mapping high-dimensional data to lower-dimensional Gaussian distributions.

Boosting machine learning model interpretability, this paper introduces cluster-based and tree-based Sparse Explanation Values (SEV) for generating more meaningful and credible explanations by optimiz…

GUIDE: Real-time human-shaped AI agents achieve up to 30% higher success rates using continuous human feedback, boosted by a parallel training model that mimics human input for continued improvement.

A new combinatorial algorithm dramatically speeds up semi-discrete optimal transport calculations, offering an efficient solution for large datasets and higher dimensions.