7 papers
SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning
Wenyuan Zhao, Rui Tuo, Chao Tian
Gaussian processes (GPs) provide a principled Bayesian framework for uncertainty estimation, but their computational complexity severely limits scalability to large datasets. We pr…
Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
Zihao Zhu, Wenyuan Zhao, Nuo Chen +2
Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, in current feed-forward designs, their predicted confidence…
Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
Yu-Shin Huang, Chao Tian, Krishna Narayanan
This paper considers the problem of multi-bit generative watermarking for large language models under a worst-case false-alarm constraint. Prior work established a lower bound on t…
Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
Wenyuan Zhao, Adithya Balachandran, Chao Tian +1
The study of multimodality has garnered significant interest in fields where the analysis of interactions among multiple information sources can enhance predictive modeling, data f…
Relatively-Secure LLM-Based Steganography via Constrained Markov Decision Processes
Yu-Shin Huang, Chao Tian, Krishna Narayanan +1
Linguistic steganography aims to conceal information within natural language text without being detected. An effective steganography approach should encode the secret message into…
Optimizing Leaky Private Information Retrieval Codes to Achieve Leakage Ratio Exponent
Wenyuan Zhao, Yu-Shin Huang, Chao Tian +1
We study the problem of leaky private information retrieval (L-PIR), where the amount of privacy leakage is measured by the pure differential privacy parameter, referred to as the…
OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions
Yu-Shin Huang, Peter Just, Hanyun Yin +3
We consider coverless steganography where a Large Language Model (LLM) is used to generate stego-texts in combination with arithmetic coding. An efficient method should embed secre…