7 citations · 9 across the 12 of their papers we have counts for
12 papers
Probabilistic Residual Learning for Online Recommendations
Wenyuan Wang, Yusong Zhao, Zihao Xu +11
Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffe…
Evidence Acquisition and Stopping via Lattice Distillation
Yixuan Zhang, Yang Song, Jiayi Zhang +4
Sequential evidence acquisition requires deciding what to observe and when to stop from partial information. We introduce a complete-record view of policy supervision: each fully o…
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
Yang Song, Yixuan Zhang, Lingfa Meng +5
Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not expose the latent interactions…
Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification
Xing Shen, Justin Szeto, Mingyang Li +2
Multimodal large language models (MLLMs) have enormous potential to perform few-shot in-context learning in the context of medical image analysis. However, safe deployment of these…
On Calibration of LLM-based Guard Models for Reliable Content Moderation
Hongfu Liu, Hengguan Huang, Xiangming Gu +2
Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM…
BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling
Hengguan Huang, Xing Shen, Songtao Wang +5
Human cognition excels at transcending sensory input and forming latent representations that structure our understanding of the world. While Large Language Model (LLM) agents demon…
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees
Guang-Yuan Hao, Hengguan Huang, Haotian Wang +2
Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domai…
Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
Hengguan Huang, Songtao Wang, Hongfu Liu +2
Traditional applications of natural language processing (NLP) in healthcare have predominantly focused on patient-centered services, enhancing patient interactions and care deliver…
Improving Robustness and Reliability in Medical Image Classification with Latent-Guided Diffusion and Nested-Ensembles
Xing Shen, Hengguan Huang, Brennan Nichyporuk +1
Once deployed, medical image analysis methods are often faced with unexpected image corruptions and noise perturbations. These unknown covariate shifts present significant challeng…
Advancing Test-Time Adaptation in Wild Acoustic Test Settings
Hongfu Liu, Hengguan Huang, Ye Wang
Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenar…
Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization
Wei Wei, Huang Hengguan, Gu Xiangming +2
Content mismatch usually occurs when data from one modality is translated to another, e.g. language learners producing mispronunciations (errors in speech) when reading a sentence…
STRODE: Stochastic Boundary Ordinary Differential Equation
Hengguan Huang, Hongfu Liu, Hao Wang +2
Perception of time from sequentially acquired sensory inputs is rooted in everyday behaviors of individual organisms. Yet, most algorithms for time-series modeling fail to learn dy…