activity
20192025
most citedConversational Dueling Bandits in Generalized Linear Models

6 citations · 15 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV20251 cited

SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement

Chelsi Jain, Yiran Wu, Yifan Zeng +5

Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modali…

cs.LG20246 cited

Conversational Dueling Bandits in Generalized Linear Models

Shuhua Yang, Hui Yuan, Xiaoying Zhang +3

Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed band…

cs.LG20241 cited

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

Zhiwei Wang, Huazheng Wang, Hongning Wang

Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and f…

cs.CL2023

How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?

Huazheng Wang, Daixuan Cheng, Haifeng Sun +5

Transformer-based pretrained language models (PLMs) have achieved great success in modern NLP. An important advantage of PLMs is good out-of-distribution (OOD) robustness. Recently…

cs.LG20231 cited

Adversarial Attacks on Online Learning to Rank with Stochastic Click Models

Zichen Wang, Rishab Balasubramanian, Hui Yuan +3

We propose the first study of adversarial attacks on online learning to rank. The goal of the adversary is to misguide the online learning to rank algorithm to place the target ite…

cs.LG20223 cited

Dynamic Global Sensitivity for Differentially Private Contextual Bandits

Huazheng Wang, David Zhao, Hongning Wang

Bandit algorithms have become a reference solution for interactive recommendation. However, as such algorithms directly interact with users for improved recommendations, serious pr…