32 citations · 111 across the 39 of their papers we have counts for
17 papers · 1 filter
When Does Retrieval Help? A Study of In-Context Adaptation in Vision-Language-Action Models
Zixuan Liu, Joris Köster, Zizhan Zheng +1
Vision-language-action (VLA) models have shown strong potential as generalist robot policies, but adapting them to unseen tasks often requires costly parameter updates. Recent work…
Adaptive Multilevel Twisted Sequential Monte Carlo for Rare Events Estimation in Language Models
Zixuan Liu, Fangzheng Wu, Brian Summa +1
Rare unsafe behaviors in large language models can remain practically significant even when their probability is extremely small, particularly at deployment scales involving millio…
Robust General Utility for Reinforcement Learning
Zixuan Liu, Fangzheng Wu, Brian Summa +1
Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broade…
Stealthy World Model Manipulation via Data Poisoning
Yibin Hu, Xiaolin Sun, Zizhan Zheng
Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from colle…
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
Zixuan Liu, Xiaolin Sun, Zizhan Zheng
Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards t…
Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
Xiaolin Sun, Feidi Liu, Zhengming Ding +1
Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based…
Online Learning with Probing for Sequential User-Centric Selection
Tianyi Xu, Yiting Chen, Henger Li +3
We formalize sequential decision-making with information acquisition as the probing-augmented user-centric selection (PUCS) framework, where a learner first probes a subset of arms…
Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits
Tianyi Xu, Jiaxin Liu, Nicholas Mattei +1
We propose a multi-agent multi-armed bandit (MA-MAB) framework aimed at ensuring fair outcomes across agents while maximizing overall system performance. A key challenge in this se…
Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
Tao Li, Henger Li, Yunian Pan +3
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to speci…
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
Xiaolin Sun, Zizhan Zheng
Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicio…
Enhancing LLM Safety via Constrained Direct Preference Optimization
Zixuan Liu, Xiaolin Sun, Zizhan Zheng
The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulne…
A First Order Meta Stackelberg Method for Robust Federated Learning
Yunian Pan, Tao Li, Henger Li +3
Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be no…
Learning to Backdoor Federated Learning
Henger Li, Chen Wu, Sencun Zhu +1
In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this…
Online Learning for Adaptive Probing and Scheduling in Dense WLANs
Tianyi Xu, Ding Zhang, Zizhan Zheng
Existing solutions to network scheduling typically assume that the instantaneous link rates are completely known before a scheduling decision is made or consider a bandit setting w…
Joint AP Probing and Scheduling: A Contextual Bandit Approach
Tianyi Xu, Ding Zhang, Parth H. Pathak +1
We consider a set of APs with unknown data rates that cooperatively serve a mobile client. The data rate of each link is i.i.d. sampled from a distribution that is unknown a priori…
Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
Dan Peng, Zizhan Zheng, Xiaofeng Zhang
Adversarial examples are perturbed inputs designed to fool machine learning models. Most recent works on adversarial examples for image classification focus on directly modifying p…
When to Reset Your Keys: Optimal Timing of Security Updates via Learning
Zizhan Zheng, Ness B. Shroff, Prasant Mohapatra
Cybersecurity is increasingly threatened by advanced and persistent attacks. As these attacks are often designed to disable a system (or a critical resource, e.g., a user account)…