6 citations · 7 across the 10 of their papers we have counts for
13 papers
LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models
Zixuan Liu, Nan Xue, Rui Bao +4
Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. However, generating each token still involves sequential computation and repeat…
Weighted Ensemble Sampling for Rare-Event Estimation in Language Models
Zixuan Liu, Gustavo Didier, Fangzheng Wu +2
Rare but severe failures of large language models can become practically significant at deployment scale. Estimating their probabilities with direct Monte Carlo sampling is highly…
Risk-Conditioned Fine-Tuning of Large Language Models
Zixuan Liu, Fangzheng Wu, Brian Summa +2
Large Language Models (LLMs) are increasingly deployed in settings where rare but severe harmful generations can have significant consequences. Existing Risk-Averse RLHF addresses…
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…
WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference
Zixuan Liu, Zhiyong Chen, Nan Xue +4
While distributed device-edge speculative decoding enhances resource utilization across heterogeneous nodes, its performance is often bottlenecked by conventional token-level verif…
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…
What Makes Value Learning Efficient in Residual Reinforcement Learning?
Guozheng Ma, Lu Li, Haoyu Wang +3
Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value l…
A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
Zixuan Liu, Yi Zhao, Zhuotao Liu +4
Machine Learning (ML)-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. H…
On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
Zhiyi Dong, Zixuan Liu, Yongyi Mao
This paper studies the hardness of unsupervised domain adaptation (UDA) under covariate shift. We model the uncertainty that the learner faces by a distribution in the ground-t…
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…
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Guozheng Ma, Lu Li, Sen Zhang +6
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like…
Enhancing Cross-Dataset Performance of Distracted Driving Detection With Score Softmax Classifier And Dynamic Gaussian Smoothing Supervision
Cong Duan, Zixuan Liu, Jiahao Xia +3
Deep neural networks enable real-time monitoring of in-vehicle drivers, facilitating the timely prediction of distractions, fatigue, and potential hazards. This technology is now i…