YB
Yuheng Bu
cs.LGcs.ITmath.ITstat.MLcs.AIcs.CLcs.CRcs.CVeess.SPmath.ST
On Valency
published · living versionsW_bqucpr6z·v1 · currentpublished
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
with Yepeng Liu, Shengmai Chen, Xuandong Zhao, Chengzhi Liu +2
1 version
Preprints & journals
61 papers in the corpus · 2015–2026Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction2609.17815v1 · Ruiquan Li, Yuheng Bu2026 · 0 citationsarXiv
Figures as Programs: Recursive Generation of Editable Scientific Figures2609.01006v1 · Yepeng Liu, Dasen Dai, Chengzhi Liu et al.2026 · 0 citationsarXiv
Learning to Follow In-Context Watermark Instructions via Self-Distillation2608.29030v1 · Yepeng Liu, Tianyi Chen, Xuandong Zhao et al.2026 · 0 citationsarXiv
Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains2607.03680v1 · Zhuoer Shen, Mingyi Wang, Shaofeng Zou et al.2026 · 0 citationsarXiv
Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization2606.24025v1 · Haobo Chen, Xiangxiang Xu, Yuheng Bu2026 · 0 citationsarXiv
Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization2606.00392v1 · Mingyi Wang, Zhuoer Shen, Yuheng Bu et al.2026 · 0 citationsarXiv
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction2605.29341v2 · Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu et al.2026 · 0 citationsarXiv
Auditing Agent Harness Safety2605.14271v2 · Chengzhi Liu, Yichen Guo, Yepeng Liu et al.2026 · 0 citationsarXiv
Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes2605.08826v1 · Haiyun He, Yepeng Liu, Zhuoer Shen et al.2026 · 0 citationsarXiv
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling2604.27039v2 · Zhen Zhang, Changyi Yang, Zijie Xia et al.2026 · 0 citationsarXiv
ConvexBench: Can LLMs Recognize Convex Functions?2602.01075v2 · Yepeng Liu, Yu Huang, Yu-Xiang Wang et al.2026 · 0 citationsarXiv
TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction2601.13422v1 · Dahai Yu, Rongchao Xu, Dingyi Zhuang et al.2026 · 0 citationsarXiv
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking2510.21053v1 · Li An, Yujian Liu, Yepeng Liu et al.2025 · 0 citationsarXiv
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption2510.18333v2 · Yepeng Liu, Xuandong Zhao, Dawn Song et al.2025 · 0 citationsarXiv
Alternative Graph Neural Networks: Synergizing GEV Models and Deep Learning for Travel Mode Choice Modeling2509.07123v2 · Yuqi Zhou, Zhanhong Cheng, Dingyi Zhuang et al.2025 · 0 citationsarXiv
UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction2508.08551v2 · Dahai Yu, Dingyi Zhuang, Lin Jiang et al.2025 · 4 citationsarXiv
Graph neural networks for residential location choice: connection to classical logit models2507.21334v1 · Zhanhong Cheng, Lingqian Hu, Yuheng Bu et al.2025 · 3 citationsarXiv
SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Prompting2506.19658v1 · Yang Xing, Jiong Wu, Yuheng Bu et al.2025 · 0 citationsarXiv
Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective2506.07861v1 · Firas Laakom, Haobo Chen, Jurgen Schmidhuber et al.2025 · 0 citationsarXiv
In-Context Watermarks for Large Language Models2505.16934v2 · Yepeng Liu, Xuandong Zhao, Christopher Kruegel et al.2025 · 0 citationsarXiv
Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning2504.06575v2 · Li An, Yujian Liu, Yepeng Liu et al.2025 · 0 citationsarXiv
Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs2502.10673v2 · Yepeng Liu, Xuandong Zhao, Dawn Song et al.2025 · 0 citationsarXiv
Distributional Information Embedding: A Framework for Multi-bit Watermarking2501.16558v2 · Haiyun He, Yepeng Liu, Ziqiao Wang et al.2025 · 0 citationsarXiv
Information-theoretic Analysis of the Gibbs Algorithm: An Individual Sample Approach2410.12623v1 · Youheng Zhu, Yuheng Bu2024 · 1 citationarXiv
Image Watermarks are Removable Using Controllable Regeneration from Clean Noise2410.05470v2 · Yepeng Liu, Yiren Song, Hai Ci et al.2024 · 0 citationsarXiv
Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach2410.02890v5 · Haiyun He, Yepeng Liu, Ziqiao Wang et al.2024 · 0 citationsarXiv
SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks2409.08766v1 · Dingyi Zhuang, Yuheng Bu, Guang Wang et al.2024 · 5 citationsarXiv
An Algorithm for Computing the Capacity of Symmetrized KL Information for Discrete Channels2407.13436v1 · Haobo Chen, Gholamali Aminian, Yuheng Bu2024 · 1 citationarXiv
Information-Theoretic Opacity-Enforcement in Markov Decision Processes2405.00157v2 · Chongyang Shi, Yuheng Bu, Jie Fu2024 · 3 citationsarXiv
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?2402.06160v3 · Maohao Shen, J. Jon Ryu, Soumya Ghosh et al.2024 · 10 citationsarXiv
Operator SVD with Neural Networks via Nested Low-Rank Approximation2402.03655v2 · J. Jon Ryu, Xiangxiang Xu, H. S. Melihcan Erol et al.2024 · 0 citationsarXiv
Adaptive Text Watermark for Large Language Models2401.13927v2 · Yepeng Liu, Yuheng Bu2024 · 4 citationsarXiv
Class-wise Generalization Error: an Information-Theoretic Analysis2401.02904v1 · Firas Laakom, Yuheng Bu, Moncef Gabbouj2024 · 0 citationsarXiv
Gibbs-Based Information Criteria and the Over-Parameterized Regime2306.05583v2 · Haobo Chen, Yuheng Bu, Gregory W. Wornell2023 · 2 citationsarXiv
Feature Learning in Image Hierarchies using Functional Maximal Correlation2305.20074v1 · Bo Hu, Yuheng Bu, Jos'e C. Pr'incipe2023 · 0 citationsarXiv
A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatch2305.08207v1 · Amir Weiss, Alejandro Lancho, Yuheng Bu et al.2023 · 4 citationsarXiv
Reliable Gradient-free and Likelihood-free Prompt Tuning2305.00593v1 · Maohao Shen, Soumya Ghosh, Prasanna Sattigeri et al.2023 · 7 citationsarXiv
On the Generalization Error of Meta Learning for the Gibbs Algorithm2304.14332v1 · Yuheng Bu, Harsha Vardhan Tetali, Gholamali Aminian et al.2023 · 4 citationsarXiv
Group Fairness with Uncertainty in Sensitive Attributes2302.08077v2 · Abhin Shah, Maohao Shen, Jongha Jon Ryu et al.2023 · 1 citationarXiv
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model2212.07359v1 · Maohao Shen, Yuheng Bu, Prasanna Sattigeri et al.2022 · 30 citationsarXiv
Information-theoretic Characterizations of Generalization Error for the Gibbs Algorithm2210.09864v1 · Gholamali Aminian, Yuheng Bu, Laura Toni et al.2022 · 12 citationsarXiv
How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?2210.08188v2 · Haiyun He, Gholamali Aminian, Yuheng Bu et al.2022 · 3 citationsarXiv
Data-Driven Blind Synchronization and Interference Rejection for Digital Communication Signals2209.04871v1 · Alejandro Lancho, Amir Weiss, Gary C.F. Lee et al.2022 · 10 citationsarXiv
Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation2208.10325v1 · Gary C.F. Lee, Amir Weiss, Alejandro Lancho et al.2022 · 7 citationsarXiv
A Maximal Correlation Framework for Fair Machine Learning.35455124 · Lee, Joshua, Bu, Yuheng, Sattigeri, Prasanna et al.2022 · 2 citationsEntropy (Basel, Switzerland). 2022;24(4)
Tighter Expected Generalization Error Bounds via Convexity of Information Measures2202.12150v1 · Gholamali Aminian, Yuheng Bu, Gregory Wornell et al.2022 · 16 citationsarXiv
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation2202.00796v3 · Maohao Shen, Yuheng Bu, Gregory Wornell2022 · 12 citationsarXiv
Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm2111.01635v1 · Yuheng Bu, Gholamali Aminian, Laura Toni et al.2021 · 5 citationsarXiv
Selective Regression Under Fairness Criteria2110.15403v3 · Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee et al.2021 · 4 citationsarXiv
Population Risk Improvement with Model Compression: An Information-Theoretic Approach.34681979 · Bu, Yuheng, Gao, Weihao, Zou, Shaofeng et al.2021 · 10 citationsEntropy (Basel, Switzerland). 2021;23(10)
Career total: 90 works. 61 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.