Jin Peng Zhou

43 papers A* 10A 3Journal 28Unranked 2
YearRankTypeTitle / Venue / Authors
2026 A* conf
K-12EduBench: A Benchmark for Evaluating Large Language Models' Knowledge, Problem-Solving, and Educational Goal Cognition in K-12 Education.
AAAI
Yuqing Ye, Xuan Zhou, Zhifu Chen, Dandan Li, Hengnian Gu, Jin Peng Zhou, Dongdai Zhou
2025 J jnl
Cognitive Structure Generation: From Educational Priors to Policy Optimization.
CoRR
Hengnian Gu, Zhifu Chen, Yuxin Chen, Jin Peng Zhou, Dongdai Zhou
2025 J jnl
Efficient Controllable Diffusion via Optimal Classifier Guidance.
CoRR
Owen Oertell, Shikun Sun, Yiding Chen, Jin Peng Zhou, Zhiyong Wang, Wen Sun
2025 A* conf
Graders Should Cheat: Privileged Information Enables Expert-Level Automated Evaluations.
EMNLP
Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding, Kilian Q. Weinberger, Nan Hua, Fei Sha
2025 J jnl
Graders should cheat: privileged information enables expert-level automated evaluations.
CoRR
Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding, Kilian Q. Weinberger, Nan Hua, Fei Sha
2025 A* conf
Hierarchical Disentanglement of Cognitive States for Enhanced Cognitive Diagnosis.
ACM Multimedia
Hengnian Gu, Zhifu Chen, Jin Peng Zhou, Dongdai Zhou
2025 — conf
INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations.
CASE
Qian Meng, Jin Peng Zhou, Kilian Q. Weinberger, Hadas Kress-Gazit
2025 J jnl
INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations.
CoRR
Qian Meng, Jin Peng Zhou, Kilian Q. Weinberger, Hadas Kress-Gazit
2025 J jnl
Learned-Database Systems Security.
Trans. Mach. Learn. Res.
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer, Paul Grubbs, Nicolas Papernot
2025 J jnl
Learning to decode logical circuits.
Nat. Comput. Sci.
Yiqing Zhou, Chao Wan, Yichen Xu, Jin Peng Zhou, Kilian Q. Weinberger, Eun-Ah Kim
2025 A* conf
On Speeding Up Language Model Evaluation.
ICLR
Jin Peng Zhou, Christian K. Belardi, Ruihan Wu, Travis Zhang, Carla P. Gomes, Wen Sun, Kilian Q. Weinberger
2025 J jnl
Pre-training Large Memory Language Models with Internal and External Knowledge.
CoRR
Linxi Zhao, Sofian Zalouk, Christian K. Belardi, Justin Lovelace, Jin Peng Zhou, Kilian Q. Weinberger, Yoav Artzi, Jennifer J. Sun
2025 J jnl
Q♯: Provably Optimal Distributional RL for LLM Post-Training.
CoRR
Jin Peng Zhou, Kaiwen Wang, Jonathan D. Chang, Zhaolin Gao, Nathan Kallus, Kilian Q. Weinberger, Kianté Brantley, Wen Sun
2025 A* conf
Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond.
ICLR
Qizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han, Kilian Q. Weinberger
2025 J jnl
Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond.
CoRR
Qizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han, Kilian Q. Weinberger
2025 J jnl
Value-Guided Search for Efficient Chain-of-Thought Reasoning.
CoRR
Kaiwen Wang, Jin Peng Zhou, Jonathan D. Chang, Zhaolin Gao, Nathan Kallus, Kianté Brantley, Wen Sun
2024 J jnl
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff.
CoRR
Hao Tang, Keya Hu, Jin Peng Zhou, Sicheng Zhong, Wei-Long Zheng, Xujie Si, Kevin Ellis
2024 A* conf
Don't Trust: Verify - Grounding LLM Quantitative Reasoning with Autoformalization.
ICLR
Jin Peng Zhou, Charles Staats, Wenda Li, Christian Szegedy, Kilian Q. Weinberger, Yuhuai Wu
2024 J jnl
Don't Trust: Verify - Grounding LLM Quantitative Reasoning with Autoformalization.
CoRR
Jin Peng Zhou, Charles Staats, Wenda Li, Christian Szegedy, Kilian Q. Weinberger, Yuhuai Wu
2024 J jnl
Enhancing Cognitive Diagnosis by Modeling Learner Cognitive Structure State.
CoRR
Zhifu Chen, Hengnian Gu, Jin Peng Zhou, Dongdai Zhou
2024 J jnl
Leveraging diffusion models for unsupervised out-of-distribution detection on image manifold.
Frontiers Artif. Intell.
Zhenzhen Liu, Jin Peng Zhou, Kilian Q. Weinberger
2024 A* conf
Magnushammer: A Transformer-Based Approach to Premise Selection.
ICLR
Maciej Mikula, Szymon Tworkowski, Szymon Antoniak, Bartosz Piotrowski, Albert Q. Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
2024 J jnl
On Speeding Up Language Model Evaluation.
CoRR
Jin Peng Zhou, Christian K. Belardi, Ruihan Wu, Travis Zhang, Carla P. Gomes, Wen Sun, Kilian Q. Weinberger
2024 J jnl
Orchestrating LLMs with Different Personalizations.
CoRR
Jin Peng Zhou, Katie Z. Luo, Jingwen Gu, Jason Yuan, Kilian Q. Weinberger, Wen Sun
2024 A* conf
REFACTOR: Learning to Extract Theorems from Proofs.
ICLR
Jin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger Baker Grosse
2024 J jnl
REFACTOR: Learning to Extract Theorems from Proofs.
CoRR
Jin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger B. Grosse
2024 J jnl
Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks.
CoRR
Jinyan Su, Jin Peng Zhou, Zhengxin Zhang, Preslav Nakov, Claire Cardie
2024 J jnl
Zero-shot Object-Level OOD Detection with Context-Aware Inpainting.
CoRR
Quang-Huy Nguyen, Jin Peng Zhou, Zhenzhen Liu, Khanh-Huyen Bui, Kilian Q. Weinberger, Dung D. Le
2023 J jnl
Correction with Backtracking Reduces Hallucination in Summarization.
CoRR
Zhenzhen Liu, Chao Wan, Varsha Kishore, Jin Peng Zhou, Minmin Chen, Kilian Q. Weinberger
2023 A conf
Does Label Differential Privacy Prevent Label Inference Attacks?
AISTATS
Ruihan Wu, Jin Peng Zhou, Kilian Q. Weinberger, Chuan Guo
2023 A* conf
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs.
ICLR
Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothée Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, Yuhuai Wu
2023 J jnl
Magnushammer: A Transformer-based Approach to Premise Selection.
CoRR
Maciej Mikula, Szymon Antoniak, Szymon Tworkowski, Albert Qiaochu Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
2023 A* conf
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting.
ICML
Zhenzhen Liu, Jin Peng Zhou, Yufan Wang, Kilian Q. Weinberger
2023 J jnl
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting.
CoRR
Zhenzhen Liu, Jin Peng Zhou, Yufan Wang, Kilian Q. Weinberger
2022 J jnl
Does Label Differential Privacy Prevent Label Inference Attacks?
CoRR
Ruihan Wu, Jin Peng Zhou, Kilian Q. Weinberger, Chuan Guo
2022 J jnl
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs.
CoRR
Albert Q. Jiang, Sean Welleck, Jin Peng Zhou, Wenda Li, Jiacheng Liu, Mateja Jamnik, Timothée Lacroix, Yuhuai Wu, Guillaume Lample
2022 J jnl
Learned Systems Security.
CoRR
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer, Paul Grubbs, Nicolas Papernot
2021 A conf
Bayesian Preference Elicitation with Keyphrase-Item Coembeddings for Interactive Recommendation.
UMAP
Hojin Yang, Scott Sanner, Ga Wu, Jin Peng Zhou
2020 J jnl
Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering.
CoRR
Jin Peng Zhou, Ga Wu, Zheda Mai, Scott Sanner
2020 J jnl
Not My Deepfake: Towards Plausible Deniability for Machine-Generated Media.
CoRR
Baiwu Zhang, Jin Peng Zhou, Ilia Shumailov, Nicolas Papernot
2020 — conf
Predicting Twitter Engagement With Deep Language Models.
RecSys Challenge
Maksims Volkovs, Zhaoyue Cheng, Mathieu Ravaut, Hojin Yang, Kevin Shen, Jin Peng Zhou, Anson Wong, Saba Zuberi, Ivan Zhang, Nick Frosst, Helen Ngo, Carol Chen, Bharat Venkitesh, Stephen Gou, Aidan N. Gomez
2020 A conf
TAFA: Two-headed Attention Fused Autoencoder for Context-Aware Recommendations.
RecSys
Jin Peng Zhou, Zhaoyue Cheng, Felipe Pérez, Maksims Volkovs
2019 J jnl
Incremental Association Rule Mining Based on Matrix Compression for Edge Computing.
IEEE Access
Dongdai Zhou, Meng Ouyang, Zhejun Kuang, Zhen Li, Jin Peng Zhou, Xiaochun Cheng