Jinghan Jia - RankMe

58 papers A* 14A 1Misc 2Journal 35Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	BLUR: A Bi-Level Optimization Approach for LLM Unlearning. EACL (Volume 1: Long Papers) Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong
2025	J	`jnl`	BLUR: A Bi-Level Optimization Approach for LLM Unlearning. CoRR Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong
2025	J	`jnl`	Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability. CoRR Jinghan Jia, Nathalie Baracaldo, Sijia Liu
2025	J	`jnl`	CyclicReflex: Improving Large Reasoning Models via Cyclical Reflection Token Scheduling. CoRR Chongyu Fan, Yihua Zhang, Jinghan Jia, Alfred Olivier Hero, Sijia Liu
2025	J	`jnl`	Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning. CoRR Yicheng Lang, Yihua Zhang, Chongyu Fan, Changsheng Wang, Jinghan Jia, Sijia Liu
2025	J	`jnl`	EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation. CoRR Jinghan Jia, Hadi Reisizadeh, Chongyu Fan, Nathalie Baracaldo, Mingyi Hong, Sijia Liu
2025	A*	`conf`	Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning. ICML Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu
2025	J	`jnl`	Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning. CoRR Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu
2025	—	`conf`	LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data. AISec@CCS Changsheng Wang, Yihua Zhang, Dennis Wei, Jinghan Jia, Pin-Yu Chen, Sijia Liu
2025	J	`jnl`	LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data. CoRR Changsheng Wang, Yihua Zhang, Dennis Wei, Jinghan Jia, Pin-Yu Chen, Sijia Liu
2025	J	`jnl`	One Token Embedding Is Enough to Deadlock Your Large Reasoning Model. CoRR Mohan Zhang, Yihua Zhang, Jinghan Jia, Zhangyang Wang, Sijia Liu, Tianlong Chen
2025	A*	`conf`	Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills. EMNLP Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
2025	J	`jnl`	Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills. CoRR Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
2025	J	`jnl`	Rethinking machine unlearning for large language models. Nat. Mac. Intell. Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Yuguang Yao, Chris Yuhao Liu, Xiaojun Xu, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, Yang Liu
2025	J	`jnl`	Robust MRI Reconstruction by Smoothed Unrolling (SMUG). IEEE J. Sel. Top. Signal Process. Shijun Liang, Van Hoang Minh Nguyen, Jinghan Jia, Ismail R. Alkhouri, Sijia Liu, Saiprasad Ravishankar
2025	A*	`conf`	Robust Multi-bit Text Watermark with LLM-based Paraphrasers. ICML Xiaojun Xu, Jinghan Jia, Yuanshun Yao, Yang Liu, Hang Li
2025	—	`conf`	SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? ACL (1) Haomin Zhuang, Yihua Zhang, Kehan Guo, Jinghan Jia, Gaowen Liu, Sijia Liu, Xiangliang Zhang
2025	A*	`conf`	Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond. ICML Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu
2025	J	`jnl`	Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond. CoRR Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu
2024	A*	`conf`	DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training. ICLR Aochuan Chen, Yimeng Zhang, Jinghan Jia, James Diffenderfer, Konstantinos Parasyris, Jiancheng Liu, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
2024	A*	`conf`	Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models. NeurIPS Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu
2024	J	`jnl`	Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models. CoRR Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu
2024	J	`jnl`	Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification. CoRR Changchang Sun, Ren Wang, Yihua Zhang, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Sijia Liu, Yan Yan
2024	J	`jnl`	Label Smoothing Improves Machine Unlearning. CoRR Zonglin Di, Zhaowei Zhu, Jinghan Jia, Jiancheng Liu, Zafar Takhirov, Bo Jiang, Yuanshun Yao, Sijia Liu, Yang Liu
2024	—	`conf`	Leveraging LLMs for Dialogue Quality Measurement. NAACL (Industry Track) Jinghan Jia, Abi Komma, Timothy Leffel, Xujun Peng, Ajay Nagesh, Tamer Soliman, Aram Galstyan, Anoop Kumar
2024	J	`jnl`	Leveraging LLMs for Dialogue Quality Measurement. CoRR Jinghan Jia, Abi Komma, Timothy Leffel, Xujun Peng, Ajay Nagesh, Tamer Soliman, Aram Galstyan, Anoop Kumar
2024	J	`jnl`	Rethinking Machine Unlearning for Large Language Models. CoRR Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Xiaojun Xu, Yuguang Yao, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, Yang Liu
2024	J	`jnl`	Robust Multi-bit Text Watermark with LLM-based Paraphrasers. CoRR Xiaojun Xu, Jinghan Jia, Yuanshun Yao, Yang Liu, Hang Li
2024	A*	`conf`	SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning. EMNLP Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
2024	J	`jnl`	SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning. CoRR Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
2024	J	`jnl`	Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning. CoRR Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu
2024	—	`conf`	To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy to Generate Unsafe Images ... For Now. ECCV (57) Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, Sijia Liu
2024	J	`jnl`	UOE: Unlearning One Expert Is Enough For Mixture-of-experts LLMS. CoRR Haomin Zhuang, Yihua Zhang, Kehan Guo, Jinghan Jia, Gaowen Liu, Sijia Liu, Xiangliang Zhang
2024	J	`jnl`	UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models. CoRR Yihua Zhang, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Xiaoming Liu, Sijia Liu
2024	A*	`conf`	UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models. NeurIPS Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Kompella, Xiaoming Liu, Sijia Liu
2024	A*	`conf`	WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models. NeurIPS Jinghan Jia, Jiancheng Liu, Yihua Zhang, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
2024	J	`jnl`	WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models. CoRR Jinghan Jia, Jiancheng Liu, Yihua Zhang, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
2023	A	`conf`	ClawSAT: Towards Both Robust and Accurate Code Models. SANER Jinghan Jia, Shashank Srikant, Tamara Mitrovska, Chuang Gan, Shiyu Chang, Sijia Liu, Una-May O'Reilly
2023	J	`jnl`	DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training. CoRR Aochuan Chen, Yimeng Zhang, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
2023	J	`jnl`	Model Sparsification Can Simplify Machine Unlearning. CoRR Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
2023	A*	`conf`	Model Sparsity Can Simplify Machine Unlearning. NeurIPS Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
2023	J	`jnl`	Robust MRI Reconstruction by Smoothed Unrolling (SMUG). CoRR Shijun Liang, Van Hoang Minh Nguyen, Jinghan Jia, Ismail Alkhouri, Sijia Liu, Saiprasad Ravishankar
2023	Misc	`conf`	Robustness-Preserving Lifelong Learning Via Dataset Condensation. ICASSP Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu, Alfred O. Hero III
2023	J	`jnl`	Robustness-preserving Lifelong Learning via Dataset Condensation. CoRR Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu, Alfred O. Hero III
2023	Misc	`conf`	SMUG: Towards Robust Mri Reconstruction by Smoothed Unrolling. ICASSP Hui Li, Jinghan Jia, Shijun Liang, Yuguang Yao, Saiprasad Ravishankar, Sijia Liu
2023	J	`jnl`	SMUG: Towards robust MRI reconstruction by smoothed unrolling. CoRR Hui Li, Jinghan Jia, Shijun Liang, Yuguang Yao, Saiprasad Ravishankar, Sijia Liu
2023	A*	`conf`	Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning. NeurIPS Yihua Zhang, Yimeng Zhang, Aochuan Chen, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Mingyi Hong, Shiyu Chang, Sijia Liu
2023	J	`jnl`	Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning. CoRR Yihua Zhang, Yimeng Zhang, Aochuan Chen, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Mingyi Hong, Shiyu Chang, Sijia Liu
2023	A*	`conf`	Text-Visual Prompting for Efficient 2D Temporal Video Grounding. CVPR Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding
2023	J	`jnl`	Text-Visual Prompting for Efficient 2D Temporal Video Grounding. CoRR Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding
2023	A*	`conf`	TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization. ICLR Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang
2023	J	`jnl`	To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now. CoRR Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, Sijia Liu
2022	J	`jnl`	CLAWSAT: Towards Both Robust and Accurate Code Models. CoRR Jinghan Jia, Shashank Srikant, Tamara Mitrovska, Chuang Gan, Shiyu Chang, Sijia Liu, Una-May O'Reilly
2022	A*	`conf`	How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective. ICLR Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jinfeng Yi, Mingyi Hong, Shiyu Chang, Sijia Liu
2022	J	`jnl`	How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective. CoRR Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jinfeng Yi, Mingyi Hong, Shiyu Chang, Sijia Liu
2022	J	`jnl`	TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization. CoRR Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang
2021	—	`conf`	Instabilities in Conventional Multi-Coil MRI Reconstruction with Small Adversarial Perturbations. ACSCC Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akçakaya
2021	J	`jnl`	On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations. CoRR Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akçakaya