Hengrui Gu

19 papers A* 3Journal 8Unranked 8
YearRankTypeTitle / Venue / Authors
2025 A* conf
DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models.
ICLR
Kaishen Wang, Hengrui Gu, Meijun Gao, Kaixiong Zhou
2025 — conf
Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification.
DASFAA (6)
Ruxue Shi, Hengrui Gu, Xu Shen, Xin Wang
2025 J jnl
Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification.
CoRR
Ruxue Shi, Hengrui Gu, Xu Shen, Xin Wang
2025 A* conf
Latte: Transfering LLMs' Latent-level Knowledge for Few-shot Tabular Learning.
IJCAI
Ruxue Shi, Hengrui Gu, Hangting Ye, Yiwei Dai, Xu Shen, Xin Wang
2025 J jnl
Latte: Transfering LLMs' Latent-level Knowledge for Few-shot Tabular Learning.
CoRR
Ruxue Shi, Hengrui Gu, Hangting Ye, Yiwei Dai, Xu Shen, Xin Wang
2025 — conf
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense.
NAACL (Long Papers)
Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Meijun Gao, Tianlong Chen, Kaixiong Zhou
2025 J jnl
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense.
CoRR
Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Tianlong Chen, Kaixiong Zhou
2025 J jnl
PPBoost: Progressive Prompt Boosting for Text-Driven Medical Image Segmentation.
CoRR
Xuchen Li, Hengrui Gu, Mohan Zhang, Qin Liu, Zhen Tan, Xinyuan Zhu, Huixue Zhou, Tianlong Chen, Kaixiong Zhou
2025 — conf
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit.
ACL (1)
Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen
2025 J jnl
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit.
CoRR
Huixue Zhou, Hengrui Gu, Xi Liu, Kaixiong Zhou, Mingfu Liang, Yongkang Xiao, Srinivas Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen
2024 J jnl
Cross-Lingual Multi-Hop Knowledge Editing - Benchmarks, Analysis and a Simple Contrastive Learning based Approach.
CoRR
Aditi Khandelwal, Harman Singh, Hengrui Gu, Tianlong Chen, Kaixiong Zhou
2024 — conf
Cross-Lingual Multi-Hop Knowledge Editing.
EMNLP (Findings)
Aditi Khandelwal, Harman Singh, Hengrui Gu, Tianlong Chen, Kaixiong Zhou
2024 — conf
LGCRS: LLM-Guided Representation-Enhancing for Conversational Recommender System.
ICANN (9)
Ruobing Wang, Xin He, Hengrui Gu, Xin Wang
2024 A* conf
Mitigate Extrinsic Social Bias in Pre-trained Language Models via Continuous Prompts Adjustment.
EMNLP
Yiwei Dai, Hengrui Gu, Ying Wang, Xin Wang
2024 — conf
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion.
EMNLP (Findings)
Hengrui Gu, Kaixiong Zhou, Yili Wang, Ruobing Wang, Xin Wang
2024 J jnl
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion.
CoRR
Hengrui Gu, Kaixiong Zhou, Yili Wang, Ruobing Wang, Xin Wang
2024 — conf
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering.
ACL (1)
Hengrui Gu, Kaixiong Zhou, Xiaotian Han, Ninghao Liu, Ruobing Wang, Xin Wang
2023 — conf
LAGCL: Towards Stable and Automated Graph Contrastive Learning.
ADMA (3)
Hengrui Gu, Ying Wang, Xin Wang
2023 J jnl
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering.
CoRR
Hengrui Gu, Kaixiong Zhou, Xiaotian Han, Ninghao Liu, Ruobing Wang, Xin Wang