Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

Internal activation revision: Safeguarding vision language models without parameter update

Published in Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), 2024

This paper was accepted to AAAI 2025 conference.

Recommended citation: J Geng, et al. (2025). "Paper Title." Proceedings of the 39th AAAI Conference on Artificial Intelligence.
Download Paper

Published in , 1900

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities

Published in ACL 2025 Main, 2025

This paper presents a universal jailbreaking method for multimodal large language models using non-textual modalities.

Recommended citation: J Geng, TT Tran, P Nakov, I Gurevych. (2025). "Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities." ACL 2025 Main.
Download Paper

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

Published in ACL 2025 Findings, 2025

This paper introduces VSCBench, a comprehensive benchmark for evaluating safety calibration in vision-language models.

Recommended citation: J Geng, Q Li, Z Chen, Y Wang, D Zhu, Z Xie, C Lyu, X Chen, P Nakov, et al. (2025). "VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration." ACL 2025 Findings.
Download Paper

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Published in ACL 2025 Main, 2025

This paper explores methods for understanding and defending against jailbreak attacks in large language models.

Recommended citation: L Gao, J Geng, X Zhang, P Nakov, X Chen. (2025). "Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models." ACL 2025 Main.
Download Paper

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs

Published in ACL 2025 Main, 2025

This paper introduces HD-NDEs, a novel approach using neural differential equations for detecting hallucinations in large language models.

Recommended citation: Q Li, J Geng, Z Chen, D Zhu, Y Wang, C Ma, C Lyu, F Karray. (2025). "HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs." ACL 2025 Main.
Download Paper

Marco-Bench-MIF: On multilingual instruction-following capability of large language models

Published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), 2025

This paper presents Marco-Bench-MIF, a benchmark for evaluating multilingual instruction-following capabilities of large language models.

Recommended citation: B Zeng, C Lyu, S Liu, M Zeng, M Wu, X Ni, T Shi, Y Zhao, Y Liu, C Zhu, et al. (2025). "Marco-Bench-MIF: On multilingual instruction-following capability of large language models." Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics.
Download Paper

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval

Published in arXiv preprint, 2025

This paper presents CoQuIR, a comprehensive benchmark for evaluating code quality-aware information retrieval systems.

Recommended citation: J Geng, F Cai, S Cui, Q Li, L Chen, C Lyu, H Li, D Zhu, W Pretschner, et al. (2025). "CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval." arXiv preprint arXiv:2506.11066.
Download Paper

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

Published in Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

This paper introduces CaMMT, a benchmark for evaluating culturally aware multimodal machine translation systems.

Recommended citation: E Villa-Cueva, S Bolatzhanova, D Turmakhan, J Geng, et al. (2025). "CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation." Findings of the Association for Computational Linguistics: EMNLP 2025.
Download Paper

Sauce: Selective concept unlearning in vision-language models with sparse autoencoders

Published in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2025), 2025

This paper was accepted to ICCV 2025 conference.

Recommended citation: J Geng, et al. (2025). "Paper Title." Proceedings of the IEEE/CVF International Conference on Computer Vision.
Download Paper

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.