CV
Curriculum vitae and selected research experience.
Contact Information
| Name | Tianle Gu |
| Professional Title | LLM Safety Researcher |
| gtl23@mails.tsinghua.edu.cn | |
| Website | https://github.com/Carol-gutianle |
Professional Summary
Researcher at Tencent, working on conversational LLMs and LLM safety.
Experience
-
2026 - Present
Education
-
2023 - 2026 M.Eng.
Tsinghua University
Electronic Information
- Supervised by Prof. Yujiu Yang, National Scholarship * 1
-
2019 - 2023 B.Eng.
Hunan University
Computer Science and Technology
- National Scholarship * 2
Publications
-
**Tianle Gu**, Zeyang Zhou, Kexin Huang, et al. MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
Accepted by NeurIPS 2024
We designed a multi-dimensional safety benchmark for MLLMs, including bilingual data, an inference toolkit, and a lightweight automatic evaluator.
-
**Tianle Gu, Zongqi Wang**, Kexin Huang, et al. Invisible Entropy: A Safe and Efficient Paradigm for Low-entropy Watermarking
ArXiv; Accepted by EMNLP Main Conference (Oral)
We introduced IE, a watermarking framework for low-entropy text without origin LLMs.
-
**Tianle Gu**, Kexin Huang, Zongqi Wang, et al. Probing the Safety Robustness of LLMs in Latent Space
Accepted by ACL 2026 Main Conference
We proposed an adversarial attack-and-defense framework to systematically uncover and mitigate latent vulnerabilities in LLM safety.
-
**Tianle Gu**, Kexin Huang, Ruilin Luo, et al. From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs
ArXiv; Accepted by ACL 2025 Findings
We proposed a streamlined knowledge-unlearning algorithm that improves forgetting quality while preserving NLU/NLG utility and resilience to MIA.
-
**Tianle Gu**, Kexin Huang, Lingyu Li, et al. From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation
Submitted to ICML 2026
We proposed UniMod, a shift from sparse binary decisions to dense reasoning trajectories for fine-grained multimodal safety moderation.
Projects
-
ValuePRM - Core Contributor
- Led ValuePRM training with response-level data to evaluate and verify value-aligned behavior in MLLMs.
- Proficient with OpenRLHF for training and fine-tuning both 7B and 70B models.
-
ChatZoo (80+ stars)
- Developed ChatZoo, an open-source toolkit for local development and evaluation of multiple LLMs.
-
CoLLiE (400+ stars)
- Accepted by EMNLP Demo 2023.
- Integrated efficient optimization and soft-prompt adaptation for better performance and resource utilization.
-
OpenRT (200+ stars)
- Introduced a standard red-teaming framework for quick evaluation.
Internship
Notes
- Note: Bold indicates first or co-first author.