Xiaomeng Hu

According to our database1, Xiaomeng Hu authored at least 19 papers between 2022 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs.
CoRR, July, 2025

Flow-CDNet: A Novel Network for Detecting Both Slow and Fast Changes in Bitemporal Images.
CoRR, July, 2025

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models.
CoRR, May, 2025

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization.
CoRR, May, 2025

ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
Mapping the neural mechanism that distinguishes between holistic thinking and analytic thinking.
NeuroImage, 2024

TableGPT2: A Large Multimodal Model with Tabular Data Integration.
CoRR, 2024

The high dimensional psychological profile and cultural bias of ChatGPT.
CoRR, 2024

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023
Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning.
CoRR, 2023

A multi-objective optimization trajectory interpolation method based on fifth-degree B-spline curves <sup>*</sup>.
Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2023

Multi-objective geometric optimization of a multi-link robot manipulator considering dynamics performance.
Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2023

RADAR: Robust AI-Text Detection via Adversarial Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022
P<sup>3</sup> Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning.
CoRR, 2022

P3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning.
Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

Stiffness modeling of redundant robots with large load capacity and workspace.
Proceedings of the IEEE International Conference on Real-time Computing and Robotics, 2022

Multi-Objective Geometric Optimization of A Multi-Link Manipulator Using Parameterized Design Method.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022


  Loading...