Search Results for author: Jiahao Yu

Found 13 papers, 5 papers with code

Decoupled Alignment for Robust Plug-and-Play Adaptation

no code implementations3 Jun 2024 Haozheng Luo, Jiahao Yu, Wenxin Zhang, Jialong Li, Jerry Yao-Chieh Hu, Xinyu Xing, Han Liu

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF).

Knowledge Distillation

Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens

no code implementations31 May 2024 Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu, Wenbo Guo, Han Liu, Xinyu Xing

Attackers carefully craft jailbreaking prompts such that a target LLM will respond to the harmful question.

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

1 code implementation5 May 2024 Zelei Cheng, Xian Wu, Jiahao Yu, Sabrina Yang, Gang Wang, Xinyu Xing

In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks.


Q2A: Querying Implicit Fully Continuous Feature Pyramid to Align Features for Medical Image Segmentation

no code implementations15 Apr 2024 Jiahao Yu, Li Chen

Therefore, we propose Q2A, a novel one-step query-based aligning paradigm, to solve the feature misalignment problem in the INR-based decoder.

Decoder Image Segmentation +2

Assessing Prompt Injection Risks in 200+ Custom GPTs

1 code implementation20 Nov 2023 Jiahao Yu, Yuhang Wu, Dong Shu, Mingyu Jin, Sabrina Yang, Xinyu Xing

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications.

Toward Trustworthy Identity Tracing via Multi-attribute Synergistic Identification

no code implementations5 Nov 2023 Decheng Liu, Jiahao Yu, Ruimin Hu, Wenbin Feng

Based on the proposed identity model, we propose a trustworthy identity tracing framework (TITF) with multi-attribute synergistic identification to determine the identity of unknown objects, which can optimize the core identification set and provide an interpretable identity tracing process.


GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

1 code implementation19 Sep 2023 Jiahao Yu, Xingwei Lin, Zheng Yu, Xinyu Xing

Remarkably, GPTFuzz achieves over 90% attack success rates against ChatGPT and Llama-2 models, even with suboptimal initial seed templates.

Minimizing $f$-Divergences by Interpolating Velocity Fields

1 code implementation24 May 2023 Song Liu, Jiahao Yu, Jack Simons, Mingxuan Yi, Mark Beaumont

Wasserstein Gradient Flow can move particles along a path that minimizes the $f$-divergence between the target and particle distributions.

Domain Adaptation Imputation

$\mathcal{L}_1$Quad: $\mathcal{L}_1$ Adaptive Augmentation of Geometric Control for Agile Quadrotors with Performance Guarantees

no code implementations14 Feb 2023 Zhuohuan Wu, Sheng Cheng, Pan Zhao, Aditya Gahlawat, Kasey A. Ackerman, Arun Lakshmanan, Chengyu Yang, Jiahao Yu, Naira Hovakimyan

Quadrotors that can operate safely in the presence of imperfect model knowledge and external disturbances are crucial in safety-critical applications.

Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models

no code implementations31 Oct 2022 Wenli Yang, Guan Huang, Renjie Li, Jiahao Yu, Yanyu Chen, Quan Bai, Beyong Kang

Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of AI-assisted applications.

Feature Correlation

SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage

1 code implementation CVPR 2022 Jiahao Yu, Li Chen, Mingrui Zhang, Mading Li

While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree.

Aesthetic Photo Collage with Deep Reinforcement Learning

no code implementations19 Oct 2021 Mingrui Zhang, Mading Li, Li Chen, Jiahao Yu

To overcome the lack of training data, we pretrain our deep aesthetic network on a large scale image aesthetic dataset (CPC) for general aesthetic feature extraction and propose an attention fusion module for structural collage feature representation.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.