Search Results for author: Zhen Guo

Found 28 papers, 7 papers with code

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs

no code implementations24 Jan 2025 Zhen Guo, Reza Tourani

With the growing demand for personalized AI solutions, customized LLMs have become a preferred choice for businesses and individuals, driving the deployment of millions of AI agents across various platforms, e. g., GPT Store hosts over 3 million customized GPTs.

Backdoor Attack

Persistent Backdoor Attacks in Continual Learning

no code implementations20 Sep 2024 Zhen Guo, Abhinav Kumar, Reza Tourani

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications.

Continual Learning

Scaling Law Hypothesis for Multimodal Model

no code implementations10 Sep 2024 Qingyun Sun, Zhen Guo, PIN AI Team

We propose a scaling law hypothesis for multimodal models processing text, audio, images, and video within a shared token and embedding space.

Decoder model

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability

no code implementations1 Jul 2024 Chenxi Li, Abhinav Kumar, Zhen Guo, Jie Hou, Reza Tourani

The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs).

Octo-planner: On-device Language Model for Planner-Action Agents

no code implementations26 Jun 2024 Wei Chen, Zhiyuan Li, Zhen Guo, Yikang Shen

In this paper, we present an efficient on-device Planner-Action framework that separates planning and action execution into two distinct components: a planner agent based on Phi-3 Mini, a 3. 8 billion parameter LLM optimized for edge devices, and an action agent using the Octopus model for function execution.

Computational Efficiency In-Context Learning +2

More Compute Is What You Need

no code implementations30 Apr 2024 Zhen Guo

Large language model pre-training has become increasingly expensive, with most practitioners relying on scaling laws to allocate compute budgets for model size and training tokens, commonly referred to as Compute-Optimal or Chinchilla Optimal.

Language Modeling Language Modelling +1

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

4 code implementations11 Apr 2024 Yikang Shen, Zhen Guo, Tianle Cai, Zengyi Qin

Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-human intelligence.

Automated HER2 Scoring in Breast Cancer Images Using Deep Learning and Pyramid Sampling

no code implementations1 Apr 2024 Sahan Yoruc Selcuk, Xilin Yang, Bijie Bai, Yijie Zhang, Yuzhu Li, Musa Aydin, Aras Firat Unal, Aditya Gomatam, Zhen Guo, Darrow Morgan Angus, Goren Kolodney, Karine Atlan, Tal Keidar Haran, Nir Pillar, Aydogan Ozcan

Human epidermal growth factor receptor 2 (HER2) is a critical protein in cancer cell growth that signifies the aggressiveness of breast cancer (BC) and helps predict its prognosis.

Prognosis

Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning

no code implementations14 Mar 2024 Xilin Yang, Bijie Bai, Yijie Zhang, Musa Aydin, Sahan Yoruc Selcuk, Zhen Guo, Gregory A. Fishbein, Karine Atlan, William Dean Wallace, Nir Pillar, Aydogan Ozcan

Systemic amyloidosis is a group of diseases characterized by the deposition of misfolded proteins in various organs and tissues, leading to progressive organ dysfunction and failure.

API Pack: A Massive Multi-Programming Language Dataset for API Call Generation

1 code implementation14 Feb 2024 Zhen Guo, Adriana Meza Soria, Wei Sun, Yikang Shen, Rameswar Panda

We introduce API Pack, a massive multi-programming language dataset containing over one million instruction-API calls for improving the API call generation capabilities of large language models.

Diversity Measurement and Subset Selection for Instruction Tuning Datasets

no code implementations4 Feb 2024 Peiqi Wang, Yikang Shen, Zhen Guo, Matthew Stallone, Yoon Kim, Polina Golland, Rameswar Panda

Our experiments demonstrate that the proposed diversity measure in the normalized weight gradient space is correlated with downstream instruction-following performance.

Diversity Instruction Following +1

CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing

1 code implementation CVPR 2024 Zhen Guo, Hongping Gan

In the domain of compressive sensing (CS) deep unfolding networks (DUNs) have garnered attention for their good performance and certain degree of interpretability rooted in CS domain achieved by marrying traditional optimization solvers with deep networks.

Compressive Sensing

AuthentiGPT: Detecting Machine-Generated Text via Black-Box Language Models Denoising

no code implementations13 Nov 2023 Zhen Guo, Shangdi Yu

Under the assumption that human-written text resides outside the distribution of machine-generated text, AuthentiGPT leverages a black-box LLM to denoise input text with artificially added noise, and then semantically compares the denoised text with the original to determine if the content is machine-generated.

Denoising Language Modeling +1

Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering

no code implementations1 Nov 2023 Zhen Guo, Yining Hua

This work demonstrates a method using continuous training and instruction fine-tuning to rapidly adapt Llama 2 base models to the Chinese medical domain.

Question Answering

Improving Small Language Models on PubMedQA via Generative Data Augmentation

no code implementations12 May 2023 Zhen Guo, Peiqi Wang, Yanwei Wang, Shangdi Yu

Large Language Models (LLMs) have made remarkable advancements in the field of natural language processing.

Data Augmentation Question Answering

Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information

no code implementations19 Feb 2023 Zhen Guo, Qi Zhang, Xinwei An, Qisheng Zhang, Audun Jøsang, Lance M. Kaplan, Feng Chen, Dong H. Jeong, Jin-Hee Cho

Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches.

Decision Making Deep Reinforcement Learning +2

Noise-resilient approach for deep tomographic imaging

no code implementations22 Nov 2022 Zhen Guo, Zhiguang Liu, Qihang Zhang, George Barbastathis, Michael E. Glinsky

We propose a noise-resilient deep reconstruction algorithm for X-ray tomography.

A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning

no code implementations12 Jun 2022 Zhen Guo, Zelin Wan, Qisheng Zhang, Xujiang Zhao, Feng Chen, Jin-Hee Cho, Qi Zhang, Lance M. Kaplan, Dong H. Jeong, Audun Jøsang

We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty.

Decision Making Survey

Physics-assisted Generative Adversarial Network for X-Ray Tomography

no code implementations7 Apr 2022 Zhen Guo, Jung Ki Song, George Barbastathis, Michael E. Glinsky, Courtenay T. Vaughan, Kurt W. Larson, Bradley K. Alpert, Zachary H. Levine

X-ray tomography is capable of imaging the interior of objects in three dimensions non-invasively, with applications in biomedical imaging, materials science, electronic inspection, and other fields.

Generative Adversarial Network

PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation

3 code implementations20 Sep 2021 Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, Zheng-Yu Niu

To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conversations.

Dialogue Generation

OTHR multitarget tracking with a GMRF model of ionospheric parameters

no code implementations5 May 2020 Zhen Guo, Zengfu Wang, Hua Lan, Quan Pan, Kun Lu

Therefore, to improve the localization accuracy of OTHR, it is important to develop accurate models and estimation methods of ionospheric parameters and the corresponding target tracking algorithms.

Proactive Human-Machine Conversation with Explicit Conversation Goal

no code implementations ACL 2019 Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, Haifeng Wang

Konv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph.

Proactive Human-Machine Conversation with Explicit Conversation Goals

8 code implementations13 Jun 2019 Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, Haifeng Wang

DuConv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph.

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