no code implementations • 24 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.
no code implementations • 20 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.
no code implementations • 10 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.
no code implementations • 1 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).
no code implementations • 26 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.
no code implementations • 30 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.
4 code implementations • 11 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.
no code implementations • 1 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.
no code implementations • 14 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.
1 code implementation • 14 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.
no code implementations • 4 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.
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.
no code implementations • 13 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.
no code implementations • 1 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.
no code implementations • 12 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.
no code implementations • 19 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.
no code implementations • 13 Dec 2022 • Qisheng Zhang, Zhen Guo, Audun Jøsang, Lance M. Kaplan, Feng Chen, Dong H. Jeong, Jin-Hee Cho
Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach.
no code implementations • 22 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.
1 code implementation • 16 Oct 2022 • Chujie Zheng, Jinfeng Zhou, Yinhe Zheng, Libiao Peng, Zhen Guo, Wenquan Wu, ZhengYu Niu, Hua Wu, Minlie Huang
Dialogue contradiction is a critical issue in open-domain dialogue systems.
no code implementations • 12 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.
no code implementations • 7 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.
no code implementations • 8 Mar 2022 • Hua Lu, Zhen Guo, Chanjuan Li, Yunyi Yang, Huang He, Siqi Bao
In recent years, Internet memes have been widely used in online chatting.
no code implementations • 15 Nov 2021 • Zhen Guo, Jung Ki Song, George Barbastathis, Michael E. Glinsky, Courtenay T. Vaughan, Kurt W. Larson, Bradley K. Alpert, Zachary H. Levine
Training the deep generative models with synthetic IC data from CircuitFaker illustrates the capabilities of the learned prior from machine learning.
3 code implementations • 20 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.
3 code implementations • Findings (ACL) 2021 • Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, Xinchao Xu
To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning.
no code implementations • 5 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.
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.
8 code implementations • 13 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.