no code implementations • 8 May 2024 • Renjie Liu, Yichuan Wang, Xiao Yan, Zhenkun Cai, Minjie Wang, Haitian Jiang, Bo Tang, Jinyang Li
In particular, by conducting graph sampling beforehand, DiskGNN acquires the node features that will be accessed by model computation, and such information is utilized to pack the target node features contiguously on disk to avoid read amplification.
no code implementations • 3 Apr 2024 • Tomoyoshi Kimura, Jinyang Li, Tianshi Wang, Denizhan Kara, Yizhuo Chen, Yigong Hu, Ruijie Wang, Maggie Wigness, Shengzhong Liu, Mani Srivastava, Suhas Diggavi, Tarek Abdelzaher
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications.
1 code implementation • 13 Mar 2024 • Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities.
no code implementations • 8 Mar 2024 • Jinyang Li, Nan Huo, Yan Gao, Jiayi Shi, Yingxiu Zhao, Ge Qu, Yurong Wu, Chenhao Ma, Jian-Guang Lou, Reynold Cheng
The challenges and costs of collecting realistic interactive logs for data analysis hinder the quantitative evaluation of Large Language Model (LLM) agents in this task.
1 code implementation • 7 Mar 2024 • Sijia Chen, En Yu, Jinyang Li, Wenbing Tao
In this study, we pioneer an exploration into the distribution patterns of tracking data and identify a pronounced long-tail distribution issue within existing MOT datasets.
1 code implementation • 20 Feb 2024 • Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, DaCheng Tao, Tianyi Zhou
In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral.
no code implementations • 3 Feb 2024 • Tianshi Wang, Jinyang Li, Ruijie Wang, Denizhan Kara, Shengzhong Liu, Davis Wertheimer, Antoni Viros-i-Martin, Raghu Ganti, Mudhakar Srivatsa, Tarek Abdelzaher
To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered.
1 code implementation • 16 Jan 2024 • Xilai Li, Xiaosong Li, Haishu Tan, Jinyang Li
Existing multi-focus image fusion (MFIF) methods often fail to preserve the uncertain transition region and detect small focus areas within large defocused regions accurately.
no code implementations • 9 Dec 2023 • Lingfan Yu, Jinyang Li
Consequently, when LLMs are used in the common setting of multi-turn conversations, a growing log of the conversation history must be processed alongside any request by the serving system at each turn, resulting in repeated history processing.
1 code implementation • NeurIPS 2023 • Shengzhong Liu, Tomoyoshi Kimura, Dongxin Liu, Ruijie Wang, Jinyang Li, Suhas Diggavi, Mani Srivastava, Tarek Abdelzaher
Existing multimodal contrastive frameworks mostly rely on the shared information between sensory modalities, but do not explicitly consider the exclusive modality information that could be critical to understanding the underlying sensing physics.
1 code implementation • 8 Oct 2023 • Chengwen Qi, Bowen Li, Binyuan Hui, Bailin Wang, Jinyang Li, Jinwang Wu, Yuanjun Laili
Our ConvRE features two tasks, Re2Text and Text2Re, which are formulated as multi-choice question answering to evaluate LLMs' ability to determine the matching between relations and associated text.
no code implementations • 19 Jul 2023 • Jinyang Li, Zhepeng Wang, Zhirui Hu, Prasanna Date, Ang Li, Weiwen Jiang
The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers.
1 code implementation • 18 May 2023 • Yingxiu Zhao, Bowen Yu, Haiyang Yu, Bowen Li, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin L. Zhang
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
no code implementations • NeurIPS 2023 • Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin C. C. Chang, Fei Huang, Reynold Cheng, Yongbin Li
Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.
Ranked #1 on Text-To-SQL on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) (Execution Accurarcy (Human) metric)
no code implementations • 23 Apr 2023 • Zhepeng Wang, Jinyang Li, Zhirui Hu, Blake Gage, Elizabeth Iwasawa, Weiwen Jiang
We further developed a reinforcement learning-based security engine, which can automatically optimize the model design under the distributed setting, such that a good trade-off between model performance and security can be made.
1 code implementation • 18 Jan 2023 • Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, Yongbin Li
Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization.
Ranked #4 on Semantic Parsing on spider
no code implementations • 30 Dec 2022 • Jinyang Li, Yuval Moskovitch, H. V. Jagadish
We propose efficient search algorithms for two different fairness measures: global representation bounds, and proportional representation.
no code implementations • 29 Aug 2022 • Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, Fei Huang, Yongbin Li
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
1 code implementation • 26 Jul 2022 • Jiawei Liu, JinKun Lin, Fabian Ruffy, Cheng Tan, Jinyang Li, Aurojit Panda, Lingming Zhang
In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers.
no code implementations • 2 Jul 2022 • Xingyu Wu, Jinyang Li
The system mainly implements two functions based on the activity inference of the sensor data, which are real time abnormal activity monitoring and trend prediction of disease related activities.
1 code implementation • 20 Jun 2022 • JinKun Lin, Anqi Zhang, Mathias Lecuyer, Jinyang Li, Aurojit Panda, Siddhartha Sen
Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution.
1 code implementation • 1 Oct 2021 • Jinning Li, Huajie Shao, Dachun Sun, Ruijie Wang, Yuchen Yan, Jinyang Li, Shengzhong Liu, Hanghang Tong, Tarek Abdelzaher
Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e. g., posts that represent user views) into an appropriate disentangled latent space.
1 code implementation • 19 Nov 2020 • Lingfan Yu, Jiajun Shen, Jinyang Li, Adam Lerer
Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data.
Ranked #20 on Node Property Prediction on ogbn-mag
1 code implementation • The 18th Conference on Embedded Networked Sensor Systems 2020 • Shuochao Yao, Jinyang Li, Dongxin Liu, Tianshi Wang, Shengzhong Liu, Huajie Shao, Tarek Abdelzaher
With comprehensive evaluations, our system can consistently reduce end-to-end latency by 2× to 4× with 1% accuracy loss, compared to state-of-the-art neural network offloading systems.
no code implementations • 2 Nov 2020 • Shuochao Yao, Yifan Hao, Yiran Zhao, Huajie Shao, Dongxin Liu, Shengzhong Liu, Tianshi Wang, Jinyang Li, Tarek Abdelzaher
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of local embedded devices that are themselves unable to support extensive computations.
no code implementations • 13 Jun 2020 • Ziming Liu, Guangyu Gao, A. K. Qin, Jinyang Li
Finally, the DTG-Net is evaluated in two ways: (i) the self-supervised DTG-Net to pre-train the supervised action recognition models with only unlabeled videos; (ii) the supervised DTG-Net to be jointly trained with the supervised action networks in an end-to-end way.
1 code implementation • 13 Feb 2020 • Chaoqi Yang, Jinyang Li, Ruijie Wang, Shuochao Yao, Huajie Shao, Dongxin Liu, Shengzhong Liu, Tianshi Wang, Tarek F. Abdelzaher
In the synthetic dataset, our model reduces error by 40%.
7 code implementations • 3 Sep 2019 • Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, Tianjun Xiao, Tong He, George Karypis, Jinyang Li, Zheng Zhang
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs.
Ranked #35 on Node Classification on Cora
1 code implementation • 21 Feb 2019 • Shuochao Yao, Ailing Piao, Wenjun Jiang, Yiran Zhao, Huajie Shao, Shengzhong Liu, Dongxin Liu, Jinyang Li, Tianshi Wang, Shaohan Hu, Lu Su, Jiawei Han, Tarek Abdelzaher
IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain.
no code implementations • 24 Jul 2018 • Minjie Wang, Chien-chin Huang, Jinyang Li
This paper presents Tofu, a system that partitions very large DNN models across multiple GPU devices to reduce per-GPU memory footprint.
no code implementations • 10 May 2018 • Minjie Wang, Chien-chin Huang, Jinyang Li
We present this automatic tiling in a new system, SoyBean, that can act as a backend for Tensorflow, MXNet, and others.