Search Results for author: YuHan Liu

Found 43 papers, 9 papers with code

基于循环交互注意力网络的问答立场分析(A Recurrent Interactive Attention Network for Answer Stance Analysis)

no code implementations CCL 2020 Wangda Luo, YuHan Liu, Bin Liang, Ruifeng Xu

针对问答立场任务中, 现有方法难以提取问答文本间的依赖关系问题, 本文提出一种基于循环交互注意力(Recurrent Interactive Attention, RIA)网络的问答立场分析方法。该方法通过模仿人类阅读理解时的思维方式, 基于交互注意力机制和循环迭代方法, 有效地从问题和答案的相互联系中挖掘问答文本的立场信息。此外, 该方法将问题进行陈述化表示, 有效地解决疑问句表述下问题文本无法明确表达自身立场的问题。实验结果表明, 本文方法取得了比现有模型方法更好的效果, 同时证明该方法能有效拟合问答立场分析任务中的问答对依赖关系。

DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning

no code implementations4 Jun 2024 Yixuan Liu, Li Xiong, YuHan Liu, Yujie Gu, Ruixuan Liu, Hong Chen

Third, the model is updated with the gradient reconstructed from recycled common knowledge and noisy incremental information.

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

no code implementations26 May 2024 Jiayi Yao, Hanchen Li, YuHan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang

To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when the context is reused as the prefix of another LLM input.

Language Modelling Large Language Model

Physics-Guided State-Space Model Augmentation Using Weighted Regularized Neural Networks

no code implementations16 May 2024 YuHan Liu, Roland Tóth, Maarten Schoukens

A new weighted regularization term is added to the cost function to penalize the difference between the state and output function of the baseline physics-based and final identified model.

TS3IM: Unveiling Structural Similarity in Time Series through Image Similarity Assessment Insights

no code implementations10 May 2024 YuHan Liu, Ke Tu

This paper introduces the Structured Similarity Index Measure for Time Series (TS3IM), a novel approach inspired by the success of the Structural Similarity Index Measure (SSIM) in image analysis, tailored to address these limitations by assessing structural similarity in time series.

Anomaly Detection Dynamic Time Warping +3

Event-based Video Frame Interpolation with Edge Guided Motion Refinement

no code implementations28 Apr 2024 YuHan Liu, Yongjian Deng, Hao Chen, Bochen Xie, Youfu Li, Zhen Yang

Moreover, given that event data can provide accurate visual references at scene edges between consecutive frames, we introduce a learned visibility map derived from event data to adaptively mitigate the occlusion problem in the warping refinement process.

Optical Flow Estimation Video Frame Interpolation

From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News

no code implementations14 Mar 2024 YuHan Liu, Xiuying Chen, Xiaoqing Zhang, Xing Gao, Ji Zhang, Rui Yan

Our simulation results uncover patterns in fake news propagation related to topic relevance, and individual traits, aligning with real-world observations.

Eloquent: A More Robust Transmission Scheme for LLM Token Streaming

no code implementations23 Jan 2024 Hanchen Li, YuHan Liu, Yihua Cheng, Siddhant Ray, Kuntai Du, Junchen Jiang

To render each generated token in real-time for users, the Large Language Model (LLM) server generates tokens one by one and streams each token (or group of a few tokens) through the network to the user right after generation, which we refer to as LLM token streaming.

Chatbot Language Modelling +1

P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models

no code implementations16 Nov 2023 YuHan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov

In this work, we take a first step towards designing summarization systems that are faithful to the author's intent, not only the semantic content of the article.

News Summarization

Attitude Takeover Control for Noncooperative Space Targets Based on Gaussian Processes with Online Model Learning

no code implementations24 Oct 2023 YuHan Liu, Pengyu Wang, Chang-Hun Lee, Roland Tóth

One major challenge for autonomous attitude takeover control for on-orbit servicing of spacecraft is that an accurate dynamic motion model of the combined vehicles is highly nonlinear, complex and often costly to identify online, which makes traditional model-based control impractical for this task.

Gaussian Processes

CacheGen: KV Cache Compression and Streaming for Fast Language Model Serving

1 code implementation11 Oct 2023 YuHan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, YuYang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang

Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 5-4. 3x and the total delay in fetching and processing contexts by 3. 2-3. 7x while having negligible impact on the LLM response quality in accuracy or perplexity.

Language Modelling Quantization

Automatic and Efficient Customization of Neural Networks for ML Applications

no code implementations7 Oct 2023 YuHan Liu, Chengcheng Wan, Kuntai Du, Henry Hoffmann, Junchen Jiang, Shan Lu, Michael Maire

ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API.

OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation

no code implementations3 Oct 2023 Kuntai Du, YuHan Liu, Yitian Hao, Qizheng Zhang, Haodong Wang, YuYang Huang, Ganesh Ananthanarayanan, Junchen Jiang

While the high demand for network bandwidth and GPU resources could be substantially reduced by optimally adapting the configuration knobs, such as video resolution and frame rate, current adaptation techniques fail to meet three requirements simultaneously: adapt configurations (i) with minimum extra GPU or bandwidth overhead; (ii) to reach near-optimal decisions based on how the data affects the final DNN's accuracy, and (iii) do so for a range of configuration knobs.

object-detection Object Detection

Knowledge Crosswords: Geometric Reasoning over Structured Knowledge with Large Language Models

1 code implementation2 Oct 2023 Wenxuan Ding, Shangbin Feng, YuHan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov

We additionally propose two new approaches, Staged Prompting and Verify-All, to augment LLMs' ability to backtrack and verify structured constraints.

GRACE: Loss-Resilient Real-Time Video through Neural Codecs

no code implementations21 May 2023 Yihua Cheng, Ziyi Zhang, Hanchen Li, Anton Arapin, Yue Zhang, Qizheng Zhang, YuHan Liu, Xu Zhang, Francis Y. Yan, Amrita Mazumdar, Nick Feamster, Junchen Jiang

In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements.


From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

1 code implementation15 May 2023 Shangbin Feng, Chan Young Park, YuHan Liu, Yulia Tsvetkov

We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks.

Fairness Misinformation

Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model

no code implementations11 Apr 2023 Yixuan Liu, Suyun Zhao, Li Xiong, YuHan Liu, Hong Chen

In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model.

Federated Learning

Agent-based Simulation for Online Mental Health Matching

no code implementations20 Mar 2023 YuHan Liu, Anna Fang, Glen Moriarty, Robert Kraut, Haiyi Zhu

Online mental health communities (OMHCs) are an effective and accessible channel to give and receive social support for individuals with mental and emotional issues.

Learning For Predictive Control: A Dual Gaussian Process Approach

no code implementations7 Nov 2022 YuHan Liu, Pengyu Wang, Roland Tóth

Gaussian process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data.

Model Predictive Control

Discrete Distribution Estimation under User-level Local Differential Privacy

no code implementations7 Nov 2022 Jayadev Acharya, YuHan Liu, Ziteng Sun

Perhaps surprisingly, we show that in suitable parameter regimes, having $m$ samples per user is equivalent to having $m$ times more users, each with only one sample.

Learning Continuous Control Policies for Information-Theoretic Active Perception

1 code implementation26 Sep 2022 Pengzhi Yang, YuHan Liu, Shumon Koga, Arash Asgharivaskasi, Nikolay Atanasov

This paper proposes a method for learning continuous control policies for active landmark localization and exploration using an information-theoretic cost.

Continuous Control

Algorithms for bounding contribution for histogram estimation under user-level privacy

no code implementations7 Jun 2022 YuHan Liu, Ananda Theertha Suresh, Wennan Zhu, Peter Kairouz, Marco Gruteser

In this scenario, the amount of noise injected into the histogram to obtain differential privacy is proportional to the maximum user contribution, which can be amplified by few outliers.

Human Behavior Recognition Method Based on CEEMD-ES Radar Selection

no code implementations6 Jun 2022 Zhaolin Zhang, Mingqi Song, Wugang Meng, YuHan Liu, Fengcong Li, Xiang Feng, Yinan Zhao

First, this method decomposes and reconstructs the radar signal according to the difference in the reflected echo frequency between the limbs and the trunk of the human body.

Empathetic Response Generation with State Management

1 code implementation7 May 2022 YuHan Liu, Jun Gao, Jiachen Du, Lanjun Zhou, Ruifeng Xu

The emotion-aware dialogue management contains two parts: (1) Emotion state tracking maintains the current emotion state of the user and (2) Empathetic dialogue policy selection predicts a target emotion and a user's intent based on the results of the emotion state tracking.

Dialogue Management Empathetic Response Generation +3

Learning Based Model Predictive Control for Quadcopters with Dual Gaussian Process

no code implementations22 Dec 2021 YuHan Liu, Roland Tóth

In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control strategy that improves the performance of a quadcopter during trajectory tracking.

Model Predictive Control

Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition

no code implementations NeurIPS 2021 Jayadev Acharya, Clement Canonne, YuHan Liu, Ziteng Sun, Himanshu Tyagi

We obtain tight minimax rates for the problem of distributed estimation of discrete distributions under communication constraints, where $n$ users observing $m $ samples each can broadcast only $\ell$ bits.

Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs

no code implementations15 Oct 2021 Ryan Jacobs, Mingren Shen, YuHan Liu, Wei Hao, Xiaoshan Li, Ruoyu He, Jacob RC Greaves, Donglin Wang, Zeming Xie, Zitong Huang, Chao Wang, Kevin G. Field, Dane Morgan

In this work, we perform semantic segmentation of multiple defect types in electron microscopy images of irradiated FeCrAl alloys using a deep learning Mask Regional Convolutional Neural Network (Mask R-CNN) model.

object-detection Object Detection +1

Multi defect detection and analysis of electron microscopy images with deep learning

no code implementations19 Aug 2021 Mingren Shen, Guanzhao Li, Dongxia Wu, YuHan Liu, Jacob Greaves, Wei Hao, Nathaniel J. Krakauer, Leah Krudy, Jacob Perez, Varun Sreenivasan, Bryan Sanchez, Oigimer Torres, Wei Li, Kevin Field, Dane Morgan

Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalable to large numbers of images or real-time analysis.

Defect Detection

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

no code implementations CVPR 2021 Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, YuHan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Hong-Xing Yu, Zexiang Xu, Kalyan Sunkavalli, Milos Hasan, Ravi Ramamoorthi, Manmohan Chandraker

Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.

Friction Inverse Rendering +1

Textual Analysis of Communications in COVID-19 Infected Community on Social Media

no code implementations3 May 2021 YuHan Liu, Yuhan Gao, Zhifan Nan, Long Chen

During the COVID-19 pandemic, people started to discuss about pandemic-related topics on social media.

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

1 code implementation2 Feb 2021 YuHan Liu, Saurabh Agarwal, Shivaram Venkataraman

With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data.

Accelerating Deep Learning Inference via Learned Caches

no code implementations18 Jan 2021 Arjun Balasubramanian, Adarsh Kumar, YuHan Liu, Han Cao, Shivaram Venkataraman, Aditya Akella

We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference.

Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints

no code implementations30 Oct 2020 Jayadev Acharya, Peter Kairouz, YuHan Liu, Ziteng Sun

We consider the problem of estimating sparse discrete distributions under local differential privacy (LDP) and communication constraints.

Learning discrete distributions: user vs item-level privacy

no code implementations NeurIPS 2020 Yuhan Liu, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar, Michael Riley

If each user has $m$ samples, we show that straightforward applications of Laplace or Gaussian mechanisms require the number of users to be $\mathcal{O}(k/(m\alpha^2) + k/\epsilon\alpha)$ to achieve an $\ell_1$ distance of $\alpha$ between the true and estimated distributions, with the privacy-induced penalty $k/\epsilon\alpha$ independent of the number of samples per user $m$.

Federated Learning

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

no code implementations25 Jul 2020 Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, YuHan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Zexiang Xu, Hong-Xing Yu, Kalyan Sunkavalli, Miloš Hašan, Ravi Ramamoorthi, Manmohan Chandraker

Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.

Friction Inverse Rendering +2

Tidal surface states as fingerprints of non-Hermitian nodal knot metals

no code implementations3 Dec 2018 Ching Hua Lee, Guangjie Li, YuHan Liu, Tommy Tai, Ronny Thomale, Xiao Zhang

Non-Hermitian nodal knot metals (NKMs) contains intricate complex-valued energy bands gives rise to knotted exceptional loops and new topological surface states.

Mesoscale and Nanoscale Physics Materials Science Other Condensed Matter Mathematical Physics Mathematical Physics Quantum Physics

Entanglement-guided architectures of machine learning by quantum tensor network

1 code implementation24 Mar 2018 Yuhan Liu, Xiao Zhang, Maciej Lewenstein, Shi-Ju Ran

In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS).

BIG-bench Machine Learning

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