Search Results for author: Yuchen Liu

Found 88 papers, 32 papers with code

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning

no code implementations14 Jun 2025 Mengyuan Sun, Yu Li, Yuchen Liu, Bo Du, Yunjie Ge

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks.

ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data

no code implementations19 May 2025 Yifeng Jiao, Yuchen Liu, Yu Zhang, Xin Guo, Yushuai Wu, Chen Jiang, Jiyang Li, Hongwei Zhang, Limei Han, Xin Gao, Yuan Qi, Yuan Cheng

The advent of single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) offers an innovative perspective for deciphering regulatory mechanisms by assembling a vast repository of single-cell chromatin accessibility data.

Rethinking Repetition Problems of LLMs in Code Generation

1 code implementation15 May 2025 Yihong Dong, Yuchen Liu, Xue Jiang, Zhi Jin, Ge Li

Specifically, RPG first leverages grammar rules to identify repetition problems during code generation, and then strategically decays the likelihood of critical tokens that contribute to repetitions, thereby mitigating them in code generation.

Code Generation HumanEval +1

ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

no code implementations11 Apr 2025 Yongsheng Yu, Haitian Zheng, Zhifei Zhang, Jianming Zhang, Yuqian Zhou, Connelly Barnes, Yuchen Liu, Wei Xiong, Zhe Lin, Jiebo Luo

Recent progress in generative models has significantly improved image restoration capabilities, particularly through powerful diffusion models that offer remarkable recovery of semantic details and local fidelity.

2k Image Restoration +1

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

no code implementations21 Mar 2025 Bhishma Dedhia, David Bourgin, Krishna Kumar Singh, Yuheng Li, Yan Kang, Zhan Xu, Niraj K. Jha, Yuchen Liu

At each diffusion step, VINs encode global semantics from the noisy input of local chunks and the encoded representations, in turn, guide DiTs in denoising chunks in parallel.

Denoising Optical Flow Estimation +1

Movable Cell-Free Massive MIMO For High-Speed Train Communications: A PPO-Based Antenna Position Optimization

no code implementations16 Mar 2025 Jie Dai, Yuchen Liu, Jiakang Zheng, Ruichen Zhang, Jiayi Zhang, Bo Ai

Simulation results demonstrate that movable CF massive MIMO effectively suppresses the negative impact of the Doppler effect in HST communications.

Deep Reinforcement Learning Position

Synergizing AI and Digital Twins for Next-Generation Network Optimization, Forecasting, and Security

no code implementations8 Mar 2025 Zifan Zhang, Minghong Fang, Dianwei Chen, Xianfeng Yang, Yuchen Liu

This article presents a comprehensive analysis of the synergy of DNTs, FL, and RL techniques, showcasing their collective potential to address critical challenges in 6G networks.

Federated Learning Reinforcement Learning (RL)

SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation Models

1 code implementation28 Feb 2025 Yichi Zhang, Bohao Lv, Le Xue, Wenbo Zhang, Yuchen Liu, Yu Fu, Yuan Cheng, Yuan Qi

SemiSAM+ consists of one or multiple promptable foundation models as generalist models, and a trainable task-specific segmentation model as specialist model.

Image Segmentation Segmentation +2

SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images

1 code implementation20 Feb 2025 Yichi Zhang, Le Xue, Wenbo Zhang, Lanlan Li, Yuchen Liu, Chen Jiang, Yuan Cheng, Yuan Qi

Positron Emission Tomography (PET) imaging plays a crucial role in modern medical diagnostics by revealing the metabolic processes within a patient's body, which is essential for quantification of therapy response and monitoring treatment progress.

Image Segmentation Segmentation +1

Optimizing Wireless Resource Management and Synchronization in Digital Twin Networks

no code implementations7 Feb 2025 Hanzhi Yu, Yuchen Liu, Zhaohui Yang, Haijian Sun, Mingzhe Chen

Since the DNT can predict the physical network status based on its historical status, the BSs may not need to send their physical network information at each time slot, allowing them to conserve spectrum resources to serve the users.

Management Q-Learning

Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning

no code implementations7 Feb 2025 Yuchen Liu, Chen Chen, Lingjuan Lyu, Yaochu Jin, Gang Chen

This gradient skew phenomenon allows Byzantine gradients to hide within the densely distributed skewed gradients.

Federated Learning Inductive Bias

BRIDLE: Generalized Self-supervised Learning with Quantization

1 code implementation4 Feb 2025 Hoang M. Nguyen, Satya N. Shukla, Qiang Zhang, Hanchao Yu, Sreya D. Roy, Taipeng Tian, Lingjiong Zhu, Yuchen Liu

To address these limitations, we introduce BRIDLE (Bidirectional Residual Quantization Interleaved Discrete Learning Encoder), a self-supervised encoder pretraining framework that incorporates residual quantization (RQ) into the bidirectional training process, and is generalized for pretraining with audio, image, and video.

image-classification Image Classification +3

INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation

no code implementations1 Feb 2025 Dianwei Chen, Zifan Zhang, Yuchen Liu, Xianfeng Terry Yang

Autonomous driving systems face significant challenges in handling unpredictable edge-case scenarios, such as adversarial pedestrian movements, dangerous vehicle maneuvers, and sudden environmental changes.

Autonomous Driving Decision Making +2

Poisoning Attacks and Defenses to Federated Unlearning

no code implementations29 Jan 2025 Wenbin Wang, Qiwen Ma, Zifan Zhang, Yuchen Liu, Zhuqing Liu, Minghong Fang

In BadUnlearn, malicious clients send specifically designed local model updates to the server during the unlearning process, aiming to ensure that the resulting unlearned model remains poisoned.

Federated Learning

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

no code implementations20 Dec 2024 Zihan Ding, Chi Jin, Difan Liu, Haitian Zheng, Krishna Kumar Singh, Qiang Zhang, Yan Kang, Zhe Lin, Yuchen Liu

In this work, we introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation, maintaining both high quality and diversity.

Computational Efficiency Diversity +1

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement

1 code implementation1 Nov 2024 Yingwei Ma, Rongyu Cao, Yongchang Cao, Yue Zhang, Jue Chen, Yibo Liu, Yuchen Liu, Binhua Li, Fei Huang, Yongbin Li

The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30. 20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22. 76% relative improvement compared to Llama 3. 1 405B), approaching the performance of closed-source models (31. 80\% issues of GPT-4o resolved).

Language Modeling Language Modelling

FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning

1 code implementation19 Oct 2024 Sizhe Liu, Jun Xia, Lecheng Zhang, Yuchen Liu, Yue Liu, Wenjie Du, Zhangyang Gao, Bozhen Hu, Cheng Tan, Hongxin Xiang, Stan Z. Li

Molecular relational learning (MRL) is crucial for understanding the interaction behaviors between molecular pairs, a critical aspect of drug discovery and development.

Benchmarking Drug Discovery +1

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

no code implementations23 Sep 2024 Alireza Ganjdanesh, Yan Kang, Yuchen Liu, Richard Zhang, Zhe Lin, Heng Huang

Finally, with a selected configuration, we fine-tune our pruned experts to obtain our mixture of efficient experts.

Denoising

Joint Vehicle Connection and Beamforming Optimization in Digital Twin Assisted Integrated Sensing and Communication Vehicular Networks

no code implementations1 Aug 2024 Weihang Ding, Zhaohui Yang, Mingzhe Chen, Yuchen Liu, Mohammad Shikh-Bahaei

To solve the simplified problem, this paper introduces both greedy and heuristic algorithms through optimizing both vehicle assignments and predictive beamforming.

Integrated sensing and communication ISAC

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

1 code implementation31 Jul 2024 Yuxin Wen, Yuchen Liu, Chen Chen, Lingjuan Lyu

In this work, we introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions.

Image Generation Memorization

Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks

no code implementations29 Jun 2024 Zifan Zhang, Yuchen Liu, Zhiyuan Peng, Mingzhe Chen, Dongkuan Xu, Shuguang Cui

To bridge this gap, we introduce a novel digital twin-assisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks.

Reinforcement Learning (RL)

Byzantine-Robust Decentralized Federated Learning

no code implementations14 Jun 2024 Minghong Fang, Zifan Zhang, Hairi, Prashant Khanduri, Jia Liu, Songtao Lu, Yuchen Liu, Neil Gong

However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients.

Federated Learning

Self-Modifying State Modeling for Simultaneous Machine Translation

1 code implementation4 Jun 2024 Donglei Yu, Xiaomian Kang, Yuchen Liu, Yu Zhou, Chengqing Zong

Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models.

Machine Translation Translation

Personalized Residuals for Concept-Driven Text-to-Image Generation

no code implementations CVPR 2024 Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu, Richard Zhang, Tobias Hinz

We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models.

Text to Image Generation Text-to-Image Generation

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

no code implementations CVPR 2024 Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj K. Jha, Yuchen Liu

Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation.

Denoising

Poisoning Attacks on Federated Learning-based Wireless Traffic Prediction

no code implementations22 Apr 2024 Zifan Zhang, Minghong Fang, Jiayuan Huang, Yuchen Liu

Federated Learning (FL) offers a distributed framework to train a global control model across multiple base stations without compromising the privacy of their local network data.

Autonomous Vehicles Federated Learning +3

Mapping Wireless Networks into Digital Reality through Joint Vertical and Horizontal Learning

no code implementations22 Apr 2024 Zifan Zhang, Mingzhe Chen, Zhaohui Yang, Yuchen Liu

In recent years, the complexity of 5G and beyond wireless networks has escalated, prompting a need for innovative frameworks to facilitate flexible management and efficient deployment.

Decision Making

F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation

1 code implementation7 Apr 2024 Junhong Wu, Yuchen Liu, Chengqing Zong

In the evolving landscape of Neural Machine Translation (NMT), the pretrain-then-finetune paradigm has yielded impressive results.

Continual Learning Machine Translation +2

DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models

no code implementations4 Apr 2024 Yuchen Liu, Luigi Palmieri, Sebastian Koch, Ilche Georgievski, Marco Aiello

In our extensive evaluation, we show that DELTA enables an efficient and fully automatic task planning pipeline, achieving higher planning success rates and significantly shorter planning times compared to the state of the art.

Common Sense Reasoning Computational Efficiency +3

Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices

no code implementations27 Mar 2024 Hanqing Fu, Gaolei Li, Jun Wu, Jianhua Li, Xi Lin, Kai Zhou, Yuchen Liu

Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks.

Federated Learning

ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph

no code implementations29 Feb 2024 Xukun Liu, Zhiyuan Peng, Xiaoyuan Yi, Xing Xie, Lirong Xiang, Yuchen Liu, Dongkuan Xu

While achieving remarkable progress in a broad range of tasks, large language models (LLMs) remain significantly limited in properly using massive external tools.

In-Context Learning

Collaborative Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Trajectory Design for 3D UAV Tracking

no code implementations22 Jan 2024 Yujiao Zhu, Mingzhe Chen, Sihua Wang, Ye Hu, Yuchen Liu, Changchuan Yin

Meanwhile, since the accuracy of the distance estimation depends on the signal-to-noise ratio of the transmission signals, the active UAV must optimize its transmit power.

Self-supervised Learning for Electroencephalogram: A Systematic Survey

no code implementations9 Jan 2024 Weining Weng, Yang Gu, Shuai Guo, Yuan Ma, Zhaohua Yang, Yuchen Liu, Yiqiang Chen

2) We provide a comprehensive review of SSL for EEG analysis, including taxonomy, methodology, and technique details of the existing EEG-based SSL frameworks, and discuss the difference between these methods.

EEG Self-Supervised Learning +1

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

no code implementations CVPR 2024 Zhengang Li, Yan Kang, Yuchen Liu, Difan Liu, Tobias Hinz, Feng Liu, Yanzhi Wang

Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method.

Video Generation

SemiSAM: Enhancing Semi-Supervised Medical Image Segmentation via SAM-Assisted Consistency Regularization

1 code implementation11 Dec 2023 Yichi Zhang, Jin Yang, Yuchen Liu, Yuan Cheng, Yuan Qi

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which typically requires intensive pixel/voxel-wise labeling by domain experts.

Image Segmentation Segmentation +2

A Joint Gradient and Loss Based Clustered Federated Learning Design

no code implementations22 Nov 2023 Licheng Lin, Mingzhe Chen, Zhaohui Yang, Yusen Wu, Yuchen Liu

In particular, our designed clustered FL algorithm must overcome two challenges associated with FL training.

Clustering Federated Learning

BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

1 code implementation2 Sep 2023 Chen Wang, Minpeng Liao, Zhongqiang Huang, Jinliang Lu, Junhong Wu, Yuchen Liu, Chengqing Zong, Jiajun Zhang

One is a cascaded approach where outputs (tokens or states) of a separately trained speech recognition system are used as inputs for LLMs, which limits their potential in modeling alignment between speech and text.

speech-recognition Speech Recognition +1

Gentopia: A Collaborative Platform for Tool-Augmented LLMs

1 code implementation8 Aug 2023 Binfeng Xu, Xukun Liu, Hua Shen, Zeyu Han, Yuhan Li, Murong Yue, Zhiyuan Peng, Yuchen Liu, Ziyu Yao, Dongkuan Xu

We present gentopia, an ALM framework enabling flexible customization of agents through simple configurations, seamlessly integrating various language models, task formats, prompting modules, and plugins into a unified paradigm.

NBMOD: Find It and Grasp It in Noisy Background

1 code implementation17 Jun 2023 Boyuan Cao, Xinyu Zhou, Congmin Guo, Baohua Zhang, Yuchen Liu, Qianqiu Tan

In the past few years, researchers have proposed many methods to address the above-mentioned issues and achieved very good results on publicly available datasets such as the Cornell dataset and the Jacquard dataset.

 Ranked #1 on Robotic Grasping on NBMOD (using extra training data)

Robotic Grasping

Few-shot Multi-domain Knowledge Rearming for Context-aware Defence against Advanced Persistent Threats

no code implementations13 Jun 2023 Gaolei Li, YuanYuan Zhao, Wenqi Wei, Yuchen Liu

Secondly, to rearm current security strategies, an finetuning-based deployment mechanism is proposed to transfer learned knowledge into the student model, while minimizing the defense cost.

Meta-Learning Scheduling

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

2 code implementations23 May 2023 Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata Mukherjee, Yuchen Liu, Dongkuan Xu

Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution.

Retrieval

MMViT: Multiscale Multiview Vision Transformers

no code implementations28 Apr 2023 Yuchen Liu, Natasha Ong, Kaiyan Peng, Bo Xiong, Qifan Wang, Rui Hou, Madian Khabsa, Kaiyue Yang, David Liu, Donald S. Williamson, Hanchao Yu

Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel.

image-classification Image Classification

Ethylene Leak Detection Based on Infrared Imaging: A Benchmark

no code implementations4 Apr 2023 Xuanchao Ma, Yuchen Liu

We find that the detection criteria used in infrared imaging ethylene leakage detection research cannot fully reflect real-world production conditions, which is not conducive to evaluate the performance of current image-based target detection methods.

Multi-modal Expression Recognition with Ensemble Method

no code implementations17 Mar 2023 Chuanhe Liu, Xinjie Zhang, Xiaolong Liu, Tenggan Zhang, Liyu Meng, Yuchen Liu, Yuanyuan Deng, Wenqiang Jiang

This paper presents our submission to the Expression Classification Challenge of the fifth Affective Behavior Analysis in-the-wild (ABAW) Competition.

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

1 code implementation13 Feb 2023 Yuchen Liu, Chen Chen, Lingjuan Lyu, Fangzhao Wu, Sai Wu, Gang Chen

In order to address this issue, we propose GAS, a \shorten approach that can successfully adapt existing robust AGRs to non-IID settings.

Federated Learning

A Composite T60 Regression and Classification Approach for Speech Dereverberation

no code implementations9 Feb 2023 Yuying Li, Yuchen Liu, Donald S. Williamson

More specifically, we develop a joint learning approach that uses a composite T60 module and a separate dereverberation module to simultaneously perform reverberation time estimation and dereverberation.

regression Speech Dereverberation

Towards Unsupervised Domain Generalization for Face Anti-Spoofing

no code implementations ICCV 2023 Yuchen Liu, Yabo Chen, Mengran Gou, Chun-Ting Huang, Yaoming Wang, Wenrui Dai, Hongkai Xiong

In this paper, we propose the first Unsupervised Domain Generalization framework for Face Anti-Spoofing, namely UDG-FAS, which could exploit large amounts of easily accessible unlabeled data to learn generalizable features for enhancing the low-data regime of FAS.

Domain Generalization Face Anti-Spoofing

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

1 code implementation CVPR 2023 Yaoming Wang, Bowen Shi, Xiaopeng Zhang, Jin Li, Yuchen Liu, Wenrui Dai, Chenglin Li, Hongkai Xiong, Qi Tian

To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation.

parameter-efficient fine-tuning

CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment

no code implementations4 Nov 2022 Yuchen Liu, Li-Chia Yang, Alex Pawlicki, Marko Stamenovic

Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing.

CodePAD: Sequence-based Code Generation with Pushdown Automaton

1 code implementation2 Nov 2022 Yihong Dong, Xue Jiang, Yuchen Liu, Ge Li, Zhi Jin

CodePAD can leverage existing sequence-based models, and we show that it can achieve 100\% grammatical correctness percentage on these benchmark datasets.

Code Generation mbpp +1

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation

1 code implementation18 Oct 2022 Chen Wang, Yuchen Liu, Boxing Chen, Jiajun Zhang, Wei Luo, Zhongqiang Huang, Chengqing Zong

Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

3D-FM GAN: Towards 3D-Controllable Face Manipulation

no code implementations24 Aug 2022 Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Richard Zhang, S. Y. Kung

While concatenating GAN inversion and a 3D-aware, noise-to-image GAN is a straight-forward solution, it is inefficient and may lead to noticeable drop in editing quality.

Court Judgement Labeling Using Topic Modeling and Syntactic Parsing

1 code implementation3 Aug 2022 Yuchen Liu

In regions that practice common law, relevant historical cases are essential references for sentencing.

Constituency Parsing Dependency Parsing +2

SdAE: Self-distillated Masked Autoencoder

1 code implementation31 Jul 2022 Yabo Chen, Yuchen Liu, Dongsheng Jiang, Xiaopeng Zhang, Wenrui Dai, Hongkai Xiong, Qi Tian

We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.

Descriptive Self-Supervised Learning

Multi-Task Learning Framework for Emotion Recognition in-the-wild

1 code implementation19 Jul 2022 Tenggan Zhang, Chuanhe Liu, Xiaolong Liu, Yuchen Liu, Liyu Meng, Lei Sun, Wenqiang Jiang, Fengyuan Zhang, Jinming Zhao, Qin Jin

This paper presents our system for the Multi-Task Learning (MTL) Challenge in the 4th Affective Behavior Analysis in-the-wild (ABAW) competition.

Emotion Recognition Multi-Task Learning +1

Scalable Model-based Policy Optimization for Decentralized Networked Systems

no code implementations13 Jul 2022 Yali Du, Chengdong Ma, Yuchen Liu, Runji Lin, Hao Dong, Jun Wang, Yaodong Yang

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks.

Traffic Signal Control

CalFAT: Calibrated Federated Adversarial Training with Label Skewness

1 code implementation30 May 2022 Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu

In this paper, we study the problem of FAT under label skewness, and reveal one root cause of the training instability and natural accuracy degradation issues: skewed labels lead to non-identical class probabilities and heterogeneous local models.

Adversarial Robustness Federated Learning

M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database

1 code implementation ACL 2022 Jinming Zhao, Tenggan Zhang, Jingwen Hu, Yuchen Liu, Qin Jin, Xinchao Wang, Haizhou Li

In this work, we propose a Multi-modal Multi-scene Multi-label Emotional Dialogue dataset, M3ED, which contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9, 082 turns and 24, 449 utterances.

Cultural Vocal Bursts Intensity Prediction Diversity +1

Subspace Nonnegative Matrix Factorization for Feature Representation

1 code implementation18 Apr 2022 Junhang Li, Jiao Wei, Can Tong, Tingting Shen, Yuchen Liu, Chen Li, Shouliang Qi, YuDong Yao, Yueyang Teng

Traditional nonnegative matrix factorization (NMF) learns a new feature representation on the whole data space, which means treating all features equally.

Multi-modal Emotion Estimation for in-the-wild Videos

no code implementations24 Mar 2022 Liyu Meng, Yuchen Liu, Xiaolong Liu, Zhaopei Huang, Yuan Cheng, Meng Wang, Chuanhe Liu, Qin Jin

In this paper, we briefly introduce our submission to the Valence-Arousal Estimation Challenge of the 3rd Affective Behavior Analysis in-the-wild (ABAW) competition.

Arousal Estimation

Evolving Transferable Neural Pruning Functions

no code implementations21 Oct 2021 Yuchen Liu, S. Y. Kung, David Wentzlaff

While most prior works in evolutionary learning aim at directly searching the structure of a network, few attempts have been made on another promising track, channel pruning, which recently has made major headway in designing efficient deep learning models.

Class-Discriminative CNN Compression

no code implementations21 Oct 2021 Yuchen Liu, David Wentzlaff, S. Y. Kung

We then propose a novel layer-adaptive hierarchical pruning approach, where we use a coarse class discrimination scheme for early layers and a fine one for later layers.

MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation

1 code implementation ACL 2021 Jingwen Hu, Yuchen Liu, Jinming Zhao, Qin Jin

Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users' emotions and generate empathetic responses.

Emotion Recognition in Conversation

Content-Aware GAN Compression

1 code implementation CVPR 2021 Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Federico Perazzi, S. Y. Kung

We then propose a novel content-aware method to guide the processes of both pruning and distillation.

Image Manipulation Knowledge Distillation

Finite generation for valuations computing stability thresholds and applications to K-stability

no code implementations18 Feb 2021 Yuchen Liu, Chenyang Xu, Ziquan Zhuang

We prove that on any log Fano pair of dimension $n$ whose stability threshold is less than $\frac{n+1}{n}$, any valuation computing the stability threshold has a finitely generated associated graded ring.

Algebraic Geometry Differential Geometry

Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization

no code implementations ICCV 2021 Yaoming Wang, Yuchen Liu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

Existing differentiable neural architecture search approaches simply assume the architectural distribution on each edge is independent of each other, which conflicts with the intrinsic properties of architecture.

Neural Architecture Search

Emotions in Online Content Diffusion

no code implementations17 Nov 2020 Yifan Yu, Shan Huang, Yuchen Liu, Yong Tan

We apply a partial-linear instrumental variable approach with a double machine learning framework to causally identify the impact of the negative discrete emotions on online content diffusion.

Articles Marketing

Bridging the Modality Gap for Speech-to-Text Translation

no code implementations28 Oct 2020 Yuchen Liu, Junnan Zhu, Jiajun Zhang, Chengqing Zong

End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way.

Decoder Speech-to-Text +2

Rethinking Class-Discrimination Based CNN Channel Pruning

no code implementations29 Apr 2020 Yuchen Liu, David Wentzlaff, S. Y. Kung

To this end, we initiate the first study on the effectiveness of a broad range of discriminant functions on channel pruning.

Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding

1 code implementation16 Dec 2019 Yuchen Liu, Jiajun Zhang, Hao Xiong, Long Zhou, Zhongjun He, Hua Wu, Haifeng Wang, Cheng-qing Zong

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Synchronously Generating Two Languages with Interactive Decoding

no code implementations IJCNLP 2019 Yining Wang, Jiajun Zhang, Long Zhou, Yuchen Liu, Cheng-qing Zong

In this paper, we introduce a novel interactive approach to translate a source language into two different languages simultaneously and interactively.

Machine Translation NMT +2

End-to-End Speech Translation with Knowledge Distillation

no code implementations17 Apr 2019 Yuchen Liu, Hao Xiong, Zhongjun He, Jiajun Zhang, Hua Wu, Haifeng Wang, Cheng-qing Zong

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years.

Knowledge Distillation speech-recognition +2

Language-Independent Representor for Neural Machine Translation

no code implementations1 Nov 2018 Long Zhou, Yuchen Liu, Jiajun Zhang, Cheng-qing Zong, Guoping Huang

Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation.

Decoder Machine Translation +4

Unsupervised Learning of Neural Networks to Explain Neural Networks

no code implementations18 May 2018 Quanshi Zhang, Yu Yang, Yuchen Liu, Ying Nian Wu, Song-Chun Zhu

Given feature maps of a certain conv-layer of the CNN, the explainer performs like an auto-encoder, which first disentangles the feature maps into object-part features and then inverts object-part features back to features of higher conv-layers of the CNN.

Disentanglement Object

Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest

no code implementations12 Nov 2015 Dmitry Kislyuk, Yuchen Liu, David Liu, Eric Tzeng, Yushi Jing

This paper presents Pinterest Related Pins, an item-to-item recommendation system that combines collaborative filtering with content-based ranking.

Collaborative Filtering

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