Search Results for author: Wei Yang

Found 210 papers, 79 papers with code

TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints

no code implementations10 Feb 2025 Pengyu Long, Zijun Zhao, Min Ouyang, Qingcheng Zhao, Qixuan Zhang, Wei Yang, Lan Xu, Jingyi Yu

We present TANGLED, a novel approach for 3D hair strand generation that accommodates diverse image inputs across styles, viewpoints, and quantities of input views.

NUDT4MSTAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild

1 code implementation23 Jan 2025 Yongxiang Liu, Weijie Li, Li Liu, Jie zhou, Xuying Xiong, Bowen Peng, Yafei Song, Wei Yang, Tianpeng Liu, Zhen Liu, Xiang Li

This paper introduces NUDT4MSTAR, a large-scale SAR dataset for remote sensing target recognition in the wild, including 40 vehicle target types and various imaging conditions across 5 realistic scenes.

Earth Observation Object Recognition +1

Boundary-enhanced time series data imputation with long-term dependency diffusion models

no code implementations11 Jan 2025 Chunjing Xiao, Xue Jiang, Xianghe Du, Wei Yang, Wei Lu, Xiaomin Wang, Kevin Chetty

Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention.

Imputation Missing Values +1

LLM4SR: A Survey on Large Language Models for Scientific Research

1 code implementation8 Jan 2025 Ziming Luo, Zonglin Yang, Zexin Xu, Wei Yang, Xinya Du

In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle.

Survey

A Large-dimensional Analysis of ESPRIT DoA Estimation: Inconsistency and a Correction via RMT

1 code implementation6 Jan 2025 Zhengyu Wang, Wei Yang, Xiaoyi Mai, Zenan Ling, Zhenyu Liao, Robert C. Qiu

In this paper, we perform asymptotic analyses of the widely used ESPRIT direction-of-arrival (DoA) estimator for large arrays, where the array size $N$ and the number of snapshots $T$ grow to infinity at the same pace.

Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model

1 code implementation12 Dec 2024 Hang Zhou, Jiale Cai, Yuteng Ye, Yonghui Feng, Chenxing Gao, Junqing Yu, Zikai Song, Wei Yang

To address this, we introduce innovative motion and appearance conditions that are seamlessly integrated into our patch diffusion model.

Anomaly Detection Video Anomaly Detection

ProGDF: Progressive Gaussian Differential Field for Controllable and Flexible 3D Editing

no code implementations11 Dec 2024 Yian Zhao, Wanshi Xu, Yang Wu, Weiheng Huang, Zhongqian Sun, Wei Yang

To address this issue, we introduce the concept of process-oriented modelling for 3D editing and propose the Progressive Gaussian Differential Field (ProGDF), an out-of-loop training approach that requires only a single training session to provide users with controllable editing capability and variable editing results through a user-friendly interface in real-time.

3DGS

Ref-GS: Directional Factorization for 2D Gaussian Splatting

no code implementations1 Dec 2024 Youjia Zhang, Anpei Chen, Yumin Wan, Zikai Song, Junqing Yu, Yawei Luo, Wei Yang

In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery.

Playable Game Generation

1 code implementation1 Dec 2024 Mingyu Yang, Junyou Li, Zhongbin Fang, Sheng Chen, Yangbin Yu, Qiang Fu, Wei Yang, Deheng Ye

In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from text-to-image generation to text-to-video and multimodal video synthesis.

Text-to-Image Generation

StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

no code implementations8 Nov 2024 Yuze He, Yanning Zhou, Wang Zhao, Zhongkai Wu, Kaiwen Xiao, Wei Yang, Yong-Jin Liu, Xiao Han

We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc.

IP-MOT: Instance Prompt Learning for Cross-Domain Multi-Object Tracking

no code implementations30 Oct 2024 Run Luo, Zikai Song, Longze Chen, Yunshui Li, Min Yang, Wei Yang

Multi-Object Tracking (MOT) aims to associate multiple objects across video frames and is a challenging vision task due to inherent complexities in the tracking environment.

Knowledge Distillation Language Modelling +2

Beyond Forecasting: Compositional Time Series Reasoning for End-to-End Task Execution

no code implementations5 Oct 2024 Wen Ye, Yizhou Zhang, Wei Yang, Lumingyuan Tang, Defu Cao, Jie Cai, Yan Liu

In this paper, we introduce Compositional Time Series Reasoning, a new task of handling intricate multistep reasoning tasks from time series data.

Anomaly Detection Decision Making +4

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

1 code implementation NeurIPS 2023 Yun Qu, Boyuan Wang, Jianzhun Shao, Yuhang Jiang, Chen Chen, Zhenbin Ye, Lin Liu, Junfeng Yang, Lin Lai, Hongyang Qin, Minwen Deng, Juchao Zhuo, Deheng Ye, Qiang Fu, Wei Yang, Guang Yang, Lanxiao Huang, Xiangyang Ji

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications.

Multi-agent Reinforcement Learning Multi-Task Learning +4

Autogenic Language Embedding for Coherent Point Tracking

1 code implementation30 Jul 2024 Zikai Song, Ying Tang, Run Luo, Lintao Ma, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang

Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences.

Decoder Point Tracking

Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software

no code implementations11 Jul 2024 Dezhi Ran, Mengzhou Wu, Wei Yang, Tao Xie

By treating data and models as the source code, Foundation Models (FMs) become a new type of software.

Management

Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models

1 code implementation2 Jul 2024 Fei Shen, Hu Ye, Sibo Liu, Jun Zhang, Cong Wang, Xiao Han, Wei Yang

Moreover, RCDMs can generate consistent stories with a single forward inference compared to autoregressive models.

Story Visualization

WindowMixer: Intra-Window and Inter-Window Modeling for Time Series Forecasting

no code implementations14 Jun 2024 Quangao Liu, RuiQi Li, Maowei Jiang, Wei Yang, Chen Liang, Longlong Pang, Zhuozhang Zou

Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance.

Missing Values Time Series +1

Tokenize features, enhancing tables: the FT-TABPFN model for tabular classification

no code implementations11 Jun 2024 Quangao Liu, Wei Yang, Chen Liang, Longlong Pang, Zhuozhang Zou

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters.

Classification tabular-classification

V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation

no code implementations4 Jun 2024 Cong Wang, Kuan Tian, Jun Zhang, Yonghang Guan, Feng Luo, Fei Shen, Zhiwei Jiang, Qing Gu, Xiao Han, Wei Yang

In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as facial pose and reference image.

Video Generation

MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting

no code implementations3 Jun 2024 Shaojie Ma, Yawei Luo, Wei Yang, Yi Yang

To achieve this, we introduce RMD-Net, a network that learns motion priors from video data to refine mesh deformations, alongside RGD-Net, which models the relative displacement between the mesh and Gaussians to enhance rendering fidelity under mesh constraints.

3D Reconstruction NeRF

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

no code implementations30 May 2024 Longwen Zhang, Ziyu Wang, Qixuan Zhang, QIwei Qiu, Anqi Pang, Haoran Jiang, Wei Yang, Lan Xu, Jingyi Yu

To narrow this disparity, we introduce CLAY, a 3D geometry and material generator designed to effortlessly transform human imagination into intricate 3D digital structures.

2k 3D geometry

Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model

no code implementations28 May 2024 Wenbing Li, Hang Zhou, Junqing Yu, Zikai Song, Wei Yang

However, fusing multiple modalities is challenging for SSMs due to its hardware-aware parallelism designs.

Mamba State Space Models

Ensembling Diffusion Models via Adaptive Feature Aggregation

1 code implementation27 May 2024 Cong Wang, Kuan Tian, Yonghang Guan, Jun Zhang, Zhiwei Jiang, Fei Shen, Xiao Han, Qing Gu, Wei Yang

In this paper, we propose a novel ensembling method, Adaptive Feature Aggregation (AFA), which dynamically adjusts the contributions of multiple models at the feature level according to various states (i. e., prompts, initial noises, denoising steps, and spatial locations), thereby keeping the advantages of multiple diffusion models, while suppressing their disadvantages.

Denoising

TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing

no code implementations23 May 2024 Teng Xu, Jiamin Chen, Peng Chen, Youjia Zhang, Junqing Yu, Wei Yang

Editing objects within a scene is a critical functionality required across a broad spectrum of applications in computer vision and graphics.

3DGS Retrieval

SARATR-X: Toward Building A Foundation Model for SAR Target Recognition

3 code implementations15 May 2024 Weijie Li, Wei Yang, Yuenan Hou, Li Liu, Yongxiang Liu, Xiang Li

Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on detecting and classifying a specific category, e. g., vehicles, ships, airplanes, or buildings.

Earth Observation Self-Supervised Learning

Sifting out communities in large sparse networks

no code implementations1 May 2024 Sharlee Climer, Kenneth Smith Jr, Wei Yang, Lisa de las Fuentes, Victor G. Dávila-Román, C. Charles Gu

Research data sets are growing to unprecedented sizes and network modeling is commonly used to extract complex relationships in diverse domains, such as genetic interactions involved in disease, logistics, and social communities.

EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation

no code implementations19 Apr 2024 Wenkai Liu, Tao Guan, Bin Zhu, Lili Ju, Zikai Song, Dan Li, Yuesong Wang, Wei Yang

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology.

3DGS 4k

Attacking Transformers with Feature Diversity Adversarial Perturbation

no code implementations10 Mar 2024 Chenxing Gao, Hang Zhou, Junqing Yu, Yuteng Ye, Jiale Cai, Junle Wang, Wei Yang

Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications.

Diversity

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models

no code implementations28 Jan 2024 Simin Chen, Xiaoning Feng, Xiaohong Han, Cong Liu, Wei Yang

In recent times, a plethora of Large Code Generation Models (LCGMs) have been proposed, showcasing significant potential in assisting developers with complex programming tasks.

Benchmarking Code Generation

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

no code implementations28 Jan 2024 Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Dehua Zheng, Weixuan Wang, Wenjin Yang, Siqin Li, Xianliang Wang, Wenhui Chen, Jing Dai, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e. g., winning games).

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

1 code implementation22 Jan 2024 Chun Liu, Longwei Yang, Dongmei Dong, Zheng Li, Wei Yang, Zhigang Han, Jiayao Wang

However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify.

Classification Hyperspectral Image Classification

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study

1 code implementation12 Jan 2024 Yufei Li, Simin Chen, Yanghong Guo, Wei Yang, Yue Dong, Cong Liu

We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision.

AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion

no code implementations20 Dec 2023 Beibei Jing, Youjia Zhang, Zikai Song, Junqing Yu, Wei Yang

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion. Recent advances in diffusion models have enabled significant progress in human motion synthesis. However, existing methods struggle to handle text inputs that describe complex or long motions. In this paper, we propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion. This process exploits the LLM's ability to provide anatomical guidance for complex motion synthesis. We then devise a two-branch fusion scheme that balances the influence of the input text and the anatomical scripts on the inverse diffusion process, which adaptively ensures the semantic fidelity and diversity of the synthesized motion. Our method can effectively handle texts with complex or long motion descriptions, where existing methods often fail.

Diversity Language Modeling +2

Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model

no code implementations18 Dec 2023 Zhenyu Xie, Yang Wu, Xuehao Gao, Zhongqian Sun, Wei Yang, Xiaodan Liang

Besides, we introduce a multi-denoiser framework for the advanced diffusion model to ease the learning of high-dimensional model and fully explore the generative potential of the diffusion model.

Denoising Motion Synthesis

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

1 code implementation CVPR 2024 Bowen Wen, Wei Yang, Jan Kautz, Stan Birchfield

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups.

3D Object Detection 3D Object Tracking +8

Optimized View and Geometry Distillation from Multi-view Diffuser

no code implementations11 Dec 2023 Youjia Zhang, Zikai Song, Junqing Yu, Yawei Luo, Wei Yang

We leverage the rendered views from the optimized radiance field as the basis and develop a two-step specialization process of a 2D diffusion model, which is adept at conducting object-specific denoising and generating high-quality multi-view images.

Denoising

Fine-grained Appearance Transfer with Diffusion Models

1 code implementation27 Nov 2023 Yuteng Ye, Guanwen Li, Hang Zhou, Cai Jiale, Junqing Yu, Yawei Luo, Zikai Song, Qilong Xing, Youjia Zhang, Wei Yang

A pivotal aspect of our approach is the strategic use of the predicted $x_0$ space by diffusion models within the latent space of diffusion processes.

Image-to-Image Translation

Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields

1 code implementation CVPR 2024 Zhiyuan Min, Yawei Luo, Wei Yang, Yuesong Wang, Yi Yang

Different from existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process.

Generalizable Novel View Synthesis NeRF

Iterative missing value imputation based on feature importance

no code implementations14 Nov 2023 Cong Guo, Chun Liu, Wei Yang

Existing imputation methods estimate the missing parts based on the observed values in the original feature space, and they treat all features as equally important during data completion, while in fact different features have different importance.

Feature Importance Imputation +2

SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers

no code implementations9 Nov 2023 Sammy Christen, Lan Feng, Wei Yang, Yu-Wei Chao, Otmar Hilliges, Jie Song

In this paper, we introduce a framework that can generate plausible human grasping motions suitable for training the robot.

Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

1 code implementation2 Nov 2023 Chun Liu, Longwei Yang, Zheng Li, Wei Yang, Zhigang Han, JianZhong Guo, Junyong Yu

In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attention from query samples to support samples.

Classification Contrastive Learning +3

Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach

1 code implementation18 Oct 2023 Feng Luo, Jinxi Xiang, Jun Zhang, Xiao Han, Wei Yang

To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based methods utilize a feature encoder to transform the image and then implement the SR image generation in a compact latent space.

Blind Super-Resolution Decoder +2

Effortless Cross-Platform Video Codec: A Codebook-Based Method

no code implementations16 Oct 2023 Kuan Tian, Yonghang Guan, Jinxi Xiang, Jun Zhang, Xiao Han, Wei Yang

Due to the absence of autoregressive modeling and optical flow alignment, we can design an extremely minimalist framework that can greatly benefit computational efficiency.

Computational Efficiency Optical Flow Estimation +1

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

1 code implementation10 Oct 2023 Fei Shen, Hu Ye, Jun Zhang, Cong Wang, Xiao Han, Wei Yang

Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance.

Image Generation

Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information

no code implementations20 Sep 2023 Kuan Tian, Yonghang Guan, Jinxi Xiang, Jun Zhang, Xiao Han, Wei Yang

First, to solve the problem of inconsistency of codec caused by the uncertainty of floating point calculations across platforms, we design a calibration transmitting system to guarantee the consistent quantization of entropy parameters between the encoding and decoding stages.

Quantization

Progressive Text-to-Image Diffusion with Soft Latent Direction

1 code implementation18 Sep 2023 Yuteng Ye, Jiale Cai, Hang Zhou, Guanwen Li, Youjia Zhang, Zikai Song, Chenxing Gao, Junqing Yu, Wei Yang

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges.

Language Modelling Large Language Model +1

RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models

no code implementations12 Sep 2023 Yufei Li, Zexin Li, Wei Yang, Cong Liu

Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses.

Management

DiffusionTrack: Diffusion Model For Multi-Object Tracking

1 code implementation19 Aug 2023 Run Luo, Zikai Song, Lintao Ma, JinLin Wei, Wei Yang, Min Yang

In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process.

Denoising model +4

Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks

1 code implementation17 Aug 2023 Mirazul Haque, Wei Yang

Then, through research studies, we provide insight into the design choices that can increase robustness of DyNNs against the attack generated using static model.

Dynamic neural networks

Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression

1 code implementation15 Aug 2023 Yue Lv, Jinxi Xiang, Jun Zhang, Wenming Yang, Xiao Han, Wei Yang

We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation.

Decoder Image Compression

IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

4 code implementations13 Aug 2023 Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, Wei Yang

Despite the simplicity of our method, an IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fully fine-tuned image prompt model.

Diffusion Personalization Tuning Free Image Generation +2

HateModerate: Testing Hate Speech Detectors against Content Moderation Policies

1 code implementation23 Jul 2023 Jiangrui Zheng, Xueqing Liu, Guanqun Yang, Mirazul Haque, Xing Qian, Ravishka Rathnasuriya, Wei Yang, Girish Budhrani

We observe significant improvement in the models' conformity to content policies while having comparable scores on the original test data.

Hate Speech Detection

MIMONet: Multi-Input Multi-Output On-Device Deep Learning

no code implementations22 Jul 2023 Zexin Li, Xiaoxi He, Yufei Li, Wei Yang, Lothar Thiele, Cong Liu

In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage.

Deep Learning Model Compression

DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization

no code implementations11 Jul 2023 Simin Chen, Shiyi Wei, Cong Liu, Wei Yang

\tool tackles the dynamic nature of DyNNs by introducing a compilation mechanism that redistributes the control and data flow of the original DNN programs during the compilation process.

Dynamic neural networks

RLTF: Reinforcement Learning from Unit Test Feedback

1 code implementation10 Jul 2023 Jiate Liu, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Wei Yang, Deheng Ye

The goal of program synthesis, or code generation, is to generate executable code based on given descriptions.

Code Generation Program Synthesis +3

AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System

no code implementations10 Jul 2023 Yuzhe Qin, Wei Yang, Binghao Huang, Karl Van Wyk, Hao Su, Xiaolong Wang, Yu-Wei Chao, Dieter Fox

For real-world experiments, AnyTeleop can outperform a previous system that was designed for a specific robot hardware with a higher success rate, using the same robot.

Imitation Learning

DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy

1 code implementation28 Jun 2023 Yiwen Zhang, Chuanpu Li, Liming Zhong, Zeli Chen, Wei Yang, Xuetao Wang

Treatment planning, which is a critical component of the radiotherapy workflow, is typically carried out by a medical physicist in a time-consuming trial-and-error manner.

Computed Tomography (CT) Denoising +1

C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction

no code implementations ICCV 2023 Luoyuan Xu, Tao Guan, Yuesong Wang, Wenkai Liu, Zhaojie Zeng, Junle Wang, Wei Yang

There is an emerging effort to combine the two popular 3D frameworks using Multi-View Stereo (MVS) and Neural Implicit Surfaces (NIS) with a specific focus on the few-shot / sparse view setting.

Depth Estimation Surface Reconstruction

SlothSpeech: Denial-of-service Attack Against Speech Recognition Models

1 code implementation1 Jun 2023 Mirazul Haque, Rutvij Shah, Simin Chen, Berrak Şişman, Cong Liu, Wei Yang

We show that popular ASR models like Speech2Text model and Whisper model have dynamic computation based on different inputs, causing dynamic efficiency.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Future-conditioned Unsupervised Pretraining for Decision Transformer

1 code implementation26 May 2023 Zhihui Xie, Zichuan Lin, Deheng Ye, Qiang Fu, Wei Yang, Shuai Li

While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data.

Decision Making Reinforcement Learning (RL)

Dynamic Transformers Provide a False Sense of Efficiency

1 code implementation20 May 2023 Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby T. Tan, Haizhou Li

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference.

Adversarial Attack

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

no code implementations23 Apr 2023 Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Weixuan Wang, Siqin Li, Xianliang Wang, Xianhan Zeng, Rundong Wang, Jiawei Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.

Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition

1 code implementation7 Apr 2023 Weijie Li, Wei Yang, Wenpeng Zhang, Tianpeng Liu, Yongxiang Liu, Li Liu

However, robustly recognizing vehicle targets is a challenging task in SAR due to the large intraclass variations and small interclass variations.

Data Augmentation Disentanglement

Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR

2 code implementations3 Apr 2023 Weijie Li, Wei Yang, Li Liu, Wenpeng Zhang, Yongxiang Liu

Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR.

Deep Learning Selection bias

NeMF: Inverse Volume Rendering with Neural Microflake Field

no code implementations ICCV 2023 Youjia Zhang, Teng Xu, Junqing Yu, Yuteng Ye, Junle Wang, Yanqing Jing, Jingyi Yu, Wei Yang

Recovering the physical attributes of an object's appearance from its images captured under an unknown illumination is challenging yet essential for photo-realistic rendering.

Learning Human-to-Robot Handovers from Point Clouds

no code implementations CVPR 2023 Sammy Christen, Wei Yang, Claudia Pérez-D'Arpino, Otmar Hilliges, Dieter Fox, Yu-Wei Chao

We propose the first framework to learn control policies for vision-based human-to-robot handovers, a critical task for human-robot interaction.

Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection

1 code implementation10 Feb 2023 Hang Zhou, Junqing Yu, Wei Yang

To address this issue, we propose an Uncertainty Regulated Dual Memory Units (UR-DMU) model to learn both the representations of normal data and discriminative features of abnormal data.

Anomaly Detection Video Anomaly Detection

Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization

1 code implementation5 Feb 2023 Zichuan Lin, Xiapeng Wu, Mingfei Sun, Deheng Ye, Qiang Fu, Wei Yang, Wei Liu

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse.

Deep Reinforcement Learning MuJoCo

Compact Transformer Tracker with Correlative Masked Modeling

1 code implementation26 Jan 2023 Zikai Song, Run Luo, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang

Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism.

Decoder Visual Object Tracking

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning

no code implementations20 Jan 2023 Haoxuan Pan, Deheng Ye, Xiaoming Duan, Qiang Fu, Wei Yang, Jianping He, Mingfei Sun

We show that, despite such state distribution shift, the policy gradient estimation bias can be reduced in the following three ways: 1) a small learning rate; 2) an adaptive-learning-rate-based optimizer; and 3) KL regularization.

continuous-control Continuous Control +3

Artificial intelligence for diagnosing and predicting survival of patients with renal cell carcinoma: Retrospective multi-center study

no code implementations12 Jan 2023 Siteng Chen, Xiyue Wang, Jun Zhang, Liren Jiang, Ning Zhang, Feng Gao, Wei Yang, Jinxi Xiang, Sen yang, Junhua Zheng, Xiao Han

The OSrisk for the prediction of 5-year survival status achieved AUC of 0. 784 (0. 746-0. 819) in the TCGA cohort, which was further verified in the independent General cohort and the CPTAC cohort, with AUC of 0. 774 (0. 723-0. 820) and 0. 702 (0. 632-0. 765), respectively.

Prognosis whole slide images

The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection

no code implementations CVPR 2023 Simin Chen, Hanlin Chen, Mirazul Haque, Cong Liu, Wei Yang

Recent advancements in deploying deep neural networks (DNNs) on resource-constrained devices have generated interest in input-adaptive dynamic neural networks (DyNNs).

Adversarial Attack Dynamic neural networks

Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo

1 code implementation CVPR 2023 Yuesong Wang, Zhaojie Zeng, Tao Guan, Wei Yang, Zhuo Chen, Wenkai Liu, Luoyuan Xu, Yawei Luo

To detect more anchor pixels to ensure better adaptive patch deformation, we propose to evaluate the matching ambiguity of a certain pixel by checking the convergence of the estimated depth as optimization proceeds.

Multi-View 3D Reconstruction Point Clouds

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

1 code implementation4 Dec 2022 Boxuan Zhao, Jun Zhang, Deheng Ye, Jian Cao, Xiao Han, Qiang Fu, Wei Yang

Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.

Benchmarking Decision Making +5

Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification

1 code implementation27 Nov 2022 Yuteng Ye, Hang Zhou, Jiale Cai, Chenxing Gao, Youjia Zhang, Junle Wang, Qiang Hu, Junqing Yu, Wei Yang

The framework mainly consists of a sparse encoder, a multi-view feature mathcing module, and a feature consolidation decoder.

Decoder Occluded Person Re-Identification

Joint Beamforming Design and 3D DoA Estimation for RIS-aided Communication System

no code implementations3 Nov 2022 Zhengyu Wang, Wei Yang, Tiebin Mi, Robert Caiming Qiu

To overcome the mutually coupled problem between the beamforming design at the RIS and DoA estimation, we explore the separable sparse representation structure and propose an alternating optimization algorithm.

PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning

no code implementations17 Oct 2022 Yiqun Chen, Hangyu Mao, Jiaxin Mao, Shiguang Wu, Tianle Zhang, Bin Zhang, Wei Yang, Hongxing Chang

Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information.

Learning-To-Rank reinforcement-learning +2

TestAug: A Framework for Augmenting Capability-based NLP Tests

1 code implementation COLING 2022 Guanqun Yang, Mirazul Haque, Qiaochu Song, Wei Yang, Xueqing Liu

Our experiments show that TestAug has three advantages over the existing work on behavioral testing: (1) TestAug can find more bugs than existing work; (2) The test cases in TestAug are more diverse; and (3) TestAug largely saves the manual efforts in creating the test suites.

DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks

no code implementations10 Oct 2022 Simin Chen, Mirazul Haque, Cong Liu, Wei Yang

To ensure an AdNN satisfies the performance requirements of resource-constrained applications, it is essential to conduct performance testing to detect IDPBs in the AdNN.

Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation

1 code implementation8 Oct 2022 Peizhe Jiang, Wei Yang, Xiaoqing Ye, Xiao Tan, Meng Wu

Monocular depth estimation (MDE) in the self-supervised scenario has emerged as a promising method as it refrains from the requirement of ground truth depth.

Data Augmentation Monocular Depth Estimation

LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models

no code implementations7 Oct 2022 Xiaoning Feng, Xiaohong Han, Simin Chen, Wei Yang

In this paper, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs.

Causal Inference Machine Translation +3

Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets

no code implementations5 Oct 2022 Yanbing Liu, Wei Li, Kun Cheng, Xun Liu, Wei Yang

In order to comprehensively investigate the influence caused by the misalignment, we proposed a method for estimating the performance of a 4f-ONN in response to various misalignment in the context of the image classification task. The misalignment in numerical simulation is estimated by manipulating the optical intensity distributions in the fourth focus plane in the 4f system.

Classification Image Classification

DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations

no code implementations28 Sep 2022 Zoey Qiuyu Chen, Karl Van Wyk, Yu-Wei Chao, Wei Yang, Arsalan Mousavian, Abhishek Gupta, Dieter Fox

The policy learned from our dataset can generalize well on unseen object poses in both simulation and the real world

Object

DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep Learning

1 code implementation13 Sep 2022 Sen yang, Tao Shen, Yuqi Fang, Xiyue Wang, Jun Zhang, Wei Yang, Junzhou Huang, Xiao Han

The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field.

Disentanglement Drug Discovery +1

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

no code implementations1 Sep 2022 Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, Xiu Li

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.

Bayesian Inference Knowledge Distillation +5

Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions

no code implementations29 Jun 2022 Yun-Chun Chen, Adithyavairavan Murali, Balakumar Sundaralingam, Wei Yang, Animesh Garg, Dieter Fox

The pipeline of current robotic pick-and-place methods typically consists of several stages: grasp pose detection, finding inverse kinematic solutions for the detected poses, planning a collision-free trajectory, and then executing the open-loop trajectory to the grasp pose with a low-level tracking controller.

Object

VulCNN: An Image-inspired Scalable Vulnerability Detection System

1 code implementation International Conference on Software Engineering 2022 Yueming Wu, Deqing Zou, Shihan Dou, Wei Yang, Duo Xu, Hai Jin

Furthermore, we conduct a case study on more than 25 million lines of code and the result indicates that VulCNN has the ability to detect large-scale vulnerability.

Image Classification Vulnerability Detection

Learning to Reverse DNNs from AI Programs Automatically

no code implementations20 May 2022 Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang

With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern.

Transformer Tracking with Cyclic Shifting Window Attention

1 code implementation CVPR 2022 Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang

Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism.

Object Visual Object Tracking

Detecting Topology Attacks against Graph Neural Networks

no code implementations21 Apr 2022 Senrong Xu, Yuan YAO, Liangyue Li, Wei Yang, Feng Xu, Hanghang Tong

In this work, we study the victim node detection problem under topology attacks against GNNs.

Node Classification

Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types

no code implementations7 Apr 2022 Siteng Chen, Jinxi Xiang, Xiyue Wang, Jun Zhang, Sen yang, Junzhou Huang, Wei Yang, Junhua Zheng, Xiao Han

MC-TMB algorithm also exhibited good generalization on the external validation cohort with an AUC of 0. 732 (0. 683-0. 761), and better performance when compared to other methods.

whole slide images

NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

1 code implementation CVPR 2022 Simin Chen, Zihe Song, Mirazul Haque, Cong Liu, Wei Yang

To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models.

Caption Generation

NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation

no code implementations8 Mar 2022 Ziyu Wang, Wei Yang, Junming Cao, Lan Xu, Junqing Yu, Jingyi Yu

We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.

NeRF Surface Reconstruction

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

no code implementations17 Feb 2022 Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, François Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman

With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.

EREBA: Black-box Energy Testing of Adaptive Neural Networks

no code implementations12 Feb 2022 Mirazul Haque, Yaswanth Yadlapalli, Wei Yang, Cong Liu

The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2, 000% compared to the original inputs.

NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing

no code implementations12 Feb 2022 Jiakai Zhang, Liao Wang, Xinhang Liu, Fuqiang Zhao, Minzhang Li, Haizhao Dai, Boyuan Zhang, Wei Yang, Lan Xu, Jingyi Yu

We further develop a hybrid neural-rasterization rendering framework to support consumer-level VR headsets so that the aforementioned volumetric video viewing and editing, for the first time, can be conducted immersively in virtual 3D space.

3D Reconstruction NeRF

Artemis: Articulated Neural Pets with Appearance and Motion synthesis

1 code implementation11 Feb 2022 Haimin Luo, Teng Xu, Yuheng Jiang, Chenglin Zhou, QIwei Qiu, Yingliang Zhang, Wei Yang, Lan Xu, Jingyi Yu

Our ARTEMIS enables interactive motion control, real-time animation, and photo-realistic rendering of furry animals.

Motion Synthesis

Video-driven Neural Physically-based Facial Asset for Production

no code implementations11 Feb 2022 Longwen Zhang, Chuxiao Zeng, Qixuan Zhang, Hongyang Lin, Ruixiang Cao, Wei Yang, Lan Xu, Jingyi Yu

In this paper, we present a new learning-based, video-driven approach for generating dynamic facial geometries with high-quality physically-based assets.

4k motion retargeting +1

Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification

1 code implementation CVPR 2022 Yonghang Guan, Jun Zhang, Kuan Tian, Sen yang, Pei Dong, Jinxi Xiang, Wei Yang, Junzhou Huang, Yuyao Zhang, Xiao Han

In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution.

Clustering graph construction +2

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

no code implementations7 Dec 2021 Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang

To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.

Efficient Exploration Hierarchical Reinforcement Learning +6

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs

no code implementations CVPR 2022 Fuqiang Zhao, Wei Yang, Jiakai Zhang, Pei Lin, Yingliang Zhang, Jingyi Yu, Lan Xu

The raw HumanNeRF can already produce reasonable rendering on sparse video inputs of unseen subjects and camera settings.

NeRF

Hierarchical Neural Data Synthesis for Semantic Parsing

no code implementations4 Dec 2021 Wei Yang, Peng Xu, Yanshuai Cao

Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.

Data Augmentation Text-To-SQL

Learning Perceptual Concepts by Bootstrapping from Human Queries

no code implementations9 Nov 2021 Andreea Bobu, Chris Paxton, Wei Yang, Balakumar Sundaralingam, Yu-Wei Chao, Maya Cakmak, Dieter Fox

Second, we treat this low-dimensional concept as an automatic labeler to synthesize a large-scale high-dimensional data set with the simulator.

Motion Planning Object

Learning Diverse Policies in MOBA Games via Macro-Goals

no code implementations NeurIPS 2021 Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, Guoan Han, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.

Deep Reinforcement Learning Diversity +1

TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems

no code implementations29 Sep 2021 Simin Chen, Mirazul Haque, Zihe Song, Cong Liu, Wei Yang

To further the understanding of such efficiency-oriented threats and raise the community’s concern on the efficiency robustness of NMT systems, we propose a new attack approach, TranSlowDown, to test the efficiency robustness of NMT systems.

Machine Translation NMT +1

NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs

no code implementations29 Sep 2021 Mirazul Haque, Simin Chen, Wasif Arman Haque, Cong Liu, Wei Yang

Unlike the memory cost, the energy consumption of the Neural ODEs during inference can be adaptive because of the adaptive nature of the ODE solvers.

Adversarial Attack Object Recognition

Estimating Predictive Uncertainty Under Program Data Distribution Shift

1 code implementation23 Jul 2021 Yufei Li, Simin Chen, Wei Yang

Experiments show that program distribution shift does degrade the DL model performance to varying degrees and that existing uncertainty methods all present certain limitations in quantifying uncertainty on program dataset.

GLIB: Towards Automated Test Oracle for Graphically-Rich Applications

1 code implementation19 Jun 2021 Ke Chen, Yufei Li, Yingfeng Chen, Changjie Fan, Zhipeng Hu, Wei Yang

We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.

Data Augmentation

Boosting Offline Reinforcement Learning with Residual Generative Modeling

no code implementations19 Jun 2021 Hua Wei, Deheng Ye, Zhao Liu, Hao Wu, Bo Yuan, Qiang Fu, Wei Yang, Zhenhui Li

While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.

Offline RL Q-Learning +3

SynthASR: Unlocking Synthetic Data for Speech Recognition

no code implementations14 Jun 2021 Amin Fazel, Wei Yang, YuLan Liu, Roberto Barra-Chicote, Yixiong Meng, Roland Maas, Jasha Droppo

Our observations show that SynthASR holds great promise in training the state-of-the-art large-scale E2E ASR models for new applications while reducing the costs and dependency on production data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

A Globally Normalized Neural Model for Semantic Parsing

no code implementations ACL (spnlp) 2021 Chenyang Huang, Wei Yang, Yanshuai Cao, Osmar Zaïane, Lili Mou

In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing.

Semantic Parsing

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

1 code implementation13 May 2021 Menghui Zhu, Minghuan Liu, Jian Shen, Zhicheng Zhang, Sheng Chen, Weinan Zhang, Deheng Ye, Yong Yu, Qiang Fu, Wei Yang

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.

Diversity

SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos

1 code implementation23 Apr 2021 Xin Chen, Anqi Pang, Wei Yang, Yuexin Ma, Lan Xu, Jingyi Yu

In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input.

Action Assessment Attribute +1

Wide-Beam Array Antenna Power Gain Maximization via ADMM Framework

no code implementations21 Apr 2021 Shiwen Lei, Jing Tian, Zhipeng Lin, Haoquan Hu, Bo Chen, Wei Yang, Pu Tang, Xiangdong Qiu

This paper proposes two algorithms to maximize the minimum array power gain in a wide-beam mainlobe by solving the power gain pattern synthesis (PGPS) problem with and without sidelobe constraints.

F3SNet: A Four-Step Strategy for QIM Steganalysis of Compressed Speech Based on Hierarchical Attention Network

1 code implementation13 Jan 2021 Chuanpeng Guo, Wei Yang, Liusheng Huang

Traditional machine learning-based steganalysis methods on compressed speech have achieved great success in the field of communication security.

Cryptography and Security

AttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack

no code implementations1 Jan 2021 Simin Chen, Zihe Song, Lei Ma, Cong Liu, Wei Yang

We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.

Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation

no code implementations ICCV 2021 Zhi Chen, Xiaoqing Ye, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang

Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.

Monocular Depth Estimation Stereo Matching

Optimizing Deeper Transformers on Small Datasets

1 code implementation ACL 2021 Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Yanshuai Cao

This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.

Reading Comprehension SQL Parsing +1

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

no code implementations18 Dec 2020 Sheng Chen, Menghui Zhu, Deheng Ye, Weinan Zhang, Qiang Fu, Wei Yang

Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the ma