Search Results for author: Xiao Liu

Found 242 papers, 117 papers with code

SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation Space

1 code implementation ACL (dialdoc) 2021 Liu Yang, Fanqi Meng, Xiao Liu, Ming-Kuang Daniel Wu, Vicent Ying, James Xu

In this work, we formulate a visual dialog as an information flow in which each piece of information is encoded with the joint visual-linguistic representation of a single dialog round.

Visual Dialog

Geo-BERT Pre-training Model for Query Rewriting in POI Search

no code implementations Findings (EMNLP) 2021 Xiao Liu, Juan Hu, Qi Shen, Huan Chen

Finally, we train a BERT-like pre-training model with text and POIs’ graph embeddings to get an integrated representation of both geographic and semantic information, and apply it in the QR of POI search.

Graph Representation Learning

P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks

no code implementations ACL 2022 Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, Jie Tang

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training.

Language Modelling

An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-Identification

no code implementations ECCV 2020 Zilong Ji, Xiaolong Zou, Xiaohan Lin, Xiao Liu, Tiejun Huang, Si Wu

By iteratively learning with the two strategies, the attentive regions are gradually shifted from the background to the foreground and the features become more discriminative.

Clustering Unsupervised Person Re-Identification

Dual-Channel Evidence Fusion for Fact Verification over Texts and Tables

no code implementations NAACL 2022 Nan Hu, Zirui Wu, Yuxuan Lai, Xiao Liu, Yansong Feng

Different from previous fact extraction and verification tasks that only consider evidence of a single format, FEVEROUS brings further challenges by extending the evidence format to both plain text and tables.

Fact Verification

Rho-1: Not All Tokens Are What You Need

2 code implementations11 Apr 2024 Zhenghao Lin, Zhibin Gou, Yeyun Gong, Xiao Liu, Yelong Shen, Ruochen Xu, Chen Lin, Yujiu Yang, Jian Jiao, Nan Duan, Weizhu Chen

After fine-tuning, Rho-1-1B and 7B achieved state-of-the-art results of 40. 6% and 51. 8% on MATH dataset, respectively - matching DeepSeekMath with only 3% of the pretraining tokens.

Continual Pretraining Language Modelling +1

AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

1 code implementation4 Apr 2024 Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, Jie Tang

Large language models (LLMs) have fueled many intelligent agent tasks, such as web navigation -- but most existing agents perform far from satisfying in real-world webpages due to three factors: (1) the versatility of actions on webpages, (2) HTML text exceeding model processing capacity, and (3) the complexity of decision-making due to the open-domain nature of web.

Decision Making Language Modelling +1

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

1 code implementation3 Apr 2024 Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Wenyi Zhao, Jie Tang, Yuxiao Dong

Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving.


ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback

no code implementations1 Apr 2024 Zhenyu Hou, Yilin Niu, Zhengxiao Du, Xiaohan Zhang, Xiao Liu, Aohan Zeng, Qinkai Zheng, Minlie Huang, Hongning Wang, Jie Tang, Yuxiao Dong

The work presents our practices of aligning LLMs with human preferences, offering insights into the challenges and solutions in RLHF implementations.

Extensive Self-Contrast Enables Feedback-Free Language Model Alignment

2 code implementations31 Mar 2024 Xiao Liu, Xixuan Song, Yuxiao Dong, Jie Tang

In this work, we introduce Self-Contrast, a feedback-free large language model alignment method via exploiting extensive self-generated negatives.

Language Modelling Large Language Model +1

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs

no code implementations29 Mar 2024 Xiao Liu, Jiawei Zhang

This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt.

Language Modelling Large Language Model

Can multiple-choice questions really be useful in detecting the abilities of LLMs?

1 code implementation26 Mar 2024 Wangyue Li, Liangzhi Li, Tong Xiang, Xiao Liu, Wei Deng, Noa Garcia

Additionally, we propose two methods to quantify the consistency and confidence of LLMs' output, which can be generalized to other QA evaluation benchmarks.

Multiple-choice Question Answering

Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization

no code implementations5 Mar 2024 Yuan Lin, Antai Xie, Xiao Liu

Most of the current studies on autonomous vehicle decision-making and control tasks based on reinforcement learning are conducted in simulated environments.

Decision Making reinforcement-learning

Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning

1 code implementation4 Mar 2024 Yiming Huang, Xiao Liu, Yeyun Gong, Zhibin Gou, Yelong Shen, Nan Duan, Weizhu Chen

Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets.

Ranked #49 on Math Word Problem Solving on MATH (using extra training data)

GSM8K Math +1

Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane Change

no code implementations1 Mar 2024 Ruichen Xu, Xiao Liu, Jinming Xu, Yuan Lin

We introduce safe hybrid-action reinforcement learning into discretionary lane change for the first time and propose Parameterized Soft Actor-Critic with PID Lagrangian (PASAC-PIDLag) algorithm.

Autonomous Driving reinforcement-learning

Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language Models

no code implementations1 Mar 2024 Jiandong Jin, Bowen Tang, Mingxuan Ma, Xiao Liu, Yunfei Wang, Qingnan Lai, Jia Yang, Changling Zhou

We introduces Crimson, a system that enhances the strategic reasoning capabilities of Large Language Models (LLMs) within the realm of cybersecurity.

Hallucination Retrieval

Teaching Large Language Models an Unseen Language on the Fly

1 code implementation29 Feb 2024 Chen Zhang, Xiao Liu, Jiuheng Lin, Yansong Feng

Existing large language models struggle to support numerous low-resource languages, particularly the extremely low-resource ones where there is minimal training data available for effective parameter updating.

In-Context Learning Translation

Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data

1 code implementation27 Feb 2024 Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, Yansong Feng

To address this gap, we introduce the Quantitative Reasoning with Data (QRData) benchmark, aiming to evaluate Large Language Models' capability in statistical and causal reasoning with real-world data.


Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking

no code implementations26 Feb 2024 Peng Gao, Xiao Liu, Yu Wang, Ru-Yue Yuan

To expedite the search process, a random channel selection strategy is employed prior to assessing operation candidates.

Decentralized Federated Unlearning on Blockchain

no code implementations26 Feb 2024 Xiao Liu, Mingyuan Li, Xu Wang, Guangsheng Yu, Wei Ni, Lixiang Li, Haipeng Peng, Renping Liu

To address this, we propose Blockchained Federated Unlearning (BlockFUL), a generic framework that redesigns the blockchain structure using Chameleon Hash (CH) technology to mitigate the complexity of model updating, thereby reducing the computational and consensus costs of unlearning tasks. Furthermore, BlockFUL supports various federated unlearning methods, ensuring the integrity and traceability of model updates, whether conducted in parallel or serial.

Federated Learning

Prejudice and Caprice: A Statistical Framework for Measuring Social Discrimination in Large Language Models

no code implementations23 Feb 2024 Yiran Liu, Ke Yang, Zehan Qi, Xiao Liu, Yang Yu, ChengXiang Zhai

The growing integration of large language models (LLMs) into social operations amplifies their impact on decisions in crucial areas such as economics, law, education, and healthcare, raising public concerns about these models' discrimination-related safety and reliability.

Attribute Sentence

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments

no code implementations22 Feb 2024 Yu Gu, Yiheng Shu, Hao Yu, Xiao Liu, Yuxiao Dong, Jie Tang, Jayanth Srinivasa, Hugo Latapie, Yu Su

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist language agents capable of operating within complex real-world environments.

Using Left and Right Brains Together: Towards Vision and Language Planning

no code implementations16 Feb 2024 Jun Cen, Chenfei Wu, Xiao Liu, Shengming Yin, Yixuan Pei, Jinglong Yang, Qifeng Chen, Nan Duan, JianGuo Zhang

Large Language Models (LLMs) and Large Multi-modality Models (LMMs) have demonstrated remarkable decision masking capabilities on a variety of tasks.

A Systematic Review of Available Datasets in Additive Manufacturing

no code implementations27 Jan 2024 Xiao Liu, Alessandra Mileo, Alan F. Smeaton

In-situ monitoring incorporating data from visual and other sensor technologies, allows the collection of extensive datasets during the Additive Manufacturing (AM) process.

Defect Detection

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

no code implementations25 Jan 2024 Guangyi Chen, Yifan Shen, Zhenhao Chen, Xiangchen Song, Yuewen Sun, Weiran Yao, Xiao Liu, Kun Zhang

Identifying the underlying time-delayed latent causal processes in sequential data is vital for grasping temporal dynamics and making downstream reasoning.

BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions

no code implementations14 Jan 2024 Xiao Liu, Jie Zhao, Wubing Chen, Mao Tan, Yongxing Su

To address this issue, we propose a novel self-interpretable structure, named Backbone Extract Tree (BET), to better explain the agent's behavior by identify the error-prone states.

Decision Making reinforcement-learning +2

CASA: Causality-driven Argument Sufficiency Assessment

1 code implementation10 Jan 2024 Xiao Liu, Yansong Feng, Kai-Wei Chang

Motivated by the definition of probability of sufficiency (PS) in the causal literature, we proposeCASA, a zero-shot causality-driven argument sufficiency assessment framework.

Logical Fallacy Detection

Robust Image Watermarking using Stable Diffusion

1 code implementation8 Jan 2024 Lijun Zhang, Xiao Liu, Antoni Viros Martin, Cindy Xiong Bearfield, Yuriy Brun, Hui Guan

Watermarking images is critical for tracking image provenance and claiming ownership.

Competition-Level Problems are Effective LLM Evaluators

no code implementations4 Dec 2023 Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen

Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about these abilities and the potential data contamination problem recently.

CritiqueLLM: Scaling LLM-as-Critic for Effective and Explainable Evaluation of Large Language Model Generation

2 code implementations30 Nov 2023 Pei Ke, Bosi Wen, Zhuoer Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

Since the natural language processing (NLP) community started to make large language models (LLMs), such as GPT-4, act as a critic to evaluate the quality of generated texts, most of them only train a critique generation model of a specific scale on specific datasets.

Language Modelling Large Language Model

Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark

1 code implementation21 Nov 2023 Xiao Liu, Jianfeng Lin, Jiawei Zhang

The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications.

Decision Making

YouTube Video Analytics for Patient Health Literacy: Evidence from Colonoscopy Preparation Videos

no code implementations21 Nov 2023 Yawen Guo, Xiao Liu, Anjana Susarla, Rema Padman

This study utilizes data analysis methods to retrieve medical information from YouTube videos concerning colonoscopy to manage health conditions.

Management Retrieval

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training

1 code implementation7 Nov 2023 Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang

However, these models are often not well aligned with human intents, which calls for additional treatments on them, that is, the alignment problem.

Group Distributionally Robust Knowledge Distillation

no code implementations1 Nov 2023 Konstantinos Vilouras, Xiao Liu, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris

Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one.

Knowledge Distillation

DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation

no code implementations19 Oct 2023 Bangbang Yang, Wenqi Dong, Lin Ma, WenBo Hu, Xiao Liu, Zhaopeng Cui, Yuewen Ma

To ensure meaningful and aligned textures to the scene, we develop a novel coarse-to-fine panoramic texture generation approach with dual texture alignment, which both considers the geometry and texture cues of the captured scenes.

Texture Synthesis

AgentTuning: Enabling Generalized Agent Abilities for LLMs

1 code implementation19 Oct 2023 Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, Jie Tang

Though many prompting methods have been proposed to complete particular agent tasks, there is lack of research focusing on improving the agent capabilities of LLMs themselves without compromising their general abilities.


Compositional Representation Learning for Brain Tumour Segmentation

no code implementations10 Oct 2023 Xiao Liu, Antanas Kascenas, Hannah Watson, Sotirios A. Tsaftaris, Alison Q. O'Neil

For brain tumour segmentation, deep learning models can achieve human expert-level performance given a large amount of data and pixel-level annotations.

Representation Learning

Adaptive Visual Scene Understanding: Incremental Scene Graph Generation

1 code implementation2 Oct 2023 Naitik Khandelwal, Xiao Liu, Mengmi Zhang

To address the lack of continual learning methodologies in SGG, we introduce the comprehensive Continual ScenE Graph Generation (CSEGG) dataset along with 3 learning scenarios and 8 evaluation metrics.

Benchmarking Continual Learning +5

Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning

no code implementations12 Sep 2023 Xiao Liu, Wubing Chen, Mao Tan

We then design a fidelity-induced mechanism by integrate a fidelity measurement into the reinforcement learning feedback.

Decision Making reinforcement-learning +2

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

1 code implementation28 Aug 2023 Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding.

16k Code Completion +2

Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer

1 code implementation ICCV 2023 Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang

To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner.

Question Answering Video Question Answering

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

1 code implementation ICCV 2023 Xin Lin, Chao Ren, Xiao Liu, Jie Huang, Yinjie Lei

Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.

Image Denoising

AgentBench: Evaluating LLMs as Agents

1 code implementation7 Aug 2023 Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, Jie Tang

We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.

Decision Making Instruction Following

Random Sub-Samples Generation for Self-Supervised Real Image Denoising

1 code implementation ICCV 2023 Yizhong Pan, Xiao Liu, Xiangyu Liao, Yuanzhouhan Cao, Chao Ren

With sufficient paired training samples, the supervised deep learning methods have attracted much attention in image denoising because of their superior performance.

Image Denoising

Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields

no code implementations ICCV 2023 WenBo Hu, Yuling Wang, Lin Ma, Bangbang Yang, Lin Gao, Xiao Liu, Yuewen Ma

Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e. g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minutes but suffers from blurring or aliasing when rendering at various distances or resolutions due to ignoring the sampling area.

Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing

no code implementations14 Jul 2023 Xiao Liu, Alessandra Mileo, Alan F. Smeaton

The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process.

Active Learning

Language-free Compositional Action Generation via Decoupling Refinement

1 code implementation7 Jul 2023 Xiao Liu, Guangyi Chen, Yansong Tang, Guangrun Wang, Xiao-Ping Zhang, Ser-Nam Lim

Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation.

Action Generation

Random Walk on Multiple Networks

1 code implementation4 Jul 2023 Dongsheng Luo, Yuchen Bian, Yaowei Yan, Xiong Yu, Jun Huan, Xiao Liu, Xiang Zhang

To take advantage of rich information in multiple networks and make better inferences on entities, in this study, we propose random walk on multiple networks, RWM.

Link Prediction Local Community Detection +1

Compositionally Equivariant Representation Learning

no code implementations13 Jun 2023 Xiao Liu, Pedro Sanchez, Spyridon Thermos, Alison Q. O'Neil, Sotirios A. Tsaftaris

By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings.

Anatomy Image Segmentation +3

How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension

1 code implementation1 Jun 2023 Chen Zhang, Jiuheng Lin, Xiao Liu, Yuxuan Lai, Yansong Feng, Dongyan Zhao

We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances.

Machine Reading Comprehension

SummIt: Iterative Text Summarization via ChatGPT

1 code implementation24 May 2023 Haopeng Zhang, Xiao Liu, Jiawei Zhang

Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step.

Text Summarization

Allies: Prompting Large Language Model with Beam Search

1 code implementation24 May 2023 Hao Sun, Xiao Liu, Yeyun Gong, Yan Zhang, Daxin Jiang, Linjun Yang, Nan Duan

With the advance of large language models (LLMs), the research field of LLM applications becomes more and more popular and the idea of constructing pipelines to accomplish complex tasks by stacking LLM API calls come true.

Language Modelling Large Language Model +3

Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration

no code implementations24 May 2023 Kejuan Yang, Xiao Liu, Kaiwen Men, Aohan Zeng, Yuxiao Dong, Jie Tang

We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW), which extends the maximum context lengths of language models, e. g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques.

Long-Context Understanding

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation

1 code implementation23 May 2023 Da Yin, Xiao Liu, Fan Yin, Ming Zhong, Hritik Bansal, Jiawei Han, Kai-Wei Chang

Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses.

Continual Learning

Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds

1 code implementation23 May 2023 Junyuan Ouyang, Xiao Liu, Haoyao Chen

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds.

Cloud Detection

Multi-Task Models Adversarial Attacks

1 code implementation20 May 2023 Lijun Zhang, Xiao Liu, Kaleel Mahmood, Caiwen Ding, Hui Guan

We then introduce a novel attack framework, the Gradient Balancing Multi-Task Attack (GB-MTA), which treats attacking a multi-task model as an optimization problem.

Multi-Task Learning

Boosting Event Extraction with Denoised Structure-to-Text Augmentation

no code implementations16 May 2023 Bo wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin

Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations.

Event Extraction Text Augmentation +1

Unsupervised Dense Retrieval Training with Web Anchors

1 code implementation10 May 2023 Yiqing Xie, Xiao Liu, Chenyan Xiong

Based on their commonalities, we train an unsupervised dense retriever, Anchor-DR, with a contrastive learning task that matches the anchor text and the linked document.

Contrastive Learning Question Answering +1

Weighted Point Cloud Normal Estimation

no code implementations6 May 2023 Weijia Wang, Xuequan Lu, Di Shao, Xiao Liu, Richard Dazeley, Antonio Robles-Kelly, Wei Pan

Existing normal estimation methods for point clouds are often less robust to severe noise and complex geometric structures.

Contrastive Learning regression

DiffuSum: Generation Enhanced Extractive Summarization with Diffusion

1 code implementation2 May 2023 Haopeng Zhang, Xiao Liu, Jiawei Zhang

This paper proposes DiffuSum, a novel paradigm for extractive summarization, by directly generating the desired summary sentence representations with diffusion models and extracting sentences based on sentence representation matching.

Extractive Summarization Sentence

Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention

1 code implementation Tiny Papers @ ICLR 2023 Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You

We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.

Dialogue Act Classification Dialogue Understanding +2

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

2 code implementations10 Apr 2023 Zhenyu Hou, Yufei He, Yukuo Cen, Xiao Liu, Yuxiao Dong, Evgeny Kharlamov, Jie Tang

Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data.

Self-Supervised Learning

Extractive Summarization via ChatGPT for Faithful Summary Generation

no code implementations9 Apr 2023 Haopeng Zhang, Xiao Liu, Jiawei Zhang

In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance.

Extractive Summarization In-Context Learning +1

Inverse Models for Estimating the Initial Condition of Spatio-Temporal Advection-Diffusion Processes

1 code implementation8 Feb 2023 Xiao Liu, Kyongmin Yeo

The irregular sampling scheme is the general scenario, while computationally efficient solutions are available in the spectral domain for non-uniform and shifted uniform sampling.

MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers

1 code implementation15 Dec 2022 Kun Zhou, Xiao Liu, Yeyun Gong, Wayne Xin Zhao, Daxin Jiang, Nan Duan, Ji-Rong Wen

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense vectors.

Passage Retrieval Retrieval

An adaptive human-in-the-loop approach to emission detection of Additive Manufacturing processes and active learning with computer vision

no code implementations12 Dec 2022 Xiao Liu, Alan F. Smeaton, Alessandra Mileo

More specifically, this paper will look at two scenarios: firstly, using convolutional neural networks (CNNs) to automatically inspect and classify emission data collected by in-situ monitoring and secondly, applying Active Learning techniques to the developed classification model to construct a human-in-the-loop mechanism in order to accelerate the labeling process of the emission data.

Active Learning Transfer Learning

LEAD: Liberal Feature-based Distillation for Dense Retrieval

1 code implementation10 Dec 2022 Hao Sun, Xiao Liu, Yeyun Gong, Anlei Dong, Jingwen Lu, Yan Zhang, Linjun Yang, Rangan Majumder, Nan Duan

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model.

Document Ranking Knowledge Distillation +2

ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information

no code implementations29 Nov 2022 Arnold Overwijk, Chenyan Xiong, Xiao Liu, Cameron VandenBerg, Jamie Callan

ClueWeb22, the newest iteration of the ClueWeb line of datasets, provides 10 billion web pages affiliated with rich information.

document understanding Retrieval

Imperceptible Adversarial Attack via Invertible Neural Networks

1 code implementation28 Nov 2022 Zihan Chen, Ziyue Wang, JunJie Huang, Wentao Zhao, Xiao Liu, Dejian Guan

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples.

Adversarial Attack

Reason from Context with Self-supervised Learning

no code implementations23 Nov 2022 Xiao Liu, Ankur Sikarwar, Gabriel Kreiman, Zenglin Shi, Mengmi Zhang

To better accommodate the object-centric nature of current downstream tasks such as object recognition and detection, various methods have been proposed to suppress contextual biases or disentangle objects from contexts.

Object Object Recognition +2

Does Debiasing Inevitably Degrade the Model Performance

no code implementations14 Nov 2022 Yiran Liu, Xiao Liu, Haotian Chen, Yang Yu

We use our theoretical framework to explain why the current debiasing methods cause performance degradation.

IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models

no code implementations25 Oct 2022 Chenguang Wang, Xiao Liu, Dawn Song

Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs.

Open Information Extraction

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval

1 code implementation21 Oct 2022 Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan, Weizhu Chen

Thus, we propose a simple ambiguous negatives sampling method, SimANS, which incorporates a new sampling probability distribution to sample more ambiguous negatives.

Retrieval Text Retrieval

Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario

1 code implementation20 Oct 2022 Xiao Liu, Yansong Feng, Jizhi Tang, Chengang Hu, Dongyan Zhao

Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way.

counterfactual Recipe Generation

Diffusion Models for Causal Discovery via Topological Ordering

1 code implementation12 Oct 2022 Pedro Sanchez, Xiao Liu, Alison Q O'Neil, Sotirios A. Tsaftaris

We introduce theory for updating the learned Hessian without re-training the neural network, and we show that computing with a subset of samples gives an accurate approximation of the ordering, which allows scaling to datasets with more samples and variables.

Causal Discovery

Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient

1 code implementation10 Oct 2022 Wubing Chen, Wenbin Li, Xiao Liu, Shangdong Yang, Yang Gao

Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces.

Multi-agent Reinforcement Learning reinforcement-learning +3

HEGEL: Hypergraph Transformer for Long Document Summarization

1 code implementation9 Oct 2022 Haopeng Zhang, Xiao Liu, Jiawei Zhang

Extractive summarization for long documents is challenging due to the extended structured input context.

Document Summarization Extractive Summarization +1

Uplifting Message Passing Neural Network with Graph Original Information

no code implementations8 Oct 2022 Xiao Liu, Lijun Zhang, Hui Guan

Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and have shown astonishing improvement in node classification tasks.

Graph Representation Learning Node Classification

PROD: Progressive Distillation for Dense Retrieval

1 code implementation27 Sep 2022 Zhenghao Lin, Yeyun Gong, Xiao Liu, Hang Zhang, Chen Lin, Anlei Dong, Jian Jiao, Jingwen Lu, Daxin Jiang, Rangan Majumder, Nan Duan

It is common that a better teacher model results in a bad student via distillation due to the nonnegligible gap between teacher and student.

Knowledge Distillation Natural Questions +1

Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer

1 code implementation24 Aug 2022 Fengji Zhang, Jin Liu, Yao Wan, Xiao Yu, Xiao Liu, Jacky Keung

Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems.

Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries

1 code implementation16 Aug 2022 Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Wu, Yuxiao Dong, Jie Tang

In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies.

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

2 code implementations23 Jul 2022 Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, Xiang Bai

Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.

Optical Character Recognition (OCR)

BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion

no code implementations16 Jul 2022 Fanglin Chen, Xiao Liu, Bo Tang, Feiyu Xiong, Serim Hwang, Guomian Zhuang

During deployment, we combine the offline RL model with the LP model to generate a robust policy under the budget constraints.

Offline RL reinforcement-learning +1

Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers

2 code implementations14 Jul 2022 Weng Lam Tam, Xiao Liu, Kaixuan Ji, Lilong Xue, Xingjian Zhang, Yuxiao Dong, Jiahua Liu, Maodi Hu, Jie Tang

By updating only 0. 1% of the model parameters, the prompt tuning strategy can help retrieval models achieve better generalization performance than traditional methods in which all parameters are updated.

Retrieval Text Retrieval +1

vMFNet: Compositionality Meets Domain-generalised Segmentation

1 code implementation29 Jun 2022 Xiao Liu, Spyridon Thermos, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris

Moreover, with a reconstruction module, unlabeled data can also be used to learn the vMF kernels and likelihoods by recombining them to reconstruct the input image.

Anatomy Image Segmentation +3

Why patient data cannot be easily forgotten?

no code implementations29 Jun 2022 Ruolin Su, Xiao Liu, Sotirios A. Tsaftaris

With the advent of AI learned on data, one can imagine that such rights can extent to requests for forgetting knowledge of patient's data within AI models.

Physics-Informed Statistical Modeling for Wildfire Aerosols Process Using Multi-Source Geostationary Satellite Remote-Sensing Data Streams

1 code implementation23 Jun 2022 Guanzhou Wei, Venkat Krishnan, Yu Xie, Manajit Sengupta, Yingchen Zhang, Haitao Liao, Xiao Liu

Increasingly frequent wildfires significantly affect solar energy production as the atmospheric aerosols generated by wildfires diminish the incoming solar radiation to the earth.

Regression Trees on Grassmann Manifold for Adapting Reduced-Order Models

no code implementations22 Jun 2022 Xiao Liu, Xinchao Liu

When a ROM, constructed using the POD basis obtained from training data, is applied to new parameter settings, the model often lacks robustness against the change of parameters in design, control, and other real-time operation problems.


Improving Subgraph Representation Learning via Multi-View Augmentation

no code implementations25 May 2022 Yili Shen, Xiao Liu, Cheng-Wei Ju, Jiaxu Yan, Jun Yi, Zhou Lin, Hui Guan

Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-property relationships and collective cellular function.

Representation Learning

GraphMAE: Self-Supervised Masked Graph Autoencoders

3 code implementations22 May 2022 Zhenyu Hou, Xiao Liu, Yukuo Cen, Yuxiao Dong, Hongxia Yang, Chunjie Wang, Jie Tang

Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields.

Contrastive Learning Graph Classification +4

MGRR-Net: Multi-level Graph Relational Reasoning Network for Facial Action Units Detection

no code implementations4 Apr 2022 Xuri Ge, Joemon M. Jose, Songpei Xu, Xiao Liu, Hu Han

While the region-level feature learning from local face patches features via graph neural network can encode the correlation across different AUs, the pixel-wise and channel-wise feature learning via graph attention network can enhance the discrimination ability of AU features from global face features.

Graph Attention Relational Reasoning

Things not Written in Text: Exploring Spatial Commonsense from Visual Signals

1 code implementation ACL 2022 Xiao Liu, Da Yin, Yansong Feng, Dongyan Zhao

We probe PLMs and models with visual signals, including vision-language pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.

Image Generation Natural Language Understanding +1

A Tree-Structured Multi-Task Model Recommender

1 code implementation10 Mar 2022 Lijun Zhang, Xiao Liu, Hui Guan

Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL).

Multi-Task Learning

Syntax-Aware Network for Handwritten Mathematical Expression Recognition

2 code implementations CVPR 2022 Ye Yuan, Xiao Liu, Wondimu Dikubab, Hui Liu, Zhilong Ji, Zhongqin Wu, Xiang Bai

In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network.

Automatic Facial Paralysis Estimation with Facial Action Units

no code implementations3 Mar 2022 Xuri Ge, Joemon M. Jose, Pengcheng Wang, Arunachalam Iyer, Xiao Liu, Hu Han

In this paper, we propose a novel Adaptive Local-Global Relational Network (ALGRNet) for facial AU detection and use it to classify facial paralysis severity.

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

1 code implementation2 Mar 2022 Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang

We present SelfKG with efficient strategies to optimize this objective for aligning entities without label supervision.

Entity Alignment Knowledge Graphs +1

Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation

no code implementations2 Mar 2022 Xiao Liu, Shuyang Liu, Wenbin Li, Shangdong Yang, Yang Gao

Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies.

3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning

no code implementations6 Jan 2022 Di Shao, Xuequan Lu, Xiao Liu

While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data.

Unsupervised Pre-training

All-in-One Image Restoration for Unknown Corruption

1 code implementation CVPR 2022 Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng

In this paper, we study a challenging problem in image restoration, namely, how to develop an all-in-one method that could recover images from a variety of unknown corruption types and levels.

Image Restoration

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

1 code implementation2 Dec 2021 Jie Ren, Wenteng Liang, Ran Yan, Luo Mai, Shiwen Liu, Xiao Liu

Large-scale Bundle Adjustment (BA) requires massive memory and computation resources which are difficult to be fulfilled by existing BA libraries.

Learning with Noisy Correspondence for Cross-modal Matching

1 code implementation NeurIPS 2021 Zhenyu Huang, guocheng niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, Hua Wu, Xi Peng

Based on this observation, we reveal and study a latent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisy labels.

Image-text matching Memorization +2

TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers

1 code implementation CVPR 2022 Yikang Ding, Wentao Yuan, Qingtian Zhu, Haotian Zhang, Xiangyue Liu, Yuanjiang Wang, Xiao Liu

We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images.

3D Reconstruction Feature Correlation

MegLoc: A Robust and Accurate Visual Localization Pipeline

no code implementations25 Nov 2021 Shuxue Peng, Zihang He, Haotian Zhang, Ran Yan, Chuting Wang, Qingtian Zhu, Xiao Liu

In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years.

Autonomous Driving Pose Estimation +1

Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression

no code implementations19 Nov 2021 Yuezhou Sun, Wenlong Zhao, Lijun Zhang, Xiao Liu, Hui Guan, Matei Zaharia

This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters.

Neural Network Compression Quantization

Meta-learning for RIS-assisted NOMA Networks

no code implementations4 Nov 2021 Yixuan Zou, Yuanwei Liu, Kaifeng Han, Xiao Liu, Kok Keong Chai

Extensive simulation results demonstrate that the proposed QoS-based NOMA network achieves significantly higher transmission throughput compared to the conventional orthogonal multiple access (OMA) network.

Clustering Meta-Learning

AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning

1 code implementation25 Oct 2021 Lijun Zhang, Xiao Liu, Hui Guan

The first challenge is to determine what parameters to share across tasks to optimize for both memory efficiency and task accuracy.

Multi-Task Learning

Deep Point Cloud Normal Estimation via Triplet Learning

no code implementations20 Oct 2021 Weijia Wang, Xuequan Lu, Dasith de Silva Edirimuni, Xiao Liu, Antonio Robles-Kelly

It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector.

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

4 code implementations14 Oct 2021 Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, Jie Tang

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training.

Language Modelling

Learning the Representation of Behavior Styles with Imitation Learning

no code implementations29 Sep 2021 Xiao Liu, Meng Wang, Zhaorong Wang, Yingfeng Chen, Yujing Hu, Changjie Fan, Chongjie Zhang

Imitation learning is one of the methods for reproducing expert demonstrations adaptively by learning a mapping between observations and actions.

Imitation Learning

LOF: Structure-Aware Line Tracking based on Optical Flow

no code implementations17 Sep 2021 Meixiang Quan, Zheng Chai, Xiao Liu

Lines provide the significantly richer geometric structural information about the environment than points, so lines are widely used in recent Visual Odometry (VO) works.

Computational Efficiency Line Detection +2

Learning Disentangled Representations in the Imaging Domain

1 code implementation26 Aug 2021 Xiao Liu, Pedro Sanchez, Spyridon Thermos, Alison Q. O'Neil, Sotirios A. Tsaftaris

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision.

Representation Learning

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

1 code implementation ICCV 2021 Yuxiang Wei, Yupeng Shi, Xiao Liu, Zhilong Ji, Yuan Gao, Zhongqin Wu, WangMeng Zuo

It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation.

Disentanglement Image Generation

Method Towards CVPR 2021 Image Matching Challenge

no code implementations10 Aug 2021 Xiaopeng Bi, Yu Chen, Xinyang Liu, Dehao Zhang, Ran Yan, Zheng Chai, Haotian Zhang, Xiao Liu

This report describes Megvii-3D team's approach towards CVPR 2021 Image Matching Workshop.

Method Towards CVPR 2021 SimLocMatch Challenge

no code implementations10 Aug 2021 Xiaopeng Bi, Ran Yan, Zheng Chai, Haotian Zhang, Xiao Liu

This report describes Megvii-3D team's approach towards SimLocMatch Challenge @ CVPR 2021 Image Matching Workshop.

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

no code implementations10 Aug 2021 Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, Xin Jiang

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.

Clone Detection Code Search +5

UniCon: Unified Context Network for Robust Active Speaker Detection

no code implementations5 Aug 2021 Yuanhang Zhang, Susan Liang, Shuang Yang, Xiao Liu, Zhongqin Wu, Shiguang Shan, Xilin Chen

Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties.

Audio-Visual Active Speaker Detection

Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval

no code implementations5 Aug 2021 Xuri Ge, Fuhai Chen, Joemon M. Jose, Zhilong Ji, Zhongqin Wu, Xiao Liu

In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e. g., "dog $\to$ play $\to$ ball" in semantic structure for an image, and (ii) seeking explicit inter-modal structural and semantic correspondence between the visual and textual modalities.

Retrieval Semantic correspondence +1

Rethinking Hard-Parameter Sharing in Multi-Domain Learning

no code implementations23 Jul 2021 Lijun Zhang, Qizheng Yang, Xiao Liu, Hui Guan

One common sharing practice is to share the bottom layers of a deep neural network among domains while using separate top layers for each domain.

Fine-Grained Image Classification Multi-Task Learning

Locality-aware Channel-wise Dropout for Occluded Face Recognition

no code implementations20 Jul 2021 Mingjie He, Jie Zhang, Shiguang Shan, Xiao Liu, Zhongqin Wu, Xilin Chen

Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.

Face Recognition

Unsupervised Neural Rendering for Image Hazing

no code implementations14 Jul 2021 Boyun Li, Yijie Lin, Xiao Liu, Peng Hu, Jiancheng Lv, Xi Peng

To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i. e., unpaired real hazy images.

Image Dehazing Neural Rendering

Controllable cardiac synthesis via disentangled anatomy arithmetic

1 code implementation4 Jul 2021 Spyridon Thermos, Xiao Liu, Alison O'Neil, Sotirios A. Tsaftaris

Motivated by the ability to disentangle images into spatial anatomy (tensor) factors and accompanying imaging (vector) representations, we propose a framework termed "disentangled anatomy arithmetic", in which a generative model learns to combine anatomical factors of different input images such that when they are re-entangled with the desired imaging modality (e. g. MRI), plausible new cardiac images are created with the target characteristics.


Boost-R: Gradient Boosted Trees for Recurrence Data

no code implementations3 Jul 2021 Xiao Liu, Rong pan

Boost-R constructs an ensemble of gradient boosted additive trees to estimate the cumulative intensity function of the recurrent event process, where a new tree is added to the ensemble by minimizing the regularized L2 distance between the observed and predicted cumulative intensity.


1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition

no code implementations2 Jul 2021 Pengcheng Wang, Lingqiao Ji, Zhilong Ji, Yuan Gao, Xiao Liu

In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021.

Face Detection Image Enhancement +2

Multi-Granularity Network with Modal Attention for Dense Affective Understanding

no code implementations18 Jun 2021 Baoming Yan, Lin Wang, Ke Gao, Bo Gao, Xiao Liu, Chao Ban, Jiang Yang, Xiaobo Li

Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation.

A Self-supervised Method for Entity Alignment

1 code implementation17 Jun 2021 Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang

We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs.

Contrastive Learning Entity Alignment +2

3rd Place Solution for Short-video Face Parsing Challenge

no code implementations14 Jun 2021 Xiao Liu, XiaoFei Si, Jiangtao Xie

Benefiting from the edge information and edge attention loss, the proposed EANet achieves 86. 16\% accuracy in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the third place.

Face Parsing

Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

1 code implementation28 Apr 2021 Manyu Zhu, Dongliang He, Xin Li, Chao Li, Fu Li, Xiao Liu, Errui Ding, Zhaoxiang Zhang

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.

Image Inpainting valid

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

9 code implementations ACL 2022 Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang

On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1. 25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.

Ranked #4 on Language Modelling on WikiText-103 (using extra training data)

Abstractive Text Summarization Classification +4

GPT Understands, Too

7 code implementations18 Mar 2021 Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, Jie Tang

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU).

Knowledge Probing Language Modelling +2

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser

1 code implementation18 Mar 2021 Yue Cao, Xiaohe Wu, Shuran Qi, Xiao Liu, Zhongqin Wu, WangMeng Zuo

To begin with, the pre-trained denoiser is used to generate the pseudo clean images for the test images.


Understanding WeChat User Preferences and "Wow" Diffusion

1 code implementation4 Mar 2021 Fanjin Zhang, Jie Tang, Xueyi Liu, Zhenyu Hou, Yuxiao Dong, Jing Zhang, Xiao Liu, Ruobing Xie, Kai Zhuang, Xu Zhang, Leyu Lin, Philip S. Yu

"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.

Graph Representation Learning Social and Information Networks

OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services

1 code implementation3 Mar 2021 Xiao Liu, Da Yin, Jingnan Zheng, Xingjian Zhang, Peng Zhang, Hongxia Yang, Yuxiao Dong, Jie Tang

Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools.

Language Modelling Link Prediction