Search Results for author:
Found 629 papers, 202 papers with code
PALM: Pre-training an Autoencoding\&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Abstractive Text Summarization
Conversational Response Generation
+8
Robust Graph Representation Learning via Neural Sparsification
Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection.
A Bayesian Topic Model for Human-Evaluated Interpretability
Given a nonparametric topic model, we can include weakly-supervised input using novel modifications to the nonparametric generative model.
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations
The emotion cause is a stimulus for human emotions.
No More Ambiguity in 360° Room Layout via Bi-Layout Estimation
A unique property of our Bi-Layout model is its ability to inherently detect ambiguous regions by comparing the two predictions.
Hierarchical Attention Models for Multi-Relational Graphs
BR-GCN models use bi-level attention to learn node embeddings through (1) node-level attention, and (2) relation-level attention.
DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness
Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models.
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general.
Efficient and Scalable Chinese Vector Font Generation via Component Composition
In this work, we first observe that most Chinese characters can be disassembled into frequently-reused components.
Image and Video Compression using Generative Sparse Representation with Fidelity Controls
Our framework can be conveniently used for both learned image compression (LIC) and learned video compression (LVC).
CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
Event Detection from Social Media for Epidemic Prediction
In our work, we pioneer exploiting Event Detection (ED) for better preparedness and early warnings of any upcoming epidemic by developing a framework to extract and analyze epidemic-related events from social media posts.
Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence
Neural rendering techniques have significantly advanced 3D human body modeling.
IterAlign: Iterative Constitutional Alignment of Large Language Models
Such a constitution discovery pipeline can be run iteratively and automatically to discover new constitutions that specifically target the alignment gaps in the current LLM.
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
This work presents FlashFace, a practical tool with which users can easily personalize their own photos on the fly by providing one or a few reference face images and a text prompt.
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments.
TablePuppet: A Generic Framework for Relational Federated Learning
In this paper, we formalize this problem as relational federated learning (RFL).
Human Detection in Realistic Through-the-Wall Environments using Raw Radar ADC Data and Parametric Neural Networks
The radar signal processing algorithm is one of the core components in through-wall radar human detection technology.
Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices
We design a memory-efficient management method to support memory-demanding inference in TEEs.
A Parallel Workflow for Polar Sea-Ice Classification using Auto-labeling of Sentinel-2 Imagery
Using the Antarctic's Ross Sea region as an example, the U-Net model trained on auto-labeled data achieves a classification accuracy of 98. 97% for auto-labeled training datasets when the thin clouds and shadows from the S2 images are filtered out.
Simplified Self-homodyne Coherent System Based on Alamouti Coding and Digital Subcarrier Multiplexing
Coherent technology inherent with more availabledegrees of freedom is deemed a competitive solution for nextgeneration ultra-high-speed short-reach optical interconnects. However, the fatal barriers to implementing the conventiona. coherent system in short-reach optical interconnect are the costfootprint, and power consumption.
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks.
How Powerful Potential of Attention on Image Restoration?
Our designs provide a closer look at the attention mechanism and reveal that some simple operations can significantly affect the model performance.
Adaptive Split Learning over Energy-Constrained Wireless Edge Networks
Then, a two-layer optimization method is proposed to solve the MIP problem.
QAQ: Quality Adaptive Quantization for LLM KV Cache
The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation.
Improving Event Definition Following For Zero-Shot Event Detection
We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types.
DECIDER: A Rule-Controllable Decoding Strategy for Language Generation by Imitating Dual-System Cognitive Theory
Lexicon-based constrained decoding approaches aim to control the meaning or style of the generated text through certain target concepts.
Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems
Real-world multi-agent systems are often dynamic and continuous, where the agents co-evolve and undergo changes in their trajectories and interactions over time.
Learning to Edit: Aligning LLMs with Knowledge Editing
Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention.
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models
In this study, we present EventRL, a reinforcement learning approach developed to enhance event extraction for large language models (LLMs).
Rethinking Human-like Translation Strategy: Integrating Drift-Diffusion Model with Large Language Models for Machine Translation
Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation.
Generalizing across Temporal Domains with Koopman Operators
By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains.
Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks
Our study thus provides first-hand insights into using ChatGPT to fulfill software engineering tasks with real-world developers and motivates the need for novel interaction mechanisms that help developers effectively work with large language models to achieve desired outcomes.
TinyLLM: Learning a Small Student from Multiple Large Language Models
To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small student LLM from multiple large teacher LLMs.
Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare
This paper examines the application of WiFi signals for real-world monitoring of daily activities in home healthcare scenarios.
Polyp-DAM: Polyp segmentation via depth anything model
In this paper, we unfold a new perspective on polyp segmentation modeling by leveraging the Depth Anything Model (DAM) to provide depth prior to polyp segmentation models.
Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detection
Single-domain generalized object detection aims to enhance a model's generalizability to multiple unseen target domains using only data from a single source domain during training.
A Survey on Self-Supervised Learning for Non-Sequential Tabular Data
Recently, SSL has been a new trend in exploring the representation learning capability in the realm of tabular data, which is more challenging due to not having explicit relations for learning descriptive representations.
Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation
The previous methods either failed to accurately fit the face region or lost the interactive generative ability with other existing concepts in T2I models.
Spatial Computing: Concept, Applications, Challenges and Future Directions
In this review, we also explored the potential challenges and limitations of spatial computing.
On the Emergence of Symmetrical Reality
Artificial intelligence (AI) has revolutionized human cognitive abilities and facilitated the development of new AI entities capable of interacting with humans in both physical and virtual environments.
Emulation-based Stabilization for Networked Control Systems with Stochastic Channels
Next, the proposed scheduling protocol is embedded into the closed-loop system, which leads to a stochastic hybrid model for NCSs with random packet dropouts.
Online Mean Estimation for Multi-frame Optical Fiber Signals On Highways
In the era of Big Data, prompt analysis and processing of data sets is critical.
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Within CivRealm, we provide interfaces for two typical agent types: tensor-based agents that focus on learning, and language-based agents that emphasize reasoning.
ConcEPT: Concept-Enhanced Pre-Training for Language Models
In this paper, we propose ConcEPT, which stands for Concept-Enhanced Pre-Training for language models, to infuse conceptual knowledge into PLMs.
Privacy-Preserving Sequential Recommendation with Collaborative Confusion
Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence.
When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks.
FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
XUAT-Copilot: Multi-Agent Collaborative System for Automated User Acceptance Testing with Large Language Model
In past years, we have been dedicated to automating user acceptance testing (UAT) process of WeChat Pay, one of the most influential mobile payment applications in China.
Hybrid Pooling and Convolutional Network for Improving Accuracy and Training Convergence Speed in Object Detection
This paper introduces HPC-Net, a high-precision and rapidly convergent object detection network.
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
To further investigate natural triggers, we propose a novel analysis-by-synthesis backdoor attack against face forgery detection models, which embeds natural triggers in the latent space.
Integer-Based Pattern Synthesis for Asymmetric Multi-Reflection RIS
This study delves into the radiation pattern synthesis of reconfigurable intelligent surfaces (RIS) / reflection metasurfaces.
DRL-Based Sidelobe Suppression for Multi-focus Reconfigurable Intelligent Surface
Reconfigurable intelligent surface (RIS) technology is receiving significant attention as a key enabling technology for 6G communications, with much attention given to coverage infill and wireless power transfer.
Contextual Reinforcement Learning for Offshore Wind Farm Bidding
We propose a framework for applying reinforcement learning to contextual two-stage stochastic optimization and apply this framework to the problem of energy market bidding of an off-shore wind farm.
ShuttleSHAP: A Turn-Based Feature Attribution Approach for Analyzing Forecasting Models in Badminton
Agent forecasting systems have been explored to investigate agent patterns and improve decision-making in various domains, e. g., pedestrian predictions and marketing bidding.
AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality.
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels.
Learning Dense Correspondence for NeRF-Based Face Reenactment
Therefore, we are inspired to ask: Can we learn the dense correspondence between different NeRF-based face representations without a 3D parametric model prior?
Dataset Distillation via Adversarial Prediction Matching
This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6. 5GB of GPU memory.
Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation
Recent domain adaptation study has shown that maximizing the sum of singular values of prediction results can simultaneously enhance their confidence (discriminability) and diversity.
Diffusion for Natural Image Matting
However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal.
Ranked #1 on
Image Matting
on Distinctions-646
Riemannian Complex Matrix Convolution Network for PolSAR Image Classification
To learn geometric structure of complex matrix, we propose a Riemannian complex matrix convolution network for PolSAR image classification in Riemannian space for the first time, which directly utilizes the complex matrix as the network input and defines the Riemannian operations to learn complex matrix's features.
The Selected-completely-at-random Complementary Label is a Practical Weak Supervision for Multi-class Classification
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong.
Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs
These models predominantly map visual information into language representation space, leveraging the vast knowledge and powerful text generation abilities of LLMs to produce multimodal instruction-following responses.
YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
In this work, we develop and release Yuan 2. 0, a series of large language models with parameters ranging from 2. 1 billion to 102. 6 billion.
RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection
This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Dynamic Fault Analysis in Substations Based on Knowledge Graphs
To address the challenge of identifying hidden danger in substations from unstructured text, a novel dynamic analysis method is proposed.
Generating Valid and Natural Adversarial Examples with Large Language Models
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks.
Joint Sensing and Communication Optimization in Target-Mounted STARS-Assisted Vehicular Networks: A MADRL Approach
Extensive experimental results confirm the effectiveness of our proposed MADRL framework in improving both sensing and communication performance through the utilization of target-mounted STARS.
Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach
Using COVID-19 as a testbed domain, our experiments demonstrate a significant alignment between the susceptibility scores estimated by our computational modeling and human judgments, confirming the effectiveness of this latent modeling approach.
A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering
The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA).
Robust Best-arm Identification in Linear Bandits
To this end, we present an instance-dependent lower bound for the robust best-arm identification problem with linear rewards.
Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning
Hence, we propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics.
Limits on the accuracy of contact inhibition of locomotion
However, in general, we find that cells have the ability to make reasonably reliable CIL decisions even for very narrow (micron-scale) contacts, even if the concentration of interfering ligands is ten times that of the correct ligands.
FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
To fill this research gap, in this paper, we propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark for LLMs.
Zero-Shot Medical Information Retrieval via Knowledge Graph Embedding
In the era of the Internet of Things (IoT), the retrieval of relevant medical information has become essential for efficient clinical decision-making.
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction.
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
This paper, instead, introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales.
F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns
We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns.
Learning under Label Proportions for Text Classification
We present one of the preliminary NLP works under the challenging setup of Learning from Label Proportions (LLP), where the data is provided in an aggregate form called bags and only the proportion of samples in each class as the ground truth.
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems.
Ranked #1 on
Visual Reasoning
on Bongard-OpenWorld
Mitigating Bias for Question Answering Models by Tracking Bias Influence
Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance by observing its influence on another instance.
Context-Enhanced Detector For Building Detection From Remote Sensing Images
Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy.
TANGO: Time-Reversal Latent GraphODE for Multi-Agent Dynamical Systems
Learning complex multi-agent system dynamics from data is crucial across many domains, such as in physical simulations and material modeling.
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation
First, FaceEncoder is used to obtain latent code by extracting features from the visual face information taken from the video source containing the face frame. Then, HyperConv, which weighting parameters are updated by HyperNet with the audio features as input, will modify the latent code to synchronize the lip movement with the audio.
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.
Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction
Information Extraction (IE) is an essential task in Natural Language Processing.
MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering
Few-shot question answering (QA) aims at achieving satisfactory results on machine question answering when only a few training samples are available.
PGraphDTA: Improving Drug Target Interaction Prediction using Protein Language Models and Contact Maps
Through extensive experimentation, we demonstrate that our proposed approaches outperform the baseline models considered in this study, presenting a compelling case for further development in this direction.
Ranked #1 on
on DAVIS-DTA
Know2BIO: A Comprehensive Dual-View Benchmark for Evolving Biomedical Knowledge Graphs
Knowledge graphs (KGs) have emerged as a powerful framework for representing and integrating complex biomedical information.
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
In this paper, we propose an interpretable and generalizable visual planning framework consisting of i) a novel Substitution-based Concept Learner (SCL) that abstracts visual inputs into disentangled concept representations, ii) symbol abstraction and reasoning that performs task planning via the self-learned symbols, and iii) a Visual Causal Transition model (ViCT) that grounds visual causal transitions to semantically similar real-world actions.
MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways
We present MIDDAG, an intuitive, interactive system that visualizes the information propagation paths on social media triggered by COVID-19-related news articles accompanied by comprehensive insights, including user/community susceptibility level, as well as events and popular opinions raised by the crowd while propagating the information.
Large Language Models Can Be Good Privacy Protection Learners
To address this challenge, we introduce Privacy Protection Language Models (PPLM), a novel paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding data privacy.
Improving Emotional Expression and Cohesion in Image-Based Playlist Description and Music Topics: A Continuous Parameterization Approach
Text generation in image-based platforms, particularly for music-related content, requires precise control over text styles and the incorporation of emotional expression.
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design.
Tradeoffs in concentration sensing in dynamic environments
However, when cells are in a environment that changes over time, past measurements may not reflect current conditions - creating a new source of error that trades off against noise in chemical sensing.
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
High-content stimulated Raman histology of human breast cancer
Here, we present a high-content stimulated Raman histology (HC-SRH) platform that provides both morphological and chemical information for cancer diagnosis based on un-stained breast tissues.
Neural Image Compression Using Masked Sparse Visual Representation
A set of semantic-class-dependent basis codebooks are learned, which are weighted combined to generate a rich latent feature for high-quality reconstruction.
Robust Backdoor Attacks on Object Detection in Real World
However, these models are vulnerable to backdoor attacks.
Unveiling Invariances via Neural Network Pruning
Invariance describes transformations that do not alter data's underlying semantics.
A DRL-based Reflection Enhancement Method for RIS-assisted Multi-receiver Communications
In reconfigurable intelligent surface (RIS)-assisted wireless communication systems, the pointing accuracy and intensity of reflections depend crucially on the 'profile,' representing the amplitude/phase state information of all elements in a RIS array.
Mean Field Game-based Waveform Precoding Design for Mobile Crowd Integrated Sensing, Communication, and Computation Systems
In this paper, we consider the environment sensing problem in the large-scale mobile crowd ISCC systems and propose an efficient waveform precoding design algorithm based on the mean field game~(MFG).
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
DALNet: A Rail Detection Network Based on Dynamic Anchor Line
In the paper, motivated by the anchor line-based lane detection methods, we propose a rail detection network called DALNet based on dynamic anchor line.
Multi-scale Target-Aware Framework for Constrained Image Splicing Detection and Localization
Additionally, in order to handle scale transformations, we introduce a multi-scale projection method, which can be readily integrated into our target-aware framework that enables the attention process to be conducted between tokens containing information of varying scales.
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface.
KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases
Large language models (LLMs) have demonstrated impressive impact in the field of natural language processing, but they still struggle with several issues regarding, such as completeness, timeliness, faithfulness and adaptability.
Artificial Intelligence for Web 3.0: A Comprehensive Survey
Then, we thoroughly analyze the current state of AI technology applications in the four layers of Web 3. 0 and offer some insights into its potential future development direction.
Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration
Specifically, our C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training scheme.
Routing Recovery for UAV Networks with Deliberate Attacks: A Reinforcement Learning based Approach
The unmanned aerial vehicle (UAV) network is popular these years due to its various applications.
From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement
Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images.
Unsupervised Decomposition Networks for Bias Field Correction in MR Image
Many retrospective algorithms were developed to facilitate the bias correction, to which the deep learning-based methods outperformed.
BotHawk: An Approach for Bots Detection in Open Source Software Projects
Identifying bot accounts and behavior is a challenging task in the OSS project.
Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services
Time series anomaly detection is crucial for industrial monitoring services that handle a large volume of data, aiming to ensure reliability and optimize system performance.
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations.
PanoPoint: Self-Supervised Feature Points Detection and Description for 360° Panorama
We introduce PanoPoint, the joint feature point detection and description applied to the nonlinear distortions and the multi-view geometry problems between 360deg panoramas.
Householder Projector for Unsupervised Latent Semantics Discovery
Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space.
Generalizing Graph ODE for Learning Complex System Dynamics across Environments
In practice, however, we might observe multiple systems that are generated across different environments, which differ in latent exogenous factors such as temperature and gravity.
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs
We propose Concept2Box, a novel approach that jointly embeds the two views of a KG using dual geometric representations.
Coordinating Supply, Demand, and Repair Resources for Optimal Postdisaster Operation of Interdependent Electric Power and Natural Gas Distribution Systems
In this paper, we focus on the interdependent electric power and natural gas distribution systems (IENDS) and propose a comprehensive "supply - demand - repair" strategy to help the IENDS tide over the emergency periods after disasters by coordinating various emergency resources.
AOG-LSTM: An adaptive attention neural network for visual storytelling
Moreover, the existing method of alleviating error accumulation based on replacing reference words does not take into account the different effects of each word.
Ranked #20 on
Visual Storytelling
on VIST
Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI
Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in brain and is widely used for brain disorder analysis. Previous studies propose to extract fMRI representations through diverse machine/deep learning methods for subsequent analysis.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
Shuffled Autoregression For Motion Interpolation
However, motion interpolation is a more complex problem that takes isolated poses (e. g., only one start pose and one end pose) as input.
Professional Basketball Player Behavior Synthesis via Planning with Diffusion
To accomplish reward-guided trajectory generation, conditional sampling is introduced to condition the diffusion model on the value function and conduct classifier-guided sampling.
Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation
Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available.
Can Directed Graph Neural Networks be Adversarially Robust?
This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs.
CAROM Air -- Vehicle Localization and Traffic Scene Reconstruction from Aerial Videos
Road traffic scene reconstruction from videos has been desirable by road safety regulators, city planners, researchers, and autonomous driving technology developers.
Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making
Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks.
TLNets: Transformation Learning Networks for long-range time-series prediction
Note that the FT and SVD blocks are capable of learning global information, while the Conv blocks focus on learning local information.
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies.
Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling
In this paper, we carefully design a new task called Multiple Definition Modeling (MDM) that pool together all contexts and definition of target words.
Lion: Adversarial Distillation of Proprietary Large Language Models
The practice of transferring knowledge from a sophisticated, proprietary large language model (LLM) to a compact, open-source LLM has garnered considerable attention.
Whisper-KDQ: A Lightweight Whisper via Guided Knowledge Distillation and Quantization for Efficient ASR
Due to the rapid development of computing hardware resources and the dramatic growth of data, pre-trained models in speech recognition, such as Whisper, have significantly improved the performance of speech recognition tasks.
Self-Supervised Learning for Point Clouds Data: A Survey
We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the pretexts' characteristics.
Sparsity-Aware Optimal Transport for Unsupervised Restoration Learning
Recent studies show that, without any prior model, the unsupervised restoration learning problem can be optimally formulated as an optimal transport (OT) problem, which has shown promising performance on denoising tasks to approach the performance of supervised methods.
Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy
We propose a binary stochastic learning algorithm that modifies all elementary neural network operations, by introducing (i) stochastic binarization of both the forwarding signals and the activation function derivatives, (ii) signed binarization of the backpropagating errors, and (iii) step-wised weight updates.
Bi-Level Attention Graph Neural Networks
Recent graph neural networks (GNNs) with the attention mechanism have historically been limited to small-scale homogeneous graphs (HoGs).
Dehazing-NeRF: Neural Radiance Fields from Hazy Images
Our method simulates the physical imaging process of hazy images using an atmospheric scattering model, and jointly learns the atmospheric scattering model and a clean NeRF model for both image dehazing and novel view synthesis.
Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation
An important topic in manipulation detection is the localization of the fake regions.
ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human
In this paper, we present ChatPLUG, a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format.
RRHF: Rank Responses to Align Language Models with Human Feedback without tears
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models.
Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge
Efficient automatic segmentation of multi-level (i. e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications.
InfluencerRank: Discovering Effective Influencers via Graph Convolutional Attentive Recurrent Neural Networks
In this paper, we propose InfluencerRank that ranks influencers by their effectiveness based on their posting behaviors and social relations over time.
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
PPG-based Heart Rate Estimation with Efficient Sensor Sampling and Learning Models
Moreover, our analysis showed that DT models with 10 to 20 input features usually have good accuracy, while are several magnitude smaller in model sizes and faster in inference time.
Efficient and Direct Inference of Heart Rate Variability using Both Signal Processing and Machine Learning
With this dataset, we developed HRV models that combine signal processing and ML to directly infer HRV.
W2KPE: Keyphrase Extraction with Word-Word Relation
This paper describes our submission to ICASSP 2023 MUG Challenge Track 4, Keyphrase Extraction, which aims to extract keyphrases most relevant to the conference theme from conference materials.
How well do Large Language Models perform in Arithmetic tasks?
Large language models have emerged abilities including chain-of-thought to answer math word problems step by step.
NLUT: Neural-based 3D Lookup Tables for Video Photorealistic Style Transfer
However, existing methods obtain stylized video sequences by performing frame-by-frame photorealistic style transfer, which is inefficient and does not ensure the temporal consistency of the stylized video.
RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused.
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model
Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions.
Weighted Sampling for Masked Language Modeling
Experiments on the Semantic Textual Similarity benchmark (STS) show that WSBERT significantly improves sentence embeddings over BERT.
LSR: A Light-Weight Super-Resolution Method
A light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed in this work.
DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining
Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations.
Theoretical Evaluation of the Capacity-Achieving Distribution for IM-DD Fiber-Optic Channels
For the IM-DD system under peak power constraint (PPC), a dynamic-assignment BA algorithm is applied to find the capacity-achieving distribution with minimum cardinality.
Designing a 3D-Aware StyleNeRF Encoder for Face Editing
For more flexible face manipulation, we then design a dual-branch StyleFlow module to transfer the StyleNeRF codes with disentangled geometry and texture flows.
Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability
We compare the performance of xGPR with the reported performance of various deep learning models on 20 benchmarks, including small molecule, protein sequence and tabular data.
Ranked #8 on
Formation Energy
on QM9
Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling
To alleviate this limitation, we propose Moleformer, a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them using rotational and translational invariant geometry-aware spatial encoding.
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement.
Ranked #1 on
Video Captioning
on MSR-VTT
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment.
From Plate to Prevention: A Dietary Nutrient-aided Platform for Health Promotion in Singapore
In this paper, we share our experience in addressing this issue and attaining medical-grade nutrient intake information to benefit Singaporeans in different aspects.
VQNet 2.0: A New Generation Machine Learning Framework that Unifies Classical and Quantum
Therefore, based on VQNet 1. 0, we further propose VQNet 2. 0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization.
Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction
We present Mask-then-Fill, a flexible and effective data augmentation framework for event extraction.
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions
However, most existing ensemble attacks depend on numerous substitute models to cover the vulnerable subspace of a target model.
Bidirectional Alignment for Domain Adaptive Detection with Transformers
We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance.
Joint Beamforming Design for Dual-Functional MIMO Radar and Communication Systems Guaranteeing Physical Layer Security
The dual-functional radar and communication (DFRC) technique constitutes a promising next-generation wireless solution, due to its benefits in terms of power consumption, physical hardware, and spectrum exploitation.
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation
Thus, recent studies concern about adversarial distillation (AD) that aims to inherit not only prediction accuracy but also adversarial robustness of a robust teacher model under the paradigm of robust optimization.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs
Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns.
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset.
Orthogonal SVD Covariance Conditioning and Latent Disentanglement
Extensive experiments on visual recognition demonstrate that our methods can simultaneously improve covariance conditioning and generalization.
A Generative Approach for Script Event Prediction via Contrastive Fine-tuning
First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well.
A Mobility-Aware Deep Learning Model for Long-Term COVID-19 Pandemic Prediction and Policy Impact Analysis
Hence, those models are unable to predict further future.
AGO: Boosting Mobile AI Inference Performance by Removing Constraints on Graph Optimization
Traditional deep learning compilers rely on heuristics for subgraph generation, which impose extra constraints on graph optimization, e. g., each subgraph can only contain at most one complex operator.
Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition
Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis.
Learning from Long-Tailed Noisy Data with Sample Selection and Balanced Loss
Specifically, we separate the noisy training data into clean labeled set and unlabeled set with sample selection, and train the deep neural network in a semi-supervised manner with a balanced loss based on model bias.
Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer
Once training is completed, EmoAug enriches expressions of emotional speech with different prosodic attributes, such as stress, rhythm and intensity, by feeding different styles into the paralinguistic encoder.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Introducing Semantics into Speech Encoders
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+10
Long bet will lose: demystifying seemingly fair gambling via two-armed Futurity bandit
No matter how much some gamblers occasionally win, as long as they continue to gamble, sooner or later they will lose more to the casino, which is the so-called long bet will lose.
Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series?
In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series.
Deep Factorization Model for Robust Recommendation
Recently, malevolent user hacking has become a huge problem for real-world companies.
Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset
To the best of our knowledge, it is currently the largest manually-annotated Chinese dataset for open event extraction.
SEVGGNet-LSTM: a fused deep learning model for ECG classification
This paper presents a fused deep learning algorithm for ECG classification.
Deep Latent Mixture Model for Recommendation
Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications.
Pronunciation Generation for Foreign Language Words in Intra-Sentential Code-Switching Speech Recognition
In this paper, we make use of limited code-switching data as driving materials and explore a shortcut to quickly develop intra-sentential code-switching recognition skill on the commissioned native language acoustic model, where we propose a data-driven method to make the seed lexicon which is used to train grapheme-to-phoneme model to predict mapping pronunciations for foreign language word in code-switching sentences.
Synthetic Data Supervised Salient Object Detection
In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model.
OSS Mentor A framework for improving developers contributions via deep reinforcement learning
In open source project governance, there has been a lot of concern about how to measure developers' contributions.
Robust Ellipse Fitting Based on Maximum Correntropy Criterion With Variable Center
For single ellipse fitting, we formulate a non-convex optimization problem to estimate the kernel bandwidth and center and divide it into two subproblems, each estimating one parameter.
ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations
Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware.
Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment
Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error.
Code Recommendation for Open Source Software Developers
In this paper, we formulate the novel problem of code recommendation, whose purpose is to predict the future contribution behaviors of developers given their interaction history, the semantic features of source code, and the hierarchical file structures of projects.
Exploiting Mixed Unlabeled Data for Detecting Samples of Seen and Unseen Out-of-Distribution Classes
We propose the Adaptive In-Out-aware Learning (AIOL) method, in which we employ the appropriate temperature to adaptively select potential ID and OOD samples from the mixed unlabeled data and consider the entropy over them for OOD detection.
Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values.
GENHOP: An Image Generation Method Based on Successive Subspace Learning
In the first module, it builds a sequence of high-to-low dimensional subspaces through a sequence of whitening processes, each of which contains samples of joint-spatial-spectral representation.
CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference
To this end, we develop an approach that can effectively take advantage of the sparsity of matrix operations in GCN inference to significantly reduce the computational overhead.
