Search Results for author:
Found 110 papers, 45 papers with code
Enhancing Self-Attention with Knowledge-Assisted Attention Maps
Large-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing.
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.
BeamSearchQA: Large Language Models are Strong Zero-Shot QA Solver
However, there are cases where answering a question requires implicit knowledge that is not directly retrievable from the question itself.
RSRM: Reinforcement Symbolic Regression Machine
Biding of these modules yields the state-of-the-art performance of RSRM in symbolic regression as demonstrated by multiple sets of benchmark examples.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval
Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Completion to recover masked semantics information.
Physics-informed neural network for seismic wave inversion in layered semi-infinite domain
In this paper, we present a PINN framework for seismic wave inversion in layered (1D) semi-infinite domain.
Attention-guided Multi-step Fusion: A Hierarchical Fusion Network for Multimodal Recommendation
The main idea of multimodal recommendation is the rational utilization of the item's multimodal information to improve the recommendation performance.
Safety Assessment of Chinese Large Language Models
To further promote the safe deployment of LLMs, we develop a Chinese LLM safety assessment benchmark.
Latent Semantic Diffusion-based Channel Adaptive De-Noising SemCom for Future 6G Systems
Upon the designed DNSC architecture, we further combine adversarial learning, variational autoencoder, and diffusion model to propose the Latent Diffusion DNSC (Latent-Diff DNSC) scheme to realize intelligent online de-noising.
IRGen: Generative Modeling for Image Retrieval
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored.
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization.
AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks
Integrating SAM with adaptive learning rate and momentum acceleration, dubbed AdaSAM, has already been explored empirically to train large-scale deep neural networks without theoretical guarantee due to the triple difficulties in analyzing the coupled perturbation step, adaptive learning rate and momentum step.
Neural Laplace Control for Continuous-time Delayed Systems
Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays.
Membership Inference Attacks against Synthetic Data through Overfitting Detection
In this work we argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution.
Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey
With the development of artificial intelligence, dialogue systems have been endowed with amazing chit-chat capabilities, and there is widespread interest and discussion about whether the generated contents are socially beneficial.
Laplacian ICP for Progressive Registration of 3D Human Head Meshes
We present a progressive 3D registration framework that is a highly-efficient variant of classical non-rigid Iterative Closest Points (N-ICP).
Accurate Gaze Estimation using an Active-gaze Morphable Model
Rather than regressing gaze direction directly from images, we show that adding a 3D shape model can: i) improve gaze estimation accuracy, ii) perform well with lower resolution inputs and iii) provide a richer understanding of the eye-region and its constituent gaze system.
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems.
PAL: Persona-Augmented Emotional Support Conversation Generation
As previous studies have demonstrated that seekers' persona is an important factor for effective support, we investigate whether there are benefits to modeling such information in dialogue models for support.
LEAD: Liberal Feature-based Distillation for Dense Retrieval
Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model.
SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection
LiDAR and camera are two essential sensors for 3D object detection in autonomous driving.
An Unsupervised Machine Learning Approach for Ground Motion Clustering and Selection
Clustering analysis of sequence data continues to address many applications in engineering design, aided with the rapid growth of machine learning in applied science.
Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation
In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing workers, or automatic generation to construct adversarial contexts that are likely to induce toxic generations.
Stare at What You See: Masked Image Modeling without Reconstruction
However, unlike the low-level features such as pixel values, we argue the features extracted by powerful teacher models already encode rich semantic correlation across regions in an intact image. This raises one question: is reconstruction necessary in Masked Image Modeling (MIM) with a teacher model?
SeismicNet: Physics-informed neural networks for seismic wave modeling in semi-infinite domain
In this paper, we present a novel physics-informed neural network (PINN) model for seismic wave modeling in semi-infinite domain without the nedd of labeled data.
Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty
The equation residuals are used to inform the spline learning in a Bayesian manner, where approximate Bayesian uncertainty calibration techniques are employed to approximate posterior distributions of the trainable parameters.
Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping
We validate our insight on a range of RL tasks and show its improvement over baselines: (1) In offline RL, the conservative exploitation leads to improved performance based on off-the-shelf algorithms; (2) In online continuous control, multiple value functions with different shifting constants can be used to tackle the exploration-exploitation dilemma for better sample efficiency; (3) In discrete control tasks, a negative reward shifting yields an improvement over the curiosity-based exploration method.
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language
Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality.
Pasture Intake Protects Against Commercial Diet-induced Lipopolysaccharide Production Facilitated by Gut Microbiota through Activating Intestinal Alkaline Phosphatase Enzyme in Meat Geese
In the gut microbiota analysis, meat geese supplemented with pasture demonstrated a significant reduction in microbial richness and diversity compared to IHF meat geese demonstrating antimicrobial, antioxidation, and anti-inflammatory ability of AGF system.
Multimodal foundation models are better simulators of the human brain
Further, from the perspective of neural encoding (based on our foundation model), we find that both visual and lingual encoders trained multimodally are more brain-like compared with unimodal ones.
Physics-informed Deep Super-resolution for Spatiotemporal Data
High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales.
CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation
Multimodal sentiment analysis and depression estimation are two important research topics that aim to predict human mental states using multimodal data.
Propagation Map Reconstruction via Interpolation Assisted Matrix Completion
This paper proposes to integrate interpolation with matrix completion to exploit both the spatial correlation and the potential low rank structure of the propagation map.
A Survey on Collaborative DNN Inference for Edge Intelligence
With the vigorous development of artificial intelligence (AI), the intelligent applications based on deep neural network (DNN) change people's lifestyles and the production efficiency.
DAUX: a Density-based Approach for Uncertainty eXplanations
Uncertainty quantification (UQ) is essential for creating trustworthy machine learning models.
A Neural Corpus Indexer for Document Retrieval
To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query.
Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search
The key concept is to interpret mathematical operations and system state variables by computational rules and symbols, establish symbolic reasoning of mathematical formulas via expression trees, and employ a Monte Carlo tree search (MCTS) agent to explore optimal expression trees based on measurement data.
Predicting parametric spatiotemporal dynamics by multi-resolution PDE structure-preserved deep learning
A more promising way is to leverage our prior physics knowledge in scientific deep learning models, known as physics-informed deep learning (PiDL).
Distilling Governing Laws and Source Input for Dynamical Systems from Videos
Distilling interpretable physical laws from videos has led to expanded interest in the computer vision community recently thanks to the advances in deep learning, but still remains a great challenge.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.
HousE: Knowledge Graph Embedding with Householder Parameterization
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties.
Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search
On the other hand, the capability of making high-CTR retrieval is optimized by learning to discriminate user's clicked ads from the entire corpus.
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm.
Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning
There have been growing interests in leveraging experimental measurements to discover the underlying partial differential equations (PDEs) that govern complex physical phenomena.
COLD: A Benchmark for Chinese Offensive Language Detection
To this end, we propose a benchmark --COLD for Chinese offensive language analysis, including a Chinese Offensive Language Dataset --COLDATASET and a baseline detector --COLDETECTOR which is trained on the dataset.
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.
Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference
Although it is well known that exploration plays a key role in Reinforcement Learning (RL), prevailing exploration strategies for continuous control tasks in RL are mainly based on naive isotropic Gaussian noise regardless of the causality relationship between action space and the task and consider all dimensions of actions equally important.
Towards artificial general intelligence via a multimodal foundation model
To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks.
Gophormer: Ego-Graph Transformer for Node Classification
Existing graph transformer models typically adopt fully-connected attention mechanism on the whole input graph and thus suffer from severe scalability issues and are intractable to train in data insufficient cases.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
Reward Shifting for Optimistic Exploration and Conservative Exploitation
We verify our insight on a range of tasks: (1) In offline RL, the conservative exploitation leads to improved learning performance based on off-the-shelf algorithms; (2) In online continuous control, multiple value functions with different shifting constants can be used to trade-off between exploration and exploitation thus improving learning efficiency; (3) In online RL with discrete action space, a negative reward shifting brings an improvement over the previous curiosity-based exploration method.
SPLID: Self-Imitation Policy Learning through Iterative Distillation
To this end, we propose a novel meta-algorithm Self-Imitation Policy Learning through Iterative Distillation (SPLID) which relies on the concept of $\delta$-distilled policy to iteratively level up the quality of the target data and agent mimics from the relabeled target data.
Localized Graph Collaborative Filtering
These methods often make recommendations based on the learned user and item embeddings.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
Safe Exploration by Solving Early Terminated MDP
Safe exploration is crucial for the real-world application of reinforcement learning (RL).
PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
Partial differential equations (PDEs) play a fundamental role in modeling and simulating problems across a wide range of disciplines.
Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos
Distilling analytical models from data has the potential to advance our understanding and prediction of nonlinear dynamics.
Encoding physics to learn reaction-diffusion processes
Modeling complex spatiotemporal dynamical systems, such as the reaction-diffusion processes, have largely relied on partial differential equations (PDEs).
PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support
In this paper, we propose PsyQA, a Chinese dataset of psychological health support in the form of question and answer pair.
Physics-informed Spline Learning for Nonlinear Dynamics Discovery
Dynamical systems are typically governed by a set of linear/nonlinear differential equations.
Hard Encoding of Physics for Learning Spatiotemporal Dynamics
Modeling nonlinear spatiotemporal dynamical systems has primarily relied on partial differential equations (PDEs).
AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search
Our motivation lies in incorporating the tremendous amount of unsupervised user behavior data from the historical search logs as the complementary graph to facilitate relevance modeling.
Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks
In this work, we propose to develop a structure-preserving progressive low-rank image completion (SPLIC) method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues.
A Supervised Segmentation Network for Hyperspectral Image Classification
To explore the spatial information for HSI classification, pixels with its adjacent pixels are usually directly cropped from hyperspectral data to form HSI cubes in CNN-based methods.
TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search
Text encoders based on C-DSSM or transformers have demonstrated strong performance in many Natural Language Processing (NLP) tasks.
Relic density of dark matter in the inert doublet model beyond leading order for the low mass region: 4. The Higgs resonance region
One-loop electroweak corrections to the annihilation cross-sections of dark matter in the Higgs resonance region of the inert doublet model (IDM) are investigated.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Relic density of dark matter in the inert doublet model beyond leading order for the low mass region: 2. Co-annihilation
We examine the relic density of the light mass dark matter region in the inert doublet model (IDM) when the dominant process is due to co-annihilation between the lightest neutral scalars of the model.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Relic density of dark matter in the inert doublet model beyond leading order for the low mass region: 3. Annihilation in 3-body final state
These are the dominant processes that enter the computation of the relic density for the low mass region of the inert doublet model (IDM) when annihilations to two on-shell vector bosons are closed.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Relic density of dark matter in the inert doublet model beyond leading order for the low mass region: 1. Renormalisation and constraints
The theoretical uncertainty brought by the scale dependence leads us to introduce a new criterion on the perturbativity of the IDM.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Self-Supervised Continuous Control without Policy Gradient
Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update.
On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
By contrast, this paper proves that LfO is almost equivalent to LfD in the deterministic robot environment, and more generally even in the robot environment with bounded randomness.
A Human Ear Reconstruction Autoencoder
The ear, as an important part of the human head, has received much less attention compared to the human face in the area of computer vision.
Extracting full-field subpixel structural displacements from videos via deep learning
This paper develops a deep learning framework based on convolutional neural networks (CNNs) that enable real-time extraction of full-field subpixel structural displacements from videos.
Incremental Bayesian tensor learning for structural monitoring data imputation and response forecasting
To address this fundamental issue, this paper presents an incremental Bayesian tensor learning method for reconstruction of spatiotemporal missing data in SHM and forecasting of structural response.
Non-local Policy Optimization via Diversity-regularized Collaborative Exploration
Conventional Reinforcement Learning (RL) algorithms usually have one single agent learning to solve the task independently.
Zeroth-Order Supervised Policy Improvement
However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample efficiency.
Physics informed deep learning for computational elastodynamics without labeled data
In this paper, we present a physics-informed neural network (PINN) with mixed-variable output to model elastodynamics problems without resort to labeled data, in which the I/BCs are hardly imposed.
MultiSpeech: Multi-Speaker Text to Speech with Transformer
Transformer-based text to speech (TTS) model (e. g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e. g., Tacotron~\cite{shen2018natural}) due to its parallel computation in training and/or inference.
Sparse representation for damage identification of structural systems
Specifically, an $\ell_2$ Bayesian learning method is firstly developed for updating the intact model and uncertainty quantification so as to set forward a baseline for damage detection.
Novel Policy Seeking with Constrained Optimization
In problem-solving, we humans can come up with multiple novel solutions to the same problem.
Physics-informed learning of governing equations from scarce data
Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines.
LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning
While pre-training and fine-tuning, e. g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online deployment in terms of both memory cost and inference speed, which hinders them from practical online usage.
Evolutionary Stochastic Policy Distillation
Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals.
Reciprocal Learning Networks for Human Trajectory Prediction
Based on this unique property, we develop a new approach, called reciprocal learning, for human trajectory prediction.
Existence of an equilibrium for pure exchange economy with fuzzy preferences
We set up a new fuzzy binary relation on the consumption set to evaluate the fuzzy preferences.
Computer Science and Game Theory
Physics-informed deep learning for incompressible laminar flows
Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems, whose basic concept is to embed physical laws to constrain/inform neural networks, with the need of less data for training a reliable model.
Policy Continuation with Hindsight Inverse Dynamics
This approach learns from Hindsight Inverse Dynamics based on Hindsight Experience Replay, enabling the learning process in a self-imitated manner and thus can be trained with supervised learning.
Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
The increasing amount of data in astronomy provides great challenges for machine learning research.
MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
Convolutional neural networks (CNNs) have been successfully applied to medical image classification, segmentation, and related tasks.
GetNet: Get Target Area for Image Pairing
Image pairing is an important research task in the field of computer vision.
Learning with Social Influence through Interior Policy Differentiation
In this work we model the social influence into the scheme of reinforcement learning, enabling the agents to learn both from the environment and from their peers.
Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets
In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets.
Adaptive Regularization of Labels
In addition, label regularization techniques such as label smoothing and label disturbance have also been proposed with the motivation of adding a stochastic perturbation to labels.
ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning
The state-of-art DNN structures involve high computation and great demand for memory storage which pose intensive challenge on DNN framework resources.
Computer-aided diagnosis in histopathological images of the endometrium using a convolutional neural network and attention mechanisms
In the ten-fold cross-validation process, the CADx approach, HIENet, achieved a 76. 91 $\pm$ 1. 17% (mean $\pm$ s. d.) classification accuracy for four classes of endometrial tissue, namely normal endometrium, endometrial polyp, endometrial hyperplasia, and endometrial adenocarcinoma.
Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion
Recently, G2P conversion is viewed as a sequence to sequence task and modeled by RNN or CNN based encoder-decoder framework.
Ranked #1 on
Text-To-Speech Synthesis
on CMUDict 0.7b
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Comparison Network for One-Shot Conditional Object Detection
A two-stage detector for OSCD is introduced to compare the extracted query and target features with the learnable metric to approach the optimized non-linear conditional probability.
Learning Fast Matching Models from Weak Annotations
The proposed training framework targets on mitigating both issues, by treating the stronger but undeployable models as annotators, and learning a deployable model from both human provided relevance labels and weakly annotated search log data.
IntRepair: Informed Repairing of Integer Overflows
Thus, in this paper, we propose a novel technique to provide automatic repairs of integer overflows in C source code.
Software Engineering
Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
The complexity of application scenarios, the redundancy of detection region, and the difficulty of dense ship detection are all the main obstacles that limit the successful operation of traditional methods in ship detection.
Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall.
Attention Incorporate Network: A network can adapt various data size
But how can we train the neural net model with different input size?
Progressive Neural Networks for Image Classification
The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images.
Hyperspectral Unmixing with Endmember Variability using Semi-supervised Partial Membership Latent Dirichlet Allocation
A semi-supervised Partial Membership Latent Dirichlet Allocation approach is developed for hyperspectral unmixing and endmember estimation while accounting for spectral variability and spatial information.
Spice up Your Chat: The Intentions and Sentiment Effects of Using Emoji
Second, from a perspective of message recipients, we further study the sentiment effects of emojis, as well as their duplications, on verbal messages.
Map-guided Hyperspectral Image Superpixel Segmentation Using Proportion Maps
A map-guided superpixel segmentation method for hyperspectral imagery is developed and introduced.
Degree of W-operator and Noncrossing Partition
We prove that W([n]) can be written as the sum of n!
Combinatorics
