Search Results for author:
Found 84 papers, 27 papers with code
RiskLabs: Predicting Financial Risk Using Large Language Model Based on Multi-Sources Data
Through comparative experiments, we demonstrate how different data sources contribute to financial risk assessment and discuss the critical role of LLMs in this context.
Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers
To this end, in this paper, we present a thorough review and provide a unified perspective to summarize the recent progress as well as emerging trends in multilingual large language models (MLLMs) literature.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Sparse and Faithful Explanations Without Sparse Models
In the loan denial example above, the SEV is 1 because only one factor is needed to explain why the loan was denied.
Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects
To enrich the literature of this domain and provide a sound basis for its future development, in this paper, we present a broad review of recent advances for fine-grained analysis in ZSL.
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences.
DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration
We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth.
Investigate The ESG Score Methodology
Whether the Refinitiv provide a reliable and trusted methodology in the process of aggregating 10 category scores to overall score?
FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
Addressing this, we introduce \textsc{FinMem}, a novel LLM-based agent framework devised for financial decision-making.
TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance
In financial trading contexts, LLMs serve as the decision core for trading agents, leveraging their layered memory system to integrate multi-source historical actions and market insights.
Attenuation and Loss of Spatial Coherence Modeling for Atmospheric Turbulence in Terahertz UAV MIMO Channels
In this paper, the attenuation and loss of spatial coherence for atmospheric turbulence are modeled in THz UAV MIMO channels.
CLEVA: Chinese Language Models EVAluation Platform
With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue.
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadvertently be exposed in the target domain.
Zero-Shot Learning by Harnessing Adversarial Samples
To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS).
Scintillation and Attenuation Modelling of Atmospheric Turbulence for Terahertz UAV Channels
Terahertz (THz) wireless communications have the potential to realize ultra-high-speed and secure data transfer with miniaturized devices for unmanned aerial vehicle (UAV) communications.
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e. g., multiple 2D slices of a CT scan for a patient).
Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?
Missing values are a fundamental problem in data science.
Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
In real applications, interaction between machine learning models and domain experts is critical; however, the classical machine learning paradigm that usually produces only a single model does not facilitate such interaction.
Deep Seam Prediction for Image Stitching Based on Selection Consistency Loss
To our knowledge, the proposed DSeam is the first deep learning based seam prediction method for image stitching.
On the Structural Generalization in Text-to-SQL
Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases.
Risk-Averse MDPs under Reward Ambiguity
We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity.
TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualization
Given thousands of equally accurate machine learning (ML) models, how can users choose among them?
Exploring the Whole Rashomon Set of Sparse Decision Trees
We show three applications of the Rashomon set: 1) it can be used to study variable importance for the set of almost-optimal trees (as opposed to a single tree), 2) the Rashomon set for accuracy enables enumeration of the Rashomon sets for balanced accuracy and F1-score, and 3) the Rashomon set for a full dataset can be used to produce Rashomon sets constructed with only subsets of the data set.
OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue
The second phase is to fine-tune the pretrained model on the TOD data.
THz ISAC: A Physical-Layer Perspective of Terahertz Integrated Sensing and Communication
In this article, challenges from THz channel and transceiver perspectives, as well as difficulties of ISAC are elaborated.
Profiling Television Watching Behaviour Using Bayesian Hierarchical Joint Models for Time-to-Event and Count Data
The model drastically reduces the dimensionality of the data from thousands of observations per customer to 11 customer-level parameter estimates and random effects.
Federated Zero-Shot Learning for Visual Recognition
We identify two key challenges in our FedZSL protocol: 1) the trained models are prone to be biased to the locally observed classes, thus failing to generalize to the unseen classes and/or seen classes appeared on other devices; 2) as each category in the training data comes from a single source, the central model is highly vulnerable to model replacement (backdoor) attacks.
Improving Multi-Interest Network with Stable Learning
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems.
GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning
To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction
When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
In this work, we aim to build a unified dialogue foundation model (DFM) which can be used to solve massive diverse dialogue tasks.
SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation
Experimental results provide evidence that our method can discover multiple concepts within a single image and outperforms state-of-the-art unsupervised methods on complex datasets such as Cityscapes and COCO-Stuff.
UniDU: Towards A Unified Generative Dialogue Understanding Framework
With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU).
SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.
Beam Training and Alignment for RIS-Assisted Millimeter Wave Systems:State of the Art and Beyond
The deployment of RIS, however, complicates the system architecture and poses a significant challenge for beam training (BT)/ beam alignment (BA), a process that is required to establish a reliable link between the transmitter and the receiver.
DFT-Spread Orthogonal Time Frequency Space System with Superimposed Pilots for Terahertz Integrated Sensing and Communication
Moreover, the effectiveness of the iterative method for data detection aided by superimposed pilots in DFT-s-OTFS systems is validated by the simulations and the bit error rate performance is not degraded by the Doppler effects.
Hyper-relationship Learning Network for Scene Graph Generation
As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships.
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers
Empirically, we show that existing backdoor attacks in malware classifiers are still detectable by recent defenses such as MNTD.
SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.
Ranked #1 on
Point Cloud Registration
on FP-O-H
Distinguishing Unseen From Seen for Generalized Zero-Shot Learning
In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories.
DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration
In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration.
Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU.
How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems.
Domain Adaptive Semantic Segmentation without Source Data
To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore.
Adaptive Feedforward Reference Design for Active Vibration Rejection in Multi-Actuator Hard Disk Drives
In December 2017, Seagate unveiled the Multi Actuator Technology to double the data performance of the future generation hard disk drives (HDD).
Data-Driven Strictly Positive Real System Identification with prior System Knowledge
Strictly Positive Real (SPR) transfer functions arise in many areas of engineering like passivity theory in circuit analysis and adaptive control to name a few.
Sensing Integrated DFT-Spread OFDM Waveform and Deep Learning-powered Receiver Design for Terahertz Integrated Sensing and Communication Systems
One step forward, THz integrated sensing and communication (ISAC) system can realize both unprecedented data rates and millimeter-level accurate sensing.
System Identification in Multi-Actuator Hard Disk Drives with Colored Noises using Observer/Kalman Filter Identification (OKID) Framework
Multi Actuator Technology in Hard Disk drives (HDDs) equips drives with two dual stage actuators (DSA) each comprising of a voice coil motor (VCM) actuator and a piezoelectric micro actuator (MA) operating on the same pivot point.
A Sparsity Algorithm with Applications to Corporate Credit Rating
We apply the sparsity algorithm to provide a simple suggestion to publicly traded companies in order to improve their credit ratings.
Mitigating Generation Shifts for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e. g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training.
CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation
Existing visually-aware models make use of the visual features as a separate collaborative signal similarly to other features to directly predict the user's preference without considering a potential bias, which gives rise to a visually biased recommendation.
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
A dual learning approach is also proposed for the utterance rewrite model to address the data sparsity problem.
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task.
Bring Your Own Codegen to Deep Learning Compiler
Deep neural networks (DNNs) have been ubiquitously applied in many applications, and accelerators are emerged as an enabler to support the fast and efficient inference tasks of these applications.
Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning
In addition to using the conditional GAN to generate class balanced supplementary training data, an innovative ensemble learning loss function ensuring each discriminator makes up for the deficiencies of the others is designed to overcome the class imbalanced problem, and an active learning algorithm is introduced to significantly reduce the cost of labeling real-world data.
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query.
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting.
Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences
We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA).
Semantics Disentangling for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes.
Continuous Copy-Paste for One-Stage Multi-Object Tracking and Segmentation
Current one-step multi-object tracking and segmentation (MOTS) methods lag behind recent two-step methods.
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.
Frequency Separation based Adaptive Feedforward Control for Rejecting Wideband Vibration with Application to Hard Disk Drives
Starting from the first region, the feedforward control parameters are learned simultaneously with the low order plant model in the same region and then moves to the next region until all the regions are performed.
Structured Hierarchical Dialogue Policy with Graph Neural Networks
A novel ComNet is proposed to model the structure of a hierarchical agent.
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e. g., hotel booking).
Deep Reinforcement Learning for On-line Dialogue State Tracking
To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems.
Dual Learning for Dialogue State Tracking
In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history.
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history.
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
A voting strategy averages the probability distributions output from the classifiers and, given that some patches are more discriminative than others, a discrimination-based attention mechanism helps to weight each patch accordingly.
Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry
We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA).
Neural Graph Matching Networks for Chinese Short Text Matching
Chinese short text matching usually employs word sequences rather than character sequences to get better performance.
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks
We also adopt graph attention networks with higher-order neighborhood information to encode the rich structure in AMR graphs.
Fully Automated 3D Segmentation of MR-Imaged Calf Muscle Compartments: Neighborhood Relationship Enhanced Fully Convolutional Network
Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction.
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
When modeling simple and complex sentences with autoencoders, we introduce different types of noise into the training process.
Concept Whitening for Interpretable Image Recognition
What does a neural network encode about a concept as we traverse through the layers?
Time-aware Gradient Attack on Dynamic Network Link Prediction
In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).
GLA-Net: An Attention Network with Guided Loss for Mismatch Removal
To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly.
CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
Thus, a multi-modal cycle-consistency loss between the synthesized semantic representations and the ground truth can be learned and leveraged to enforce the generated semantic features to approximate to the real distribution in semantic space.
Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Joint Active and Passive Precoding Design
In this framework, we study joint active and passive precoding design for IRS-assisted mmWave systems, where multiple IRSs are deployed to assist the data transmission from a base station (BS) to a single-antenna receiver.
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
Experiments show that AgentGraph models significantly outperform traditional reinforcement learning approaches on most of the 18 tasks of the PyDial benchmark.
Supervised and Semi-Supervised Deep Neural Networks for CSI-Based Authentication
In addition, we propose to use the convolutional recurrent neural network (CRNN)---a combination of the CNN and the RNN---to learn local and contextual information in CSI for user authentication.
Adversarial Feature Matching for Text Generation
We propose a framework for generating realistic text via adversarial training.
Low-Rank Tensor Decomposition-Aided Channel Estimation for Millimeter Wave MIMO-OFDM Systems
Different from most existing studies that are concerned with narrowband channels, we consider estimation of wideband mmWave channels with frequency selectivity, which is more appropriate for mmWave MIMO-OFDM systems.
Information Theory Information Theory
