Search Results for author:
Found 88 papers, 23 papers with code
Cross-Lingual Transfer with MAML on Trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+1
How does BERT process disfluency?
Analysis on sentence embeddings of disfluent and fluent sentence pairs reveals that the deeper the layer, the more similar their representation (exp2).
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
In conclusion, VidEgoThink reflects a research trend towards employing MLLMs for egocentric vision, akin to human capabilities, enabling active observation and interaction in the complex real-world environments.
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
In this paper, we study a new task of navigating to diverse target objects in a large number of scene types.
Ethereum Fraud Detection via Joint Transaction Language Model and Graph Representation Learning
To address these challenges, we propose TLMG4Eth that combines a transaction language model with graph-based methods to capture semantic, similarity, and structural features of transaction data in Ethereum.
The Role of Transformer Models in Advancing Blockchain Technology: A Systematic Survey
As blockchain technology rapidly evolves, the demand for enhanced efficiency, security, and scalability grows. Transformer models, as powerful deep learning architectures, have shown unprecedented potential in addressing various blockchain challenges.
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding.
High-Dimensional Fault Tolerance Testing of Highly Automated Vehicles Based on Low-Rank Models
Hence, Fault Injection (FI) testing is conducted by practitioners to evaluate the safety level of HAVs.
Assessment of Continuous-Time Transmission-Distribution-Interface Active and Reactive Flexibility for Flexible Distribution Networks
This model comprehensively considers the flexible devices in the FDN and the impact of uncertainty of photovoltaic power generation and load.
Local Clustering for Lung Cancer Image Classification via Sparse Solution Technique
The performance of our methods is shown to be very effective in classifying images.
Flow to Rare Events: An Application of Normalizing Flow in Temporal Importance Sampling for Automated Vehicle Validation
To solve it, we devise a method to represent, generate, and reweight the distribution of risky rare events.
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO).
LiteSearch: Efficacious Tree Search for LLM
Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.
Semi-supervised Regression Analysis with Model Misspecification and High-dimensional Data
In this paper, we present an inference framework for estimating regression coefficients in conditional mean models within both SSL and CSTL settings, while allowing for the misspecification of conditional mean models.
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from raw documents through self-teaching.
VideoTetris: Towards Compositional Text-to-Video Generation
Diffusion models have demonstrated great success in text-to-video (T2V) generation.
Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping
The Mixture-of-Expert (MoE) technique plays a crucial role in expanding the size of DNN model parameters.
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning.
Ranked #1 on
GSM8K
on GSM8K
AdaViPro: Region-based Adaptive Visual Prompt for Large-Scale Models Adapting
Recently, prompt-based methods have emerged as a new alternative `parameter-efficient fine-tuning' paradigm, which only fine-tunes a small number of additional parameters while keeping the original model frozen.
Federated Transfer Learning with Differential Privacy
By investigating the minimax rates and identifying the costs of privacy for these problems, we show that federated differential privacy is an intermediate privacy model between the well-established local and central models of differential privacy.
Self-Consistency Boosts Calibration for Math Reasoning
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.
Collaborative decoding of critical tokens for boosting factuality of large language models
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model.
Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
In this paper, we propose RealCompo, a new training-free and transferred-friendly text-to-image generation framework, which aims to leverage the respective advantages of text-to-image models and spatial-aware image diffusion models (e. g., layout, keypoints and segmentation maps) to enhance both realism and compositionality of the generated images.
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i. e. "hallucinations", even when they hold relevant knowledge.
ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images
This paper presents a novel zero-shot method for jointly denoising and enhancing real-word low-light images.
FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting
Additionally, adopting a frequency-based perspective can effectively mitigate the influence of noise within MTS data, which helps capture more genuine dependencies.
On semi-supervised estimation using exponential tilt mixture models
Consider a semi-supervised setting with a labeled dataset of binary responses and predictors and an unlabeled dataset with only the predictors.
Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?
Learning from free-text human feedback is essential for dialog systems, but annotated data is scarce and usually covers only a small fraction of error types known in conversational AI.
Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
While supervised federated learning approaches have enjoyed significant success, the domain of unsupervised federated learning remains relatively underexplored.
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning
Firstly we retrieve the relevant embedding from the knowledge graph by utilizing group relations in metadata and then integrate it with other modalities.
Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises.
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge.
EQ-Net: Elastic Quantization Neural Networks
In this paper, we explore a one-shot network quantization regime, named Elastic Quantization Neural Networks (EQ-Net), which aims to train a robust weight-sharing quantization supernet.
View while Moving: Efficient Video Recognition in Long-untrimmed Videos
To this end, inspired by human cognition, we propose a novel recognition paradigm of "View while Moving" for efficient long-untrimmed video recognition.
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation.
Improving Social Media Popularity Prediction with Multiple Post Dependencies
Social Media Popularity Prediction has drawn a lot of attention because of its profound impact on many different applications, such as recommendation systems and multimedia advertising.
Robust Fully-Asynchronous Methods for Distributed Training over General Architecture
Perfect synchronization in distributed machine learning problems is inefficient and even impossible due to the existence of latency, package losses and stragglers.
Designing Novel Cognitive Diagnosis Models via Evolutionary Multi-Objective Neural Architecture Search
Then, we propose multi-objective genetic programming (MOGP) to explore the NAS task's search space by maximizing model performance and interpretability.
RestGPT: Connecting Large Language Models with Real-World RESTful APIs
To address the practical challenges of tackling complex instructions, we propose RestGPT, which exploits the power of LLMs and conducts a coarse-to-fine online planning mechanism to enhance the abilities of task decomposition and API selection.
Coordinated Frequency-Constrained Stochastic Economic Dispatch for Integrated Transmission and Distribution System via Distributed Optimization
TPS and ADNs can deliver base point power bidirectionally and provide frequency regulation support bidirectionally, which extend the existing reserve assumption in ITD dispatch and enhance the operational security of the ITD system.
Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness
Assuming a known intrinsic dimension, we proposed a penalized empirical risk minimization method and a spectral method that are \textit{adaptive} to the similarity structure and \textit{robust} to outlier tasks.
Joint Chance-Constrained Economic Dispatch Involving Joint Optimization of Frequency-related Inverter Control and Regulation Reserve Allocation
The issues of uncertainty and frequency security could become significantly serious in power systems with the high penetration of volatile inverter-based renewables (IBRs).
Robust Unsupervised Multi-task and Transfer Learning on Gaussian Mixture Models
Unsupervised learning has been widely used in many real-world applications.
Deep Maxout Network Gaussian Process
Study of neural networks with infinite width is important for better understanding of the neural network in practical application.
Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP.
Semi-supervised Ranking for Object Image Blur Assessment
Based on this dataset, we propose a method to obtain the blur scores only with the pairwise rank labels as supervision.
Detecting Schizophrenia with 3D Structural Brain MRI Using Deep Learning
Our finding corroborates that schizophrenia is associated with widespread alterations in subcortical brain structure and the subcortical structural information provides prominent features in diagnostic classification.
Improving Across-Dataset Brain Tissue Segmentation Using Transformer
Transformers have demonstrated success in natural image segmentation and have recently been applied to 3D medical image segmentation tasks due to their ability to capture long-distance relationships in the input where the local receptive fields of CNNs struggle.
Neyman-Pearson Multi-class Classification via Cost-sensitive Learning
In this work, we tackle the multi-class NP problem by establishing a connection with the CS problem via strong duality and propose two algorithms.
Acceleration in Distributed Optimization under Similarity
In order to reduce the number of communications to reach a solution accuracy, we proposed a {\it preconditioned, accelerated} distributed method.
CCTrans: Simplifying and Improving Crowd Counting with Transformer
However, the transformer can model the global context easily.
Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation
Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each individual for complete epochs in individual evaluation.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Transfer Learning under High-dimensional Generalized Linear Models
In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data.
Principled Design of Translation, Scale, and Rotation Invariant Variation Operators for Metaheuristics
In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems.
Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging
In light of the recent success of data-driven approaches, we propose the novel future bridging NLG (FBNLG) concept for dialogue systems and simulators.
AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.
Evaluating the Effect of Longitudinal Dose and INR Data on Maintenance Warfarin Dose Predictions
Since a sequence of prior doses and INR better capture the variability in individual warfarin response, we hypothesized that longitudinal dose response data will improve maintenance dose predictions.
Meta-Learning with MAML on Trees
We show that TreeMAML improves the state of the art results for cross-lingual Natural Language Inference.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+2
RaSE: A Variable Screening Framework via Random Subspace Ensembles
Variable screening methods have been shown to be effective in dimension reduction under the ultra-high dimensional setting.
Imaging vibrations of locally gated, electromechanical few layer graphene resonators with a moving vacuum enclosure
With it we characterize the lowest frequency mode of a FLG resonator by measuring its frequency response as a function of position on the membrane.
Mesoscale and Nanoscale Physics
A Multilayer Correlated Topic Model
We proposed a novel multilayer correlated topic model (MCTM) to analyze how the main ideas inherit and vary between a document and its different segments, which helps understand an article's structure.
Model agnostic meta-learning on trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related, and sharing information between unrelated tasks might hurt performance.
DeepDyve: Dynamic Verification for Deep Neural Networks
The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much.
AMRNet: Chips Augmentation in Aerial Images Object Detection
Specifically, we propose a scale adaptive module, which dynamically adjusts chip size to balance object scale, narrowing scale variation in training.
CG-SENSE revisited: Results from the first ISMRM reproducibility challenge
The reference implementations were in good agreement, both visually and in terms of image similarity metrics.
Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.
RaSE: Random Subspace Ensemble Classification
In addition, we show that in a high-dimensional framework, the number of random subspaces needs to be very large to guarantee that a subspace covering signals is selected.
Downstream Model Design of Pre-trained Language Model for Relation Extraction Task
We believe that PLMs can also be used to solve the relation extraction problem, but it is necessary to establish a specially designed downstream task model or even loss function for dealing with complicated relations.
Ranked #3 on
Relation Extraction
on SemEval-2010 Task-8
Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks
This paper proposes a novel family of primal-dual-based distributed algorithms for smooth, convex, multi-agent optimization over networks that uses only gradient information and gossip communications.
Learning a Multi-Domain Curriculum for Neural Machine Translation
Most data selection research in machine translation focuses on improving a single domain.
Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images
Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist.
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models.
Machine Learning Allows Calibration Models to Predict Trace Element Concentration in Soil with Generalized LIBS Spectra
Machine learning has been used to develop the model.
THORS: An Efficient Approach for Making Classifiers Cost-sensitive
In this paper, we propose an effective THresholding method based on ORder Statistic, called THORS, to convert an arbitrary scoring-type classifier, which can induce a continuous cumulative distribution function of the score, into a cost-sensitive one.
Treat the system like a human student: Automatic naturalness evaluation of generated text without reference texts
The current most popular method for automatic Natural Language Generation (NLG) evaluation is comparing generated text with human-written reference sentences using a metrics system, which has drawbacks around reliability and scalability.
Aggression Identification and Multi Lingual Word Embeddings
The system presented here took part in the 2018 Trolling, Aggression and Cyberbullying shared task (Forest and Trees team) and uses a Gated Recurrent Neural Network architecture (Cho et al., 2014) in an attempt to assess whether combining pre-trained English and Hindi fastText (Mikolov et al., 2018) word embeddings as a representation of the sequence input would improve classification performance.
Aggression Identification
Multi-Label Text Classification
+1
ClusterNet: 3D Instance Segmentation in RGB-D Images
We show that our method generalizes well on real-world data achieving visually better segmentation results.
Resisting Large Data Variations via Introspective Transformation Network
Experimental results verify that our approach significantly improves the ability of deep networks to resist large variations between training and testing data and achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN, CIFAR-10 and miniImageNet.
Facebook sentiment: Reactions and Emojis
FB reactions (e. g. {``}Love{''} and {``}Angry{''}) indicate the readers{'} overall sentiment, against which we can investigate the types of emojis used the comments under different reaction profiles.
PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization
To address these issues, we have developed a MATLAB platform for evolutionary multi-objective optimization in this paper, called PlatEMO, which includes more than 50 multi-objective evolutionary algorithms and more than 100 multi-objective test problems, along with several widely used performance indicators.
DUEL: A Multi-lingual Multimodal Dialogue Corpus for Disfluency, Exclamations and Laughter
We present the DUEL corpus, consisting of 24 hours of natural, face-to-face, loosely task-directed dialogue in German, French and Mandarin Chinese.
