Search Results for author:
Found 77 papers, 32 papers with code
CMU’s IWSLT 2022 Dialect Speech Translation System
We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems.
Grid Monitoring and Protection with Continuous Point-on-Wave Measurements and Generative AI
Purpose This article presents a case for a next-generation grid monitoring and control system, leveraging recent advances in generative artificial intelligence (AI), machine learning, and statistical inference.
Forecasting Electricity Market Signals via Generative AI
This paper presents a generative artificial intelligence approach to probabilistic forecasting of electricity market signals, such as real-time locational marginal prices and area control error signals.
Multitask Multilingual Model Adaptation with Featurized Low-Rank Mixtures
By composing feature-specific parameters for each dataset, FLix can accommodate diverse dataset mixtures and generalize better to unseen datasets.
A Survey on Data Selection for Language Models
A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training.
Generative Probabilistic Time Series Forecasting and Applications in Grid Operations
Generative probabilistic forecasting produces future time series samples according to the conditional probability distribution given past time series observations.
Rate-Quality or Energy-Quality Pareto Fronts for Adaptive Video Streaming?
Adaptive video streaming is a key enabler for optimising the delivery of offline encoded video content.
Understanding the Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we propose that we can view an LM as deriving new conclusions by aggregating indirect reasoning paths seen at pre-training time.
Tweets to Citations: Unveiling the Impact of Social Media Influencers on AI Research Visibility
As the number of accepted papers at AI and ML conferences reaches into the thousands, it has become unclear how researchers access and read research publications.
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model
With the functional and characteristic similarity analysis, we introduce a novel gradient editing (GE) mechanism and verify its feasibility in generating transferable samples on various models.
MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome.
Comparative Study of Hardware and Software Power Measurements in Video Compression
The environmental impact of video streaming services has been discussed as part of the strategies towards sustainable information and communication technologies.
The Good, The Bad, and Why: Unveiling Emotions in Generative AI
Through extensive experiments involving language and multi-modal models on semantic understanding, logical reasoning, and generation tasks, we demonstrate that both textual and visual EmotionPrompt can boost the performance of AI models while EmotionAttack can hinder it.
Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition
Therefore, this paper proposes a Multi-task gEnerative mask dEcoupling face Recognition (MEER) network to jointly handle these two tasks, which can learn occlusionirrelevant and identity-related representation while achieving unmasked face synthesis.
SiRA: Sparse Mixture of Low Rank Adaptation
Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks.
Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization
Parameter-efficient fine-tuning (PEFT) using labeled task data can significantly improve the performance of large language models (LLMs) on the downstream task.
Continual Event Extraction with Semantic Confusion Rectification
We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting.
DANAA: Towards transferable attacks with double adversarial neuron attribution
While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments.
Guiding Language Model Math Reasoning with Planning Tokens
Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought reasoning.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning.
Multi-model fusion for Aerial Vision and Dialog Navigation based on human attention aids
Drones have been widely used in many areas of our daily lives.
UGC Quality Assessment: Exploring the Impact of Saliency in Deep Feature-Based Quality Assessment
Preliminary results indicate that high correlations are achieved by using only deep features while adding saliency is not always boosting the performance.
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks.
Non-parametric Probabilistic Time Series Forecasting via Innovations Representation
Probabilistic time series forecasting predicts the conditional probability distributions of the time series at a future time given past realizations.
mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations
Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings.
Evaluating and Modeling Attribution for Cross-Lingual Question Answering
Based on these models, we improve the attribution level of a cross-lingual question-answering system.
TheoremQA: A Theorem-driven Question Answering dataset
We evaluate a wide spectrum of 16 large language and code models with different prompting strategies like Chain-of-Thoughts and Program-of-Thoughts.
Ranked #1 on
Natural Questions
on TheoremQA
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
We also introduce a self-refinement module, which utilizes the symbolic solver's error messages to revise symbolic formalizations.
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
We evaluate commonly used models on the benchmark.
Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation
We conduct a series of experiments to compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process.
Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction
Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity.
Complexity and Enumeration in Models of Genome Rearrangement
In this paper, we examine the computational complexity of enumeration in certain genome rearrangement models.
Air-Ground Integrated Sensing and Communications: Opportunities and Challenges
The air-ground integrated sensing and communications (AG-ISAC) network, which consists of unmanned aerial vehicles (UAVs) and ground terrestrial networks, offers unique capabilities and demands special design techniques.
Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
A Survey of Face Recognition
Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks.
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
By combining PoT with self-consistency decoding, we can achieve SoTA performance on all math problem datasets and near-SoTA performance on financial datasets.
TW-BAG: Tensor-wise Brain-aware Gate Network for Inpainting Disrupted Diffusion Tensor Imaging
Diffusion Weighted Imaging (DWI) is an advanced imaging technique commonly used in neuroscience and neurological clinical research through a Diffusion Tensor Imaging (DTI) model.
Novelty Detection in Time Series via Weak Innovations Representation: A Deep Learning Approach
We consider novelty detection in time series with unknown and nonparametric probability structures.
A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models
Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022).
Semantic Preserving Adversarial Attack Generation with Autoencoder and Genetic Algorithm
Widely used deep learning models are found to have poor robustness.
Enhancing Document-level Relation Extraction by Entity Knowledge Injection
Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document.
Ranked #23 on
Relation Extraction
on DocRED
A Comprehensive Review on Deep Supervision: Theories and Applications
Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network.
Taxonomy of Benchmarks in Graph Representation Learning
Graph Neural Networks (GNNs) extend the success of neural networks to graph-structured data by accounting for their intrinsic geometry.
Causal Balancing for Domain Generalization
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations.
Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation
The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language.
Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond
With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets.
Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
Therefore, federated learning can be exploited to train a collaborative fault diagnosis model.
PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers
Building natural language inference (NLI) benchmarks that are both challenging for modern techniques, and free from shortcut biases is difficult.
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models.
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.
Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection
An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation.
RefBERT: Compressing BERT by Referencing to Pre-computed Representations
Differently, in this paper, we propose RefBERT to leverage the knowledge learned from the teacher, i. e., facilitating the pre-computed BERT representation on the reference sample and compressing BERT into a smaller student model.
Counterfactual Maximum Likelihood Estimation for Training Deep Networks
Although deep learning models have driven state-of-the-art performance on a wide array of tasks, they are prone to spurious correlations that should not be learned as predictive clues.
Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
With populations ageing, the number of people with dementia worldwide is expected to triple to 152 million by 2050.
Multi-view Subword Regularization
Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary.
Gradient-guided Loss Masking for Neural Machine Translation
To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts.
Meta Back-translation
Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data.
Fast Dynamics in a Model Metallic Glass-forming Material
We investigate the fast $\beta$- and Johari-Goldstein (JG) $\beta$-relaxation processes, along with the elastic scattering response of glass-forming (GF) liquids and the Boson peak, in a simulated Al-Sm GF material exhibiting a fragile-strong (FS) transition.
Materials Science
Dynamic Heterogeneity, Cooperative Motion, and Johari-Goldstein $β$-Relaxation in a Metallic Glass-Forming Material Exhibiting a Fragile to Strong Transition
We investigate the Johari-Goldstein (JG) $\beta$-relaxation process in a model metallic glass-forming (GF) material (Al90Sm10), previously studied extensively by both frequency-dependent mechanical measurements and simulation studies devoted to equilibrium properties, by molecular dynamics simulations based on validated and optimized interatomic potentials with the primary aim of better understanding the nature of this universal relaxation process from a dynamic heterogeneity (DH) perspective.
Materials Science
Modeling Disclosive Transparency in NLP Application Descriptions
Broader disclosive transparency$-$truth and clarity in communication regarding the function of AI systems$-$is widely considered desirable.
A Deep Learning Approach to Anomaly Sequence Detection for High-Resolution Monitoring of Power Systems
A deep learning approach is proposed to detect data and system anomalies using high-resolution continuous point-on-wave (CPOW) or phasor measurements.
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL).
Adaptive Subband Compression for Streaming of Continuous Point-on-Wave and PMU Data
A data compression system capable of providing real-time streaming of high-resolution continuous point-on-wave (CPOW) and phasor measurement unit (PMU) measurements is proposed.
Balancing Training for Multilingual Neural Machine Translation
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others.
A Probabilistic Formulation of Unsupervised Text Style Transfer
Across all style transfer tasks, our approach yields substantial gains over state-of-the-art non-generative baselines, including the state-of-the-art unsupervised machine translation techniques that our approach generalizes.
Optimizing Data Usage via Differentiable Rewards
To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems.
Improving Conditioning in Context-Aware Sequence to Sequence Models
Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence.
Ranked #6 on
Open-Domain Question Answering
on ELI5
Domain Differential Adaptation for Neural Machine Translation
We then use these learned domain differentials to adapt models for the target task accordingly.
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018).
compare-mt: A Tool for Holistic Comparison of Language Generation Systems
In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation.
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
Multilingual Neural Machine Translation With Soft Decoupled Encoding
Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages.
A Tree-based Decoder for Neural Machine Translation
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations.
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation
In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT).
XNMT: The eXtensible Neural Machine Translation Toolkit
In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing.
