Search Results for author:
Found 46 papers, 17 papers with code
Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN
In this paper, we performed a thorough study on the effect of incorporating BBBM into deep generative models.
Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Content
In this paper, we propose a novel lightweight network called Coding Prior-Guided Super-Resolution (CPGSR) to address the SR challenges in compressed game video content.
TPOT: Topology Preserving Optimal Transport in Retinal Fundus Image Enhancement
Retinal fundus photography enhancement is important for diagnosing and monitoring retinal diseases.
Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models
To this end, we explore the notion of Large Language Models (LLMs) and model the first query when making inference about the follow-ups (based on the ASR-decoded text), via prompting of a pretrained LLM, or by adapting a binary classifier on top of the LLM.
EVOLvE: Evaluating and Optimizing LLMs For Exploration
In this work, we measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.
Supervised Multi-Modal Fission Learning
Learning from multimodal datasets can leverage complementary information and improve performance in prediction tasks.
Training Language Models to Self-Correct via Reinforcement Learning
In particular, we observe that training via SFT falls prey to either a distribution mismatch between mistakes made by the data-collection policy and the model's own responses, or to behavior collapse, where learning implicitly prefers only a certain mode of correction behavior that is often not effective at self-correction on test problems.
CUNSB-RFIE: Context-aware Unpaired Neural Schr"{o}dinger Bridge in Retinal Fundus Image Enhancement
In this work, we leverage the SB framework to propose an image-to-image translation pipeline for retinal image enhancement.
OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure
It searches the optimal tree structure that maximizes the mathematical expectation of the acceptance length in each decoding step.
Demonstration Augmentation for Zero-shot In-context Learning
Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates.
OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning
Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities. However, their massive number of parameters leads to high deployment requirements and incurs significant inference costs, which impedes their practical applications.
VISION2UI: A Real-World Dataset with Layout for Code Generation from UI Designs
Automatically generating UI code from webpage design visions can significantly alleviate the burden of developers, enabling beginner developers or designers to directly generate Web pages from design diagrams.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
This paper addresses the prevalent issue of label shift in an online setting with missing labels, where data distributions change over time and obtaining timely labels is challenging.
KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs
Large Language Models (LLMs) might hallucinate facts, while curated Knowledge Graph (KGs) are typically factually reliable especially with domain-specific knowledge.
A Novel Hybrid Ordinal Learning Model with Health Care Application
This situation is quite common in health care datasets due to limitations of the diagnostic instrument, sparse clinical visits, or/and patient dropout.
Ordinal Classification with Distance Regularization for Robust Brain Age Prediction
However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects.
Ranked #1 on
Ordinal Classification
on OASIS+NACC+ICBM+ABIDE+IXI
Leveraging Large Language Models for Exploiting ASR Uncertainty
While large language models excel in a variety of natural language processing (NLP) tasks, to perform well on spoken language understanding (SLU) tasks, they must either rely on off-the-shelf automatic speech recognition (ASR) systems for transcription, or be equipped with an in-built speech modality.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Intensity-free Convolutional Temporal Point Process: Incorporating Local and Global Event Contexts
Popular convolutional neural networks, which are designated for local context capturing, have never been applied to TPP modelling due to their incapability of modelling in continuous time.
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models.
Long-Term Value of Exploration: Measurements, Findings and Algorithms
We conduct live experiments on one of the largest short-form video recommendation platforms that serves billions of users to validate the new experiment designs, quantify the long-term values of exploration, and to verify the effectiveness of the adopted neural linear bandit algorithm for exploration.
Test-Time Adaptation with Perturbation Consistency Learning
Accordingly, in this paper, we propose perturbation consistency learning (PCL), a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts.
A Surface-Based Federated Chow Test Model for Integrating APOE Status, Tau Deposition Measure, and Hippocampal Surface Morphometry
Objective: To build a surface-based model to 1) detect differences between APOE subgroups in patterns of tau deposition and hippocampal atrophy, and 2) use the extracted surface-based features to predict cognitive decline.
Decision Support System for Chronic Diseases Based on Drug-Drug Interactions
Many patients with chronic diseases resort to multiple medications to relieve various symptoms, which raises concerns about the safety of multiple medication use, as severe drug-drug antagonism can lead to serious adverse effects or even death.
Data-Driven Offline Decision-Making via Invariant Representation Learning
The goal in offline data-driven decision-making is synthesize decisions that optimize a black-box utility function, using a previously-collected static dataset, with no active interaction.
Improved Prediction of Beta-Amyloid and Tau Burden Using Hippocampal Surface Multivariate Morphometry Statistics and Sparse Coding
Experimental results suggest that amyloid/tau measurements predicted with our PASCP-MP representations are closer to the real values than the measures derived from other approaches, such as hippocampal surface area, volume, and shape morphometry features based on spherical harmonics (SPHARM).
Greykite: Deploying Flexible Forecasting at Scale at LinkedIn
We present Greykite, an open-source Python library for forecasting that has been deployed on over twenty use cases at LinkedIn.
Offline RL for Natural Language Generation with Implicit Language Q Learning
Large language models distill broad knowledge from text corpora.
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control.
Deep residual inception encoder-decoder network for amyloid PET harmonization
Multiple positron emission tomography (PET) tracers are available for amyloid imaging, posing a significant challenge to consensus interpretation and quantitative analysis.
Predicting Tau Accumulation in Cerebral Cortex with Multivariate MRI Morphometry Measurements, Sparse Coding, and Correntropy
We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
Tianshou: a Highly Modularized Deep Reinforcement Learning Library
In this paper, we present Tianshou, a highly modularized Python library for deep reinforcement learning (DRL) that uses PyTorch as its backend.
Online Adaptation to Label Distribution Shift
Machine learning models often encounter distribution shifts when deployed in the real world.
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
Human language understanding operates at multiple levels of granularity (e. g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined.
Optimizing Rankings for Recommendation in Matching Markets
Based on the success of recommender systems in e-commerce, there is growing interest in their use in matching markets (e. g., labor).
Game-based Pricing and Task Offloading in Mobile Edge Computing Enabled Edge-Cloud Systems
In this paper, we formulate a distributed mechanism to analyze the interaction between OSPs and IoT MDs in the MEC enabled edge-cloud system by appling multi-leader multi-follower two-tier Stackelberg game theory.
Edge-computing
Computer Science and Game Theory
Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition
With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.
Off-policy Bandits with Deficient Support
Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e. g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data.
Accurate Tumor Tissue Region Detection with Accelerated Deep Convolutional Neural Networks
Our approach was approximately 100 times faster than the original DCNN approach while simultaneously preserving high accuracy and precision.
Adaptive Estimator Selection for Off-Policy Evaluation
We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings.
Developing an Unsupervised Real-time Anomaly Detection Scheme for Time Series with Multi-seasonality
In light of this, we have developed a prediction-driven, unsupervised anomaly detection scheme, which adopts a backbone model combining the decomposition and the inference of time series data.
Model Adaptation via Model Interpolation and Boosting for Web Search Ranking
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm.
Doubly robust off-policy evaluation with shrinkage
We propose a new framework for designing estimators for off-policy evaluation in contextual bandits.
CAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning
In addition, it is sub-differentiable such that it can be used for learning, unlike the SWITCH estimator.
A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification
In this study, a multi-task deep neural network is proposed for skin lesion analysis.
