Search Results for author:
Found 224 papers, 88 papers with code
An Analysis of WordNet’s Coverage of Gender Identity Using Twitter and The National Transgender Discrimination Survey
While gender identities in the Western world are typically regarded as binary, our previous work (Hicks et al., 2015) shows that there is more lexical variety of gender identity and the way people identify their gender.
MIRA: Medical Time Series Foundation Model for Real-World Health Data
To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting.
Learning to Select In-Context Demonstration Preferred by Large Language Model
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations.
Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
Time Series Foundation Models (TSFMs), which are pretrained on large-scale, cross-domain data and capable of zero-shot forecasting in new scenarios without further training, are increasingly adopted in real-world applications.
R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility.
R&D-Agent: Automating Data-Driven AI Solution Building Through LLM-Powered Automated Research, Development, and Evolution
Recent advances in AI and ML have transformed data science, yet increasing complexity and expertise requirements continue to hinder progress.
Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations
To fill the gaps, we present SDIFT, Sequential DIffusion in Functional Tucker space, a novel framework that generates full-field evolution of physical dynamics from irregular sparse observations.
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases.
TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation
Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more training data.
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
In evaluation, we propose new metrics to assess not only visual quality but also the action following capacity when generating new scenes, which is crucial for a world model.
Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings.
Chemistry-aware battery degradation prediction under simulated real-world cyclic protocols
Battery degradation is governed by complex and randomized cyclic conditions, yet existing modeling and prediction frameworks usually rely on rigid, unchanging protocols that fail to capture real-world dynamics.
Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data
Employing \textit{CoF}, we construct the \textit{ChartCoF} dataset, with 1. 4k complex reasoning Q\&A for fine-grained analysis and 50k Q\&A for reasoning enhancement.
Fast Autoregressive Video Generation with Diagonal Decoding
Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of tokens.
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelling
This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by 12. 52% on MSE and 6. 34% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size.
Functional Complexity-adaptive Temporal Tensor Decomposition
While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent factors, they still struggle with general tensor data with continuous indexes not only in the temporal mode but also in other modes, such as spatial coordinates in climate data.
Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models
Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabilities.
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
In this work, we introduce CADFusion, a framework that uses Large Language Models (LLMs) as the backbone and alternates between two training stages: the sequential learning (SL) stage and the visual feedback (VF) stage.
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications.
TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts
Time series generation models are crucial for applications like data augmentation and privacy preservation.
AR4D: Autoregressive 4D Generation from Monocular Videos
To avoid appearance drift introduced by autoregressive generation, we further incorporate a refinement stage based on a global deformation field and the geometry of each frame's 3D representation.
From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context.
OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations
In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by leveraging reanalysis data.
VidTwin: Video VAE with Decoupled Structure and Dynamics
Recent advancements in video autoencoders (Video AEs) have significantly improved the quality and efficiency of video generation.
The ELEVATE-AI LLMs Framework: An Evaluation Framework for Use of Large Language Models in HEOR: an ISPOR Working Group Report
The ELEVATE AI LLMs framework and checklist fill a critical gap in HEOR by offering structured guidance for evaluating LLM-assisted research.
AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models
Third, we introduce a proofreading strategy that allows LLMs to incrementally correct the errors in the initial design, akin to human designers who iteratively check and adjust the initial topology design to ensure accuracy.
VidTok: A Versatile and Open-Source Video Tokenizer
Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations.
InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
Then, we employ a lightweight trainable module that automatically preserves invariant semantic information and uses it to guide the diffusion model's sampling process toward unbiased outcomes simultaneously.
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
This reformulation enables the use of first-order optimization algorithms in calculating the backward pass gradients, allowing our framework to potentially utilize any state-of-the-art solver.
Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models
This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients.
FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens.
ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons.
Pre-trained Molecular Language Models with Random Functional Group Masking
Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science.
Generative AI in Health Economics and Outcomes Research: A Taxonomy of Key Definitions and Emerging Applications, an ISPOR Working Group Report
The article discusses strategies to improve the accuracy of these AI tools.
IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
Through this unified latent action space, IGOR enables knowledge transfer among large-scale robot and human activity data.
Diffusion Models in 3D Vision: A Survey
In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.
C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences.
FlashMask: Efficient and Rich Mask Extension of FlashAttention
In this paper, we propose FlashMask, an extension of FlashAttention that introduces a column-wise sparse representation of attention masks.
Environment Scan of Generative AI Infrastructure for Clinical and Translational Science
This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States.
Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)
Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries.
Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities
Training deep Convolutional Neural Networks (CNNs) presents unique challenges, including the pervasive issue of elimination singularities, consistent deactivation of nodes leading to degenerate manifolds within the loss landscape.
GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation
Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries.
WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models
Our work aims to advance the AI-based weather forecasting research towards a more application-focused and operation-ready approach.
Enhancing Cross-domain Pre-Trained Decision Transformers with Adaptive Attention
Although this cross-domain pre-training approach achieves superior performance compared to training from scratch in environments required short-term planning ability, the mechanisms by which pre-training benefits the fine-tuning phase remain unclear.
MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects.
Compositional 3D-aware Video Generation with LLM Director
Specifically, given an input textual prompt, our scheme consists of three stages: 1) We leverage LLM as the director to first decompose the complex query into several sub-prompts that indicate individual concepts within the video~(\textit{e. g.}, scene, objects, motions), then we let LLM to invoke pre-trained expert models to obtain corresponding 3D representations of concepts.
Collaborative Evolving Strategy for Automatic Data-Centric Development
By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges.
UF-HOBI at "Discharge Me!": A Hybrid Solution for Discharge Summary Generation Through Prompt-based Tuning of GatorTronGPT Models
This paper presents a hybrid solution for generating discharge summary sections as part of our participation in the "Discharge Me!"
Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned
While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge.
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.
Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents
This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements.
Video In-context Learning
In-context learning for vision data has been underexplored compared with that in natural language.
Generative AI for Health Technology Assessment: Opportunities, Challenges, and Policy Considerations
This review introduces the transformative potential of generative Artificial Intelligence (AI) and foundation models, including large language models (LLMs), for health technology assessment (HTA).
When Search Engine Services meet Large Language Models: Visions and Challenges
Combining Large Language Models (LLMs) with search engine services marks a significant shift in the field of services computing, opening up new possibilities to enhance how we search for and retrieve information, understand content, and interact with internet services.
Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement
Instead, we propose to disentangle the motion and appearance, and then generate them one by one with a speech-to-motion diffusion model and a motion-conditioned appearance generation model.
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved.
Graph Neural Network Enhanced Retrieval for Question Answering of LLMs
A graph neural network (GNN) is then leveraged to exploit the relationships between passages and improve the retrieval of supporting passages.
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models generate heatmaps, indicating the probability distribution of each edge being part of the optimal solution, to guide MCTS in solution finding.
InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation
Recent talking avatar generation models have made strides in achieving realistic and accurate lip synchronization with the audio, but often fall short in controlling and conveying detailed expressions and emotions of the avatar, making the generated video less vivid and controllable.
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.
DPO Meets PPO: Reinforced Token Optimization for RLHF
For its practical implementation, \texttt{RTO} innovatively integrates Direct Preference Optimization (DPO) and PPO.
Protecting Your LLMs with Information Bottleneck
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content.
©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model
To mitigate this, we propose the \copyright Plug-in Authorization framework, introducing three operations: addition, extraction, and combination.
Towards Data-Centric Automatic R&D
We appeal to future work to take developing techniques for tackling automatic R&D into consideration, thus bringing the opportunities of the potential revolutionary upgrade to human productivity.
Empowering Large Language Models on Robotic Manipulation with Affordance Prompting
While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequences properly.
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency.
End-to-End Rate-Distortion Optimized 3D Gaussian Representation
3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering.
Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding
Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa.
Improving Generalizability of Extracting Social Determinants of Health Using Large Language Models through Prompt-tuning
The progress in natural language processing (NLP) using large language models (LLMs) has greatly improved patient information extraction from clinical narratives.
Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning
We examined the prompt-tuning strategies, the size of soft prompts, and the few-short learning ability of GatorTronGPT, a generative clinical LLM developed using 277 billion clinical and general English words with up to 20 billion parameters.
Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure
Cancer treatments are known to introduce cardiotoxicity, negatively impacting outcomes and survivorship.
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
However, the effective utilization of their strong modeling ability in the probabilistic time series forecasting task remains an open question, partially due to the challenge of instability arising from their stochastic nature.
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt.
Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
Accordingly, permutation on the training data is considered as a potential solution, since this can make the model predict antecedent words or tokens.
Me LLaMA: Foundation Large Language Models for Medical Applications
This work underscores the importance of domain-specific data in developing medical LLMs and addresses the high computational costs involved in training, highlighting a balance between pre-training and fine-tuning strategies.
UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
Recent advances in text-guided video editing have showcased promising results in appearance editing (e. g., stylization).
Feasibility of Identifying Factors Related to Alzheimer's Disease and Related Dementia in Real-World Data
We constructed an interactive knowledge map to disseminate our study results.
XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications
Adverse clinical events related to unsafe care are among the top ten causes of death in the U. S.
Addressing Distribution Shift in Time Series Forecasting with Instance Normalization Flows
Due to non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting.
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process Download PDF
To address this challenge, we introduce a novel Multi-Granularity Time Series Diffusion (MG-TSD) model, which achieves state-of-the-art predictive performance by leveraging the inherent granularity levels within the data as given targets at intermediate diffusion steps to guide the learning process of diffusion models.
Morphological Profiling for Drug Discovery in the Era of Deep Learning
Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.
Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need
Objective To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.
GAIA: Zero-shot Talking Avatar Generation
Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image.
On the Generalization Properties of Diffusion Models
This precisely elucidates the adverse effect of "modes shift" in ground truths on the model generalization.
BatteryML:An Open-source platform for Machine Learning on Battery Degradation
Battery degradation remains a pivotal concern in the energy storage domain, with machine learning emerging as a potent tool to drive forward insights and solutions.
MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models
For developers and amateurs, it is very difficult to grasp all of these task to satisfy their requirements in music processing, especially considering the huge differences in the representations of music data and the model applicability across platforms among various tasks.
Leveraging Large Language Model for Automatic Evolving of Industrial Data-Centric R&D Cycle
In the wake of relentless digital transformation, data-driven solutions are emerging as powerful tools to address multifarious industrial tasks such as forecasting, anomaly detection, planning, and even complex decision-making.
From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models
Through GTL, we not only foster a deeper integration of LLMs' sophisticated abilities into tabular data comprehension and application but also offer a new training resource and a test bed for LLMs to enhance their ability to comprehend tabular data.
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries.
On the Impact of Cross-Domain Data on German Language Models
Traditionally, large language models have been either trained on general web crawls or domain-specific data.
NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining
In this work, we make key technical contributions that are tailored to the numerical properties of time-series data and allow the model to scale to large datasets, e. g., millions of temporal sequences.
Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction
We evaluated the transfer learning ability of the prompt-based learning algorithms in a cross-institution setting.
Accurate battery lifetime prediction across diverse aging conditions with deep learning
Here we introduce a universal deep learning approach that is capable of accommodating various aging conditions and facilitating effective learning under low-resource conditions by leveraging data from rich conditions.
TiC: Exploring Vision Transformer in Convolution
While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks.
Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial
Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4.
EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort.
PromptTTS 2: Describing and Generating Voices with Text Prompt
TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech.
Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)
Background: Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications.
Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction
In this paper, we propose a novel Hypergraph Convolutional Network that allows the representation of non-pairwise relationships among diagnosis codes in a hypergraph to capture the hidden feature structures so that fine-grained patient similarity can be calculated for personalized mortality risk prediction.
Microstructure-Empowered Stock Factor Extraction and Utilization
To address these challenges, we propose a novel framework that aims to effectively extract essential factors from order flow data for diverse downstream tasks across different granularities and scenarios.
Apple Vision Pro for Healthcare: "The Ultimate Display"? -- Entering the Wonderland of Precision Medicine
At the Worldwide Developers Conference (WWDC) in June 2023, Apple introduced the Vision Pro.
Pre-Trained Large Language Models for Industrial Control
2)~How well can GPT-4 generalize to different scenarios for HVAC control?
Improving Primary Healthcare Workflow Using Extreme Summarization of Scientific Literature Based on Generative AI
The time needed to answer questions related to the content of abstracts was significantly lower in groups two and three compared to the first group using full abstracts.
Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance
Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets.
EmoGen: Eliminating Subjective Bias in Emotional Music Generation
In this paper, we propose EmoGen, an emotional music generation system that leverages a set of emotion-related music attributes as the bridge between emotion and music, and divides the generation into two stages: emotion-to-attribute mapping with supervised clustering, and attribute-to-music generation with self-supervised learning.
Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series
Irregularly sampled multivariate time series are ubiquitous in various fields, particularly in healthcare, and exhibit two key characteristics: intra-series irregularity and inter-series discrepancy.
A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management
Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment.
Mildly Constrained Evaluation Policy for Offline Reinforcement Learning
Offline reinforcement learning (RL) methodologies enforce constraints on the policy to adhere closely to the behavior policy, thereby stabilizing value learning and mitigating the selection of out-of-distribution (OOD) actions during test time.
UADB: Unsupervised Anomaly Detection Booster
This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods.
MuseCoco: Generating Symbolic Music from Text
In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements.
Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts.
A Study of Generative Large Language Model for Medical Research and Healthcare
This study provides insights on the opportunities and challenges of LLMs for medical research and healthcare.
GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework
Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.
ResiDual: Transformer with Dual Residual Connections
In this paper, we propose ResiDual, a novel Transformer architecture with Pre-Post-LN (PPLN), which fuses the connections in Post-LN and Pre-LN together and inherits their advantages while avoids their limitations.
H-TSP: Hierarchically Solving the Large-Scale Travelling Salesman Problem
We propose an end-to-end learning framework based on hierarchical reinforcement learning, called H-TSP, for addressing the large-scale Travelling Salesman Problem (TSP).
Deep Reinforcement Learning
Hierarchical Reinforcement Learning
+1
Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem
Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology.
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor.
Identifying Symptoms of Delirium from Clinical Narratives Using Natural Language Processing
To assist in the diagnosis and phenotyping of delirium, we formed an expert panel to categorize diverse delirium symptoms, composed annotation guidelines, created a delirium corpus with diverse delirium symptoms, and developed NLP methods to extract delirium symptoms from clinical notes.
DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
Additionally, we propose a novel method for generating continuous video frames with the DDIM image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly.
HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details
3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image.
Ranked #1 on
3D Face Reconstruction
on REALY (side-view)
Contextualized Medication Information Extraction Using Transformer-based Deep Learning Architectures
Materials and methods: We developed NLP systems for medication mention extraction, event classification (indicating medication changes discussed or not), and context classification to classify medication changes context into 5 orthogonal dimensions related to drug changes.
Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension
GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the two datasets by 1%~3% and 0. 7%~1. 3%, respectively.
Clinical Concept Extraction
Machine Reading Comprehension
+3
DR-VIDAL -- Doubly Robust Variational Information-theoretic Deep Adversarial Learning for Counterfactual Prediction and Treatment Effect Estimation on Real World Data
DR-VIDAL integrates: (i) a variational autoencoder (VAE) to factorize confounders into latent variables according to causal assumptions; (ii) an information-theoretic generative adversarial network (Info-GAN) to generate counterfactuals; (iii) a doubly robust block incorporating treatment propensities for outcome predictions.
Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks
Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?
A Study on ReLU and Softmax in Transformer
This paper sheds light on the following points: 1) Softmax and ReLU use different normalization methods over elements which lead to different variances of results, and ReLU is good at dealing with a large number of key-value slots; 2) FFN and key-value memory are equivalent, and thus the Transformer can be viewed as a memory network where FFNs and self-attention networks are both key-value memories.
Regeneration Learning: A Learning Paradigm for Data Generation
Regeneration learning extends the concept of representation learning to data generation tasks, and can be regarded as a counterpart of traditional representation learning, since 1) regeneration learning handles the abstraction (Y') of the target data Y for data generation while traditional representation learning handles the abstraction (X') of source data X for data understanding; 2) both the processes of Y'-->Y in regeneration learning and X-->X' in representation learning can be learned in a self-supervised way (e. g., pre-training); 3) both the mappings from X to Y' in regeneration learning and from X' to Y in representation learning are simpler than the direct mapping from X to Y.
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples.
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.
Empowering Diffusion Models on the Embedding Space for Text Generation
Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space.
Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their supply and demand.
SODA: A Natural Language Processing Package to Extract Social Determinants of Health for Cancer Studies
Objective: We aim to develop an open-source natural language processing (NLP) package, SODA (i. e., SOcial DeterminAnts), with pre-trained transformer models to extract social determinants of health (SDoH) for cancer patients, examine the generalizability of SODA to a new disease domain (i. e., opioid use), and evaluate the extraction rate of SDoH using cancer populations.
TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets
There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies.
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
To reduce the compute time overhead of private learning, we show that \emph{per-layer clipping}, where the gradient of each neural network layer is clipped separately, allows clipping to be performed in conjunction with backpropagation in differentially private optimization.
VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing
In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech.
Multi-Objective Personalized Product Retrieval in Taobao Search
These problems promote us to further strengthen the capabilities of our EBR model in both relevance estimation and personalized retrieval.
GLARE: A Dataset for Traffic Sign Detection in Sun Glare
It provides an essential enrichment to the widely used LISA Traffic Sign dataset.
Learning Differential Operators for Interpretable Time Series Modeling
In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data.
AA-Forecast: Anomaly-Aware Forecast for Extreme Events
Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.
P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
Variational Temporal Deconfounder for Individualized Treatment Effect Estimation from Longitudinal Observational Data
Estimating treatment effects, especially individualized treatment effects (ITE), using observational data is challenging due to the complex situations of confounding bias.
Joint Application of the Target Trial Causal Framework and Machine Learning Modeling to Optimize Antibiotic Therapy: Use Case on Acute Bacterial Skin and Skin Structure Infections due to Methicillin-resistant Staphylococcus aureus
ABSSSI-MRSA is a challenging condition with reduced treatment options - vancomycin is the preferred choice, but it has non-negligible side effects.
Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures
It uses less than 5% FLOPS compared with previous SOTA methods on the largest benchmark dataset.
LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
We investigate the physical information in the MSR loss, which we called long-range entanglements, and identify the challenge that the neural network requires the capacity to model the long-range entanglements in the spatial domain of the PDE, whose patterns vary in different PDEs.
MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services
For scalable inference in a single node, especially when the model size is larger than GPU memory, MoESys builds the CPU-GPU memory jointly into a ring of sections to load the model, and executes the computation tasks across the memory sections in a round-robin manner for efficient inference.
A Simple yet Effective Framework for Active Learning to Rank
To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.
Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble
Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner.
DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting
However, the complicated dependencies of the PTS signal on its inherent periodicity as well as the sophisticated composition of various periods hinder the performance of PTS forecasting.
Temporal Subtyping of Alzheimer's Disease Using Medical Conditions Preceding Alzheimer's Disease Onset in Electronic Health Records
Subtyping of Alzheimer's disease (AD) can facilitate diagnosis, treatment, prognosis and disease management.
Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting
How to discover the useful implicit relation between entities and effectively utilize the relations for each entity under various circumstances is crucial.
Learning Physics-Informed Neural Networks without Stacked Back-propagation
In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks.
AF$_2$: Adaptive Focus Framework for Aerial Imagery Segmentation
As a specific semantic segmentation task, aerial imagery segmentation has been widely employed in high spatial resolution (HSR) remote sensing images understanding.
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records
GatorTron models scale up the clinical language model from 110 million to 8. 9 billion parameters and improve 5 clinical NLP tasks (e. g., 9. 6% and 9. 5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery.
Ranked #10 on
Zero-Shot Learning
on MedConceptsQA
DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation
To handle concept drift, previous methods first detect when/where the concept drift happens and then adapt models to fit the distribution of the latest data.
SHGNN: Structure-Aware Heterogeneous Graph Neural Network
Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path.
KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings
Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering.
Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning
Class-imbalance is a common problem in machine learning practice.
HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information
To overcome the shortcomings of previous work, we proposed a novel stock trend forecasting framework that can adequately mine the concept-oriented shared information from predefined concepts and hidden concepts.
ReLF: Scalable Remote Live Forensics for Android
The world has witnessed the proliferation of mobile technologies as well as smartphone-related cybercrimes in recent years.
Deep Ensemble Policy Learning
Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).
Multi-Agent Reinforcement Learning with Shared Resource in Inventory Management
We consider inventory management (IM) problem for a single store with a large number of SKUs (stock keeping units) in this paper, where we need to make replenishment decisions for each SKU to balance its supply and demand.
Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
In this paper, we propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps for multivariate time series forecasting.
A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models
In this study, we examined two state-of-the-art transformer-based NLP models, including BERT and RoBERTa, to extract SBDoH concepts from clinical narratives, applied the best performing model to extract SBDoH concepts on a lung cancer screening patient cohort, and examined the difference of SBDoH information between NLP extracted results and structured EHRs (SBDoH information captured in standard vocabularies such as the International Classification of Diseases codes).
Clinical Relation Extraction Using Transformer-based Models
The goal of this study is to systematically explore three widely used transformer-based models (i. e., BERT, RoBERTa, and XLNet) for clinical relation extraction and develop an open-source package with clinical pre-trained transformer-based models to facilitate information extraction in the clinical domain.
Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
Modeling and managing portfolio risk is perhaps the most important step to achieve growing and preserving investment performance.
Assessing putative bias in prediction of anti-microbial resistance from real-world genotyping data under explicit causal assumptions
Whole genome sequencing (WGS) is quickly becoming the customary means for identification of antimicrobial resistance (AMR) due to its ability to obtain high resolution information about the genes and mechanisms that are causing resistance and driving pathogen mobility.
Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport
In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns.
Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter
We chose the best performing models in each task to assemble an end-to-end deep learning pipeline to detect DS AE signals and compared the results to the known DS AEs from a DS knowledge base (i. e., iDISK).
Deep Subdomain Adaptation Network for Image Classification
The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.
Impact of pandemic fatigue on the spread of COVID-19: a mathematical modelling study
We used a stochastic metapopulation model with a hierarchical structure and fitted the model to the positive cases in the US from the start of outbreak to the end of 2020.
A Conversational Agent System for Dietary Supplements Use
Dietary supplements (DS) have been widely used by consumers, but the information around the efficacy and safety of DS is disparate or incomplete, thus creating barriers for consumers to find information effectively.
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.
Model Complexity of Deep Learning: A Survey
Model complexity is a fundamental problem in deep learning.
REST: Relational Event-driven Stock Trend Forecasting
To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts.
Universal Trading for Order Execution with Oracle Policy Distillation
As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument.
Applications of artificial intelligence in drug development using real-world data
The US Food and Drug Administration (FDA) has been actively promoting the use of real-world data (RWD) in drug development.
Dynamic Graph Representation Learning with Fourier Temporal State Embedding
In this work, we present a new method named Fourier Temporal State Embedding (FTSE) to address the temporal information in dynamic graph representation learning.
LINGUINE: LearnIng to pruNe on subGraph convolUtIon NEtworks
In recent years, research communities have been developing stochastic sampling methods to handle large graphs when it is unreal to put the whole graph into a single batch.
Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representations
While adopting complex GNN models with more informative message passing and aggregation mechanisms can obviously benefit heterogeneous vertex representations and cooperative policy learning, it could, on the other hand, increase the training difficulty of MARL and demand more intense and direct reward signals compared to the original global reward.
ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting
Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field.
COSEA: Convolutional Code Search with Layer-wise Attention
However, most existing studies overlook the code's intrinsic structural logic, which indeed contains a wealth of semantic information, and fails to capture intrinsic features of codes.
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.
Qlib: An AI-oriented Quantitative Investment Platform
Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments.
Learning to Reweight with Deep Interactions
Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.
Measuring Model Complexity of Neural Networks with Curve Activation Functions
Our results demonstrate that the occurrence of overfitting is positively correlated with the increase of model complexity during training.
MC-BERT: Efficient Language Pre-Training via a Meta Controller
Pre-trained contextual representations (e. g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks.
Invertible Image Rescaling
High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images.
Ranked #1 on
Image Rescaling
on Urban100-4x
Integrating Crowdsourcing and Active Learning for Classification of Work-Life Events from Tweets
Results show that crowdsourcing is useful to create high-quality annotations and active learning helps in reducing the number of required tweets, although there was no substantial difference among the strategies tested.
Work-in-progress: a deep learning strategy for I/O scheduling in storage systems
Under the big data era, there is a crucial need to improve the performance of storage systems for data-intensive applications.
Hardware Aware Neural Architecture Search
Irregular Time Series
+2
Federated Learning for Healthcare Informatics
With the rapid development of computer software and hardware technologies, more and more healthcare data are becoming readily available from clinical institutions, patients, insurance companies and pharmaceutical industries, among others.
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution.
Ranked #3 on
Atari Games
on Atari 2600 Skiing
(using extra training data)
Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods
Early detection of cancer patients at risk for cardiotoxicity before cardiotoxic treatments and providing preventive measures are potential solutions to improve cancer patients's quality of life.
Demonstration Actor Critic
One approach leverages demonstration data in a supervised manner, which is simple and direct, but can only provide supervision signal over those states seen in the demonstrations.
Independence-aware Advantage Estimation
Most of existing advantage function estimation methods in reinforcement learning suffer from the problem of high variance, which scales unfavorably with the time horizon.
Self-paced Ensemble for Highly Imbalanced Massive Data Classification
To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers.
LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm
Instead of using fixed coding matrix and decoding strategy, LightMC uses a differentiable decoding strategy, which enables it to dynamically optimize the coding matrix and decoding strategy, toward increasing the overall accuracy of multiclass classification, via back propagation jointly with the training of base learners in an iterative way.
