Search Results for author:
Found 54 papers, 10 papers with code
hBERT + BiasCorp - Fighting Racism on the Web
In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer.
Benchmarking Next-Generation Reasoning-Focused Large Language Models in Ophthalmology: A Head-to-Head Evaluation on 5,888 Items
Average inference time was recorded for a subset of 100 randomly selected questions.
Auto-Bench: An Automated Benchmark for Scientific Discovery in LLMs
We evaluate state-of-the-art LLMs, including GPT-4, Gemini, Qwen, Claude, and Llama, and observe a significant performance drop as the problem complexity increases, which suggests an important gap between machine and human intelligence that future development of LLMs need to take into consideration.
Multi-Novelty: Improve the Diversity and Novelty of Contents Generated by Large Language Models via inference-time Multi-Views Brainstorming
Large Language Models (LLMs) demonstrate remarkable proficiency in generating accurate and fluent text.
Representation Collapsing Problems in Vector Quantization
In this study, we investigate representation collapse in vector quantization - a critical degradation where codebook tokens or latent embeddings lose their discriminative power by converging to a limited subset of values.
Improving Discrete Optimisation Via Decoupled Straight-Through Gumbel-Softmax
Discrete representations play a crucial role in many deep learning architectures, yet their non-differentiable nature poses significant challenges for gradient-based optimization.
Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior
This principled framework avoids various heuristics and strong assumptions that are needed with the VQ-VAE to address training instability and to improve codebook utilization.
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Building on the Efficient Stochastic Transformer-based World Models (STORM) architecture, we replace the traditional MLP prior with a Masked Generative Prior (e. g., MaskGIT Prior) and introduce GIT-STORM.
CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept
Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors.
Brain-inspired continual pre-trained learner via silent synaptic consolidation
In this study, we introduce the Artsy, inspired by the activation mechanisms of silent synapses via spike-timing-dependent plasticity observed in mature brains, to enhance the continual learning capabilities of pre-trained models.
Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model
In external validations, LEME excelled in long-form QA with a Rouge-L of 0. 19 (all p<0. 0001), ranked second in MCQ accuracy (0. 68; all p<0. 0001), and scored highest in EHR summarization and clinical QA (ranging from 4. 24 to 4. 83 out of 5 for correctness, completeness, and readability).
Safety challenges of AI in medicine in the era of large language models
These concerns about AI safety have emerged as the most significant obstacles to the adoption of AI in medicine.
Balance of Number of Embedding and their Dimensions in Vector Quantization
The dimensionality of the embedding and the number of available embeddings ( also called codebook size) are critical factors influencing the performance of Vector Quantization(VQ), a discretization process used in many models such as the Vector Quantized Variational Autoencoder (VQ-VAE) architecture.
Common and Rare Fundus Diseases Identification Using Vision-Language Foundation Model with Knowledge of Over 400 Diseases
Here we introduce RetiZero, a vision-language foundation model that leverages knowledge from over 400 fundus diseases.
Verbalized Probabilistic Graphical Modeling with Large Language Models
Faced with complex problems, the human brain demonstrates a remarkable capacity to transcend sensory input and form latent understandings of perceived world patterns.
Bifurcated Generative Flow Networks
Generative Flow Networks (GFlowNets), a new family of probabilistic samplers, have recently emerged as a promising framework for learning stochastic policies that generate high-quality and diverse objects proportionally to their rewards.
VQSynery: Robust Drug Synergy Prediction With Vector Quantization Mechanism
The pursuit of optimizing cancer therapies is significantly advanced by the accurate prediction of drug synergy.
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos.
Unsupervised Concept Discovery Mitigates Spurious Correlations
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases.
BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning
Conclusion: BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios.
Evolution Guided Generative Flow Networks
Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards.
Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architectures
We develop a robust and generalizable method that utilizes GFlowOut integrated with ResNet18 and ViT models as the backbone in identifying various ocular conditions.
Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents
Individuals, despite having varied life experiences and learning processes, can communicate effectively through languages.
Physical Reasoning and Object Planning for Household Embodied Agents
We introduce the CommonSense Object Affordance Task (COAT), a novel framework designed to analyze reasoning capabilities in commonsense scenarios.
Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems
Understanding causal relationships within Gene Regulatory Networks (GRNs) is essential for unraveling the gene interactions in cellular processes.
Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries
Due to limited resources and fast economic growth, designing optimal transportation road networks with traffic simulation and validation in a cost-effective manner is vital for developing countries, where extensive manual testing is expensive and often infeasible.
Attention Schema in Neural Agents
A strong prediction of this theory is that an agent can use its own AS to also infer the states of other agents' attention and consequently enhance coordination with other agents.
Enhancing Human Capabilities through Symbiotic Artificial Intelligence with Shared Sensory Experiences
In this paper, we introduce a novel concept in Human-AI interaction called Symbiotic Artificial Intelligence with Shared Sensory Experiences (SAISSE), which aims to establish a mutually beneficial relationship between AI systems and human users through shared sensory experiences.
A Transformer-based Deep Learning Algorithm to Auto-record Undocumented Clinical One-Lung Ventilation Events
We hypothesized that available intraoperative mechanical ventilation and physiological time-series data combined with other clinical events could be used to accurately predict missing start and end times of OLV.
Construction of extra-large scale screening tools for risks of severe mental illnesses using real world healthcare data
First, the predictive models were constructed and tested using data in case-control cohorts from insurance claims or EHR data.
GFlowOut: Dropout with Generative Flow Networks
These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation.
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
We formalize the notions of coordination level and heterogeneity level of an environment and present HECOGrid, a suite of multi-agent RL environments that facilitates empirical evaluation of different MARL approaches across different levels of coordination and environmental heterogeneity by providing a quantitative control over coordination and heterogeneity levels of the environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
As antibiotic-resistant bacterial strains are rapidly spreading worldwide, infections caused by these strains are emerging as a global crisis causing the death of millions of people every year.
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another.
Intelligent Communication
Multi-agent Reinforcement Learning
+2
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data
Federated learning is a distributed machine learning approach which enables a shared server model to learn by aggregating the locally-computed parameter updates with the training data from spatially-distributed client silos.
Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization
Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit.
PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
Federated machine learning is a versatile and flexible tool to utilize distributed data from different sources, especially when communication technology develops rapidly and an unprecedented amount of data could be collected on mobile devices nowadays.
Discrete-Valued Neural Communication
Deep learning has advanced from fully connected architectures to structured models organized into components, e. g., the transformer composed of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes.
HBert + BiasCorp -- Fighting Racism on the Web
In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer.
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters
To promote the practical application for autonomous floating wastes cleaning, we present FloW, the first dataset for floating waste detection in inland water areas.
Patient similarity: methods and applications
Patient similarity analysis is important in health care applications.
FakeSafe: Human Level Data Protection by Disinformation Mapping using Cycle-consistent Adversarial Network
The concept of disinformation is to use fake messages to confuse people in order to protect the real information.
A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models
We present a timely and novel methodology that combines disease estimates from mechanistic models with digital traces, via interpretable machine-learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real-time.
Federated pretraining and fine tuning of BERT using clinical notes from multiple silos
Large scale contextual representation models, such as BERT, have significantly advanced natural language processing (NLP) in recently years.
Federated machine learning with Anonymous Random Hybridization (FeARH) on medical records
Sometimes electrical medical records are restricted and difficult to centralize for machine learning, which could only be trained in distributed manner that involved many institutions in the process.
Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
Specifically, we design, implement and evaluate a channel-based update algorithm for the central server in a distributed system, which selects the channels with regard to the most active features in a training loop and uploads them as learned information from local datasets.
Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning
Artificial neural network has achieved unprecedented success in a wide variety of domains such as classifying, predicting and recognizing objects.
Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence
We proposed and evaluated a confederated learning to training machine learning model to stratify the risk of several diseases among when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching.
Two-stage Federated Phenotyping and Patient Representation Learning
A large percentage of medical information is in unstructured text format in electronic medical record systems.
Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records
Electronic medical records (EMRs) supports the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events.
Artificial neural networks condensation: A strategy to facilitate adaption of machine learning in medical settings by reducing computational burden
In this project we explored methods to increase computational efficiency of ML algorithms, in particular Artificial Neural Nets (NN), while not compromising the accuracy of the predicted results.
LoAdaBoost: loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data
One challenge in applying federated machine learning is the possibly different distributions of data from diverse sources.
FADL:Federated-Autonomous Deep Learning for Distributed Electronic Health Record
Electronic health record (EHR) data is collected by individual institutions and often stored across locations in silos.
DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain
Previous research on automatic pain estimation from facial expressions has focused primarily on "one-size-fits-all" metrics (such as PSPI).
