Канал: Научные семинары по искусственному интеллекту

Перенесли канал в Дзен

Перенесли канал в Дзен

Обнаружение и диагностика неисправностей при помощи графовых нейронных сетей

Обнаружение и диагностика неисправностей при помощи графовых нейронных сетей

Механизм внимания в моделях, основанных на деревьях решений

Механизм внимания в моделях, основанных на деревьях решений

Автоматический анализ временных рядов (с упором на классификацию и поиск аномалий)

Автоматический анализ временных рядов (с упором на классификацию и поиск аномалий)

Решение задачи оптимального транспорта на основе нейросетей

Решение задачи оптимального транспорта на основе нейросетей

Learning to Recommend Method Names with Global Context

Learning to Recommend Method Names with Global Context

Генерация SQL запросов по тексту на естественном языке

Генерация SQL запросов по тексту на естественном языке

Automating Reinforcement Learning Architecture Design for Code Optimization

Automating Reinforcement Learning Architecture Design for Code Optimization

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Predicting What You Already Know Helps: Provable Self-Supervised Learning

Predicting What You Already Know Helps: Provable Self-Supervised Learning

Emerging Properties in Self-Supervised Vision Transforms

Emerging Properties in Self-Supervised Vision Transforms

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

Block-Recurrent Transformers

Block-Recurrent Transformers

Assessing Project-Level Fine-Tuning of ML4SE Models

Assessing Project-Level Fine-Tuning of ML4SE Models

Предсказание типов для исходного кода с использованием графовых нейронных сетей

Предсказание типов для исходного кода с использованием графовых нейронных сетей

Industry-scale IR-based Bug Localization: A Perspective from Facebook

Industry-scale IR-based Bug Localization: A Perspective from Facebook

Code Smells for Machine Learning Applications

Code Smells for Machine Learning Applications

Fastformer: Additive Attention Can Be All You Need

Fastformer: Additive Attention Can Be All You Need

Language Models are Unsupervised Multitask Learners

Language Models are Unsupervised Multitask Learners

Neural Code Completion: Research & Practice

Neural Code Completion: Research & Practice

Машинное обучение на динамических графах

Машинное обучение на динамических графах

Drug Target Profiler

Drug Target Profiler

Code Tagger

Code Tagger

Modeling Polypharmacy Side Effects with Graph Convolutional Networks

Modeling Polypharmacy Side Effects with Graph Convolutional Networks

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Offline Reinforcement Learning as One Big Sequence Modeling Problem

Offline Reinforcement Learning as One Big Sequence Modeling Problem

Building IntelliJ-based plugins

Building IntelliJ-based plugins

Self-Imitation Learning

Self-Imitation Learning

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Model-based Reinforcement Learning

Model-based Reinforcement Learning

Challenges for Static Analysis of Java Reflection – Literature Review and Empirical Study

Challenges for Static Analysis of Java Reflection – Literature Review and Empirical Study

Decision Transformer: Reinforcement Learning via Sequence Modeling

Decision Transformer: Reinforcement Learning via Sequence Modeling

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Collect & Infer - a fresh look at data-efficient Reinforcement Learning

Collect & Infer - a fresh look at data-efficient Reinforcement Learning

How to structure your ideas and make yourself understood

How to structure your ideas and make yourself understood

ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

AI in Software Engineering at Facebook

AI in Software Engineering at Facebook

Self-imitation Learning from Demonstrations

Self-imitation Learning from Demonstrations

Do Transformers Really Perform Bad for Graph Representation?

Do Transformers Really Perform Bad for Graph Representation?

Real-Time Speech Enhancement in the Waveform Domain

Real-Time Speech Enhancement in the Waveform Domain

Optimal Auctions through Deep Learning

Optimal Auctions through Deep Learning

Методы машинного обучения в функциональной геномике

Методы машинного обучения в функциональной геномике

SPARQLing Database Queries from Intermediate Question Decompositions

SPARQLing Database Queries from Intermediate Question Decompositions

Documentation Matters: Human-Centered System to Assist Data Science Code Documentation in Notebooks

Documentation Matters: Human-Centered System to Assist Data Science Code Documentation in Notebooks

Cognitive phenomena in software engineering

Cognitive phenomena in software engineering

Диффузные модели

Диффузные модели

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

QMIX / Graph Attention Networks with Positional Embeddings

QMIX / Graph Attention Networks with Positional Embeddings

Same data, different conclusions

Same data, different conclusions

Distilling Knowledge from Reader to Retriever for Question Answering

Distilling Knowledge from Reader to Retriever for Question Answering

Code quality for online learning platforms

Code quality for online learning platforms

Biology meets graph machine learning

Biology meets graph machine learning

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

Automated Comment Update: How Far are We?

Automated Comment Update: How Far are We?

Rethinking Attention with Performers / A Generalization of Transformer Networks to Graphs

Rethinking Attention with Performers / A Generalization of Transformer Networks to Graphs

Large-scale Analysis of Kotlin Code

Large-scale Analysis of Kotlin Code

Language-Agnostic Representation Learning of Source Code from Structure and Context

Language-Agnostic Representation Learning of Source Code from Structure and Context

Import2vec: Learning Embeddings for Software Libraries

Import2vec: Learning Embeddings for Software Libraries

Diversity oriented Deep Reinforcement Learning for targeted molecule generation

Diversity oriented Deep Reinforcement Learning for targeted molecule generation

Re-splitting Jupyter notebook cells

Re-splitting Jupyter notebook cells

Collecting a dataset of bug fixing commits

Collecting a dataset of bug fixing commits

Aggregation model for stack trace grouping / Deep assignee prediction for bug stacktraces

Aggregation model for stack trace grouping / Deep assignee prediction for bug stacktraces

Reassessing Automatic Evaluation Metrics for Code Summarization Tasks

Reassessing Automatic Evaluation Metrics for Code Summarization Tasks

Stack trace Similarity

Stack trace Similarity

Инструменты оптимизации для задач SE

Инструменты оптимизации для задач SE

A Differential Testing Approach for Evaluating Abstract Syntax Tree Mapping Algorithms

A Differential Testing Approach for Evaluating Abstract Syntax Tree Mapping Algorithms

Expertise Embeddings and Assignee Prediction Task

Expertise Embeddings and Assignee Prediction Task

Fast Reinforcement Learning with Generalized Updates & Evolving Reinforcement Learning Algorithms

Fast Reinforcement Learning with Generalized Updates & Evolving Reinforcement Learning Algorithms

Quality Metrics for Code Generation Models

Quality Metrics for Code Generation Models

«Запахи в тестах» в Python: определение, нахождение, анализ

«Запахи в тестах» в Python: определение, нахождение, анализ

Применение методов deep learning к задаче эпитопного картирования

Применение методов deep learning к задаче эпитопного картирования

Предсказание структуры CDR-H3 с помощью методов глубокого обучения

Предсказание структуры CDR-H3 с помощью методов глубокого обучения

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation

Применение различных методов оптимизации для моделей суммаризации кода

Применение различных методов оптимизации для моделей суммаризации кода

NFNets: семейство нейросетей для распознавания изображений без использования BatchNormalization

NFNets: семейство нейросетей для распознавания изображений без использования BatchNormalization

Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations

Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations

Causal Inference Q-Network: Toward Resilient Reinforcement Learning

Causal Inference Q-Network: Toward Resilient Reinforcement Learning

Suggesting identifier names

Suggesting identifier names

Сжатие сейсмических данных с применением глубокого обучения

Сжатие сейсмических данных с применением глубокого обучения

Обзор методов интерпретации графовых нейронных сетей для предсказания молекулярных свойств

Обзор методов интерпретации графовых нейронных сетей для предсказания молекулярных свойств

Exploring the Effectiveness of Deep Learning for Bug Triaging problem

Exploring the Effectiveness of Deep Learning for Bug Triaging problem

Synthetic Returns for Long-Term Credit Assignment

Synthetic Returns for Long-Term Credit Assignment

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

DALL·E: Zero-Shot Text-to-Image Generation

DALL·E: Zero-Shot Text-to-Image Generation

Reflekt

Reflekt

One-Class Classification vs Positive-Unlabeled Learning

One-Class Classification vs Positive-Unlabeled Learning

Улучшение модели предсказания совместных воздействий лекарств на человеческий организм

Улучшение модели предсказания совместных воздействий лекарств на человеческий организм

Comprehensible AI Services

Comprehensible AI Services

Replacing rewards with examples

Replacing rewards with examples

Integrating Demonstrations Into Self-Imitation Learning

Integrating Demonstrations Into Self-Imitation Learning

Decoding EEG Brain Activity for Multi-Modal Natural Language Processing

Decoding EEG Brain Activity for Multi-Modal Natural Language Processing

3D детектирование объектов в задаче беспилотников

3D детектирование объектов в задаче беспилотников

VoiceFilter-Lite: целевое разделение голоса для распознавания речи на устройстве

VoiceFilter-Lite: целевое разделение голоса для распознавания речи на устройстве

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics

Self-Paced Deep Reinforcement Learning

Self-Paced Deep Reinforcement Learning

Taming Transformers for High-Resolution Image Synthesis

Taming Transformers for High-Resolution Image Synthesis

Identifying Nanoparticle Geometry from Emissivity

Identifying Nanoparticle Geometry from Emissivity

Adversarially Guided Actor-Critic

Adversarially Guided Actor-Critic

AntiCopyPaster: выделение дубликатов кода в момент их появления

AntiCopyPaster: выделение дубликатов кода в момент их появления

Hierarchical Clustering Analysis of Spectral Fingerprints for Cheminformatics

Hierarchical Clustering Analysis of Spectral Fingerprints for Cheminformatics

Token-to-token ViT: Training Vision Transformers from Scratch on ImageNet

Token-to-token ViT: Training Vision Transformers from Scratch on ImageNet

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems

Predicting Synergistic Drug Combinations for COVID with Biological Bottleneck Models

Predicting Synergistic Drug Combinations for COVID with Biological Bottleneck Models

Reward Propagation Using Graph Convolutional Networks

Reward Propagation Using Graph Convolutional Networks

Kanji Workbook: интеллектуальная система для изучения письменности Кандзи

Kanji Workbook: интеллектуальная система для изучения письменности Кандзи

Методы машинного обучения для предсказания ретросинтеза

Методы машинного обучения для предсказания ретросинтеза

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code

PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

Adversarial Stein Training for Graph Energy Models

Adversarial Stein Training for Graph Energy Models

Extracting Training Data from Large Language Models

Extracting Training Data from Large Language Models

Создание эмбеддингов зависимостей и их использование в рекоммендательной системе

Создание эмбеддингов зависимостей и их использование в рекоммендательной системе

Limb: генерация абстрактных изображений с помощью CPPN сетей и рекомендательных систем

Limb: генерация абстрактных изображений с помощью CPPN сетей и рекомендательных систем

Исследование среды с помощью моделей мира

Исследование среды с помощью моделей мира

Learning Super-Resolution Electron Density Map of Proteins using 3D U-Net

Learning Super-Resolution Electron Density Map of Proteins using 3D U-Net

Counterfactual Generative Networks

Counterfactual Generative Networks

Effective Diversity in Population Based Reinforcement Learning

Effective Diversity in Population Based Reinforcement Learning

Создание эмбеддингов зависимостей и их использование в рекоммендательной системе

Создание эмбеддингов зависимостей и их использование в рекоммендательной системе

Differential Cross Entropy Model

Differential Cross Entropy Model

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

MELD (Meta RL with Latent Dynamics)

MELD (Meta RL with Latent Dynamics)

ERASER: A Benchmark to Evaluate Rationalized NLP Models

ERASER: A Benchmark to Evaluate Rationalized NLP Models

Различные подходы к негативному сэмплированию в графах знаний

Различные подходы к негативному сэмплированию в графах знаний

Анализ Jupyter-ноутбуков

Анализ Jupyter-ноутбуков

Neural Text Generation with Unlikelihood Training

Neural Text Generation with Unlikelihood Training

Primal Wasserstein Imitation Learning

Primal Wasserstein Imitation Learning

Reformer: The Efficient Transformer

Reformer: The Efficient Transformer

Предсказание тегов задач спортивного программирования

Предсказание тегов задач спортивного программирования

Curriculum Learning for Reinforcement Learning Domains

Curriculum Learning for Reinforcement Learning Domains

From local explanations to global understanding with explainable AI for trees

From local explanations to global understanding with explainable AI for trees

Методы анализа научных публикаций

Методы анализа научных публикаций

Recent advances is anomaly detection

Recent advances is anomaly detection

Support vector machines for drug discovery

Support vector machines for drug discovery

Visually-Aware Fashion Recommendation and Design with Generative Image Models

Visually-Aware Fashion Recommendation and Design with Generative Image Models

Learning latent state representation for speeding up exploration

Learning latent state representation for speeding up exploration

Sleep quality prediction in caregivers using physiological signals

Sleep quality prediction in caregivers using physiological signals

Suggesting Identifier Names

Suggesting Identifier Names

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Мультилейбльная классификация биомедицинских текстов

Мультилейбльная классификация биомедицинских текстов

Closing the Reality Gap in Sim2Real

Closing the Reality Gap in Sim2Real

EfficientDet: Scalable and Efficient Object Detection

EfficientDet: Scalable and Efficient Object Detection

Семантическая сегментация медицинских изображений

Семантическая сегментация медицинских изображений

RL in music: accomponement and music generation using reingorcement learning approach

RL in music: accomponement and music generation using reingorcement learning approach

Использование спутниковых снимков в изучении экономического благосостояния

Использование спутниковых снимков в изучении экономического благосостояния

Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess

Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess

Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans

Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans

Multilingual end-to-end speech translation

Multilingual end-to-end speech translation

Multi-agent Social Reinforcement Learning Improves Generalization

Multi-agent Social Reinforcement Learning Improves Generalization

Graph Representation Learning and Beyond

Graph Representation Learning and Beyond

ML + SE - Source Code

ML + SE - Source Code

Contrastive Learning for Dreamer

Contrastive Learning for Dreamer

Автоматическая генерация подсказок для решения задач по программированию

Автоматическая генерация подсказок для решения задач по программированию

Предсказание липофильности при помощи молекулярных подструктур и multitask обучения

Предсказание липофильности при помощи молекулярных подструктур и multitask обучения

A Game Theoretic Framework for Model Based Reinforcement Learning

A Game Theoretic Framework for Model Based Reinforcement Learning

Адаптивные стохастические градиентные методы: теория и практика

Адаптивные стохастические градиентные методы: теория и практика

Визуализация рефакторингов кода

Визуализация рефакторингов кода

Предсказание структуры H3 петли антител с помощью методов машинного обучения

Предсказание структуры H3 петли антител с помощью методов машинного обучения

Мультимодальные задачи в машинном обучении

Мультимодальные задачи в машинном обучении

Munchausen Reinforcement Learning

Munchausen Reinforcement Learning

Поиск шаблонов изменений в Python и их автоматизация

Поиск шаблонов изменений в Python и их автоматизация

Построение векторного представления программного кода на основе AST

Построение векторного представления программного кода на основе AST

Построение векторных представлений для изменений программного кода

Построение векторных представлений для изменений программного кода

Агрегация биологических и химических данных в DL

Агрегация биологических и химических данных в DL

Маршрутизирующие сети

Маршрутизирующие сети

Neural Kernel Methods

Neural Kernel Methods

The AI Economist

The AI Economist

Применение тематического моделирования в SE

Применение тематического моделирования в SE

Building Implicit Vector Representations of Individual Coding Style

Building Implicit Vector Representations of Individual Coding Style

Finding Similar Code Repositories

Finding Similar Code Repositories

Self-Tuning Deep Reinforcement Learning

Self-Tuning Deep Reinforcement Learning

Генерация синтетических healthcare данных

Генерация синтетических healthcare данных

Zero Shot Learning for Code Education

Zero Shot Learning for Code Education

A Spatiotemporal Epidemic Model to Quantify the Effects of Contact Tracing, Testing, and Containment

A Spatiotemporal Epidemic Model to Quantify the Effects of Contact Tracing, Testing, and Containment

Sample Efficiency in RL

Sample Efficiency in RL

State-of-the-art Real-time Object Detection

State-of-the-art Real-time Object Detection

Code Prediction by Feeding Trees to Transformers

Code Prediction by Feeding Trees to Transformers

Машинное обучение в разработке малых молекул в фармацевтике

Машинное обучение в разработке малых молекул в фармацевтике

Представления химических молекул, основанные на грамматиках.

Представления химических молекул, основанные на грамматиках.

Suggesting Natural Method Names to Check Name Consistencies

Suggesting Natural Method Names to Check Name Consistencies

Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors

Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Studying software evolution using topic models

Studying software evolution using topic models

Tree Structures and (Self)attention

Tree Structures and (Self)attention

Синтез речи в 2020

Синтез речи в 2020

All SMILES variational autoencoder for drug discovery

All SMILES variational autoencoder for drug discovery

AlphaGo to MuZero. Победа компьютера над человеком в интеллектуальных играх.

AlphaGo to MuZero. Победа компьютера над человеком в интеллектуальных играх.

Машинное обучение для анализа данных RNA-Seq

Машинное обучение для анализа данных RNA-Seq

Adversarial robustness of source code models

Adversarial robustness of source code models

Agent57: Outperforming the Atari Human Benchmark

Agent57: Outperforming the Atari Human Benchmark

Recommendation of commands in IDEs

Recommendation of commands in IDEs

Analyzing and Supporting Adaptation of Online Code Examples

Analyzing and Supporting Adaptation of Online Code Examples

AI vs. COVID-19

AI vs. COVID-19

Dream To Control

Dream To Control

Визуализация биологических данных методами сокращения размерности

Визуализация биологических данных методами сокращения размерности

Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code

Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code

Code Generation as a Dual Task of Code Summarization

Code Generation as a Dual Task of Code Summarization

Почему иерархическое обучение (иногда) работает?

Почему иерархическое обучение (иногда) работает?

An Overview and Analysis of Reading Comprehension Datasets

An Overview and Analysis of Reading Comprehension Datasets