Conferences
All Work
Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization
Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization
Efficient technique improves machine-learning models’ reliability
Efficient technique improves machine-learning models’ reliability
MIT News
↗
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint
S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint
Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
Convergent representations of computer programs in human and artificial neural networks
Convergent representations of computer programs in human and artificial neural networks
Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks
Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
How hard are computer vision datasets? Calibrating dataset difficulty to viewing time
How hard are computer vision datasets? Calibrating dataset difficulty to viewing time
Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs
Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs
MIT News
↗
Debugging foundation models for bias
Debugging foundation models for bias
IBM Research
↗
A simpler path to better computer vision
A simpler path to better computer vision
MIT News
↗
A far-sighted approach to machine learning
A far-sighted approach to machine learning
MIT News
↗
This AI can harness sound to reveal the structure of unseen spaces
This AI can harness sound to reveal the structure of unseen spaces
Popular Science
↗
Perceptron: AI that sees with sound, learns to walk and predicts seismic physics
Perceptron: AI that sees with sound, learns to walk and predicts seismic physics
TechCrunch
↗
In machine learning, synthetic data can offer real performance improvements
In machine learning, synthetic data can offer real performance improvements
MIT News
↗
Learning on the edge
Learning on the edge
MIT News
↗
Converting several audio streams into one voice makes it easier for AI to learn
Converting several audio streams into one voice makes it easier for AI to learn
IBM Research
↗
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
More Language, Less Labeling with Kate Saenko
More Language, Less Labeling with Kate Saenko
This Week in Machine Learning & AI (TWIML) podcast
↗
A safer, lower-cost alternative to real data for pretraining computer vision models
A safer, lower-cost alternative to real data for pretraining computer vision models
IBM Research blog
↗
MIT engineers devise a recipe for improving any autonomous robotic system
MIT engineers devise a recipe for improving any autonomous robotic system
MIT News
↗
Keeping web-browsing data safe from hackers
Keeping web-browsing data safe from hackers
MIT News
↗
Hallucinating to better text translation
Hallucinating to better text translation
MIT News
↗
On the road to cleaner, greener, and faster driving
On the road to cleaner, greener, and faster driving
MIT News
↗
Artificial intelligence system learns concepts shared across video, audio, and text
Artificial intelligence system learns concepts shared across video, audio, and text
MIT News
↗
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
Does this artificial intelligence think like a human?
Does this artificial intelligence think like a human?
MIT News
↗
Generating new molecules with graph grammar
Generating new molecules with graph grammar
MIT News
↗
Solving the challenges of robotic pizza-making
Solving the challenges of robotic pizza-making
MIT News
↗
Better learning through ‘complex dough-manipulation’
Better learning through ‘complex dough-manipulation’
Tech Crunch
↗
Neuro-symbolic AI brings us closer to machines with common sense
Neuro-symbolic AI brings us closer to machines with common sense
BD TechTalks
↗
Using artificial intelligence to find anomalies hiding in massive datasets
Using artificial intelligence to find anomalies hiding in massive datasets
MIT News
↗
TinyML is bringing neural networks to small microcontrollers
TinyML is bringing neural networks to small microcontrollers
TechTalks
↗
Clever Compression of Some Neural Nets Improves Performance
Clever Compression of Some Neural Nets Improves Performance
IEEE Spectrum
↗
AI Researchers Fight Noise by Turning to Biology
AI Researchers Fight Noise by Turning to Biology
Quanta Magazine
↗
PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
Machine learning speeds up vehicle routing
Machine learning speeds up vehicle routing
MIT News
↗
Generating a realistic 3D world
Generating a realistic 3D world
MIT News
↗
Toward speech recognition for uncommon spoken languages
Toward speech recognition for uncommon spoken languages
MIT News
↗
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
IBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021
IBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021
IBM Research
↗
Can you teach AI common sense?
Can you teach AI common sense?
VentureBeat
↗
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning
Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning
StarNet: towards weakly supervised few-shot detection and explainable few-shot classification
StarNet: towards weakly supervised few-shot detection and explainable few-shot classification
We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos
We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos
Fashion IQ: A New Dataset towards Retrieving Images by Natural Language Feedback
Fashion IQ: A New Dataset towards Retrieving Images by Natural Language Feedback
Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
Heterogeneous Knowledge Transfer via Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning
Heterogeneous Knowledge Transfer via Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules
Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Neural Network Control Policy Verification with Persistent Adversarial Perturbations
Neural Network Control Policy Verification with Persistent Adversarial Perturbations
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning.
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning.
Augmenting Policy Learning with Routines Discovered from a Single Demonstration
Augmenting Policy Learning with Routines Discovered from a Single Demonstration
Auto-NBA: Efficient and Effective Search Over The Joint Space of Networks, Bitwidths, and Accelerators
Auto-NBA: Efficient and Effective Search Over The Joint Space of Networks, Bitwidths, and Accelerators
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
AI Algorithms Are Slimming Down to Fit in Your Fridge
AI Algorithms Are Slimming Down to Fit in Your Fridge
WIRED
↗
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
Researchers Figured Out How to Fit More AI Than Ever onto Internet of Things Microchips
Researchers Figured Out How to Fit More AI Than Ever onto Internet of Things Microchips
Morning Brew
↗
Is neuroscience the key to protecting AI from adversarial attacks?
Is neuroscience the key to protecting AI from adversarial attacks?
TechTalks
↗
Neuroscientists find a way to make object-recognition models perform better
Neuroscientists find a way to make object-recognition models perform better
MIT News
↗
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Simulating a Primate Visual Cortex at the Front of CNNs Improves Robustness to Adversarial Attacks and Image Corruptions
Simulating a Primate Visual Cortex at the Front of CNNs Improves Robustness to Adversarial Attacks and Image Corruptions
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
System brings deep learning to “internet of things” devices
System brings deep learning to “internet of things” devices
MIT News
↗
This hybrid AI system can understand causality in controlled environments
This hybrid AI system can understand causality in controlled environments
TheNextWeb
↗
Learning to learn with distributional signatures for text data
Learning to learn with distributional signatures for text data
Online AI planning with graph neural networks and adaptive scheduling
Online AI planning with graph neural networks and adaptive scheduling
CAG: A Real-Time Low-Cost Enhanced-Robustness High-Transferability Content-Aware Adversarial Attack Generator
CAG: A Real-Time Low-Cost Enhanced-Robustness High-Transferability Content-Aware Adversarial Attack Generator
Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions
Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
MAi : An Intelligent Model Acquisition Interface for Interactive Specification of Dialogue Agents
MAi : An Intelligent Model Acquisition Interface for Interactive Specification of Dialogue Agents
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation