Papers + Code - MIT-IBM Watson AI Lab

Ensemble Estimation of Information Divergence

Information Theory

Gradient Descent for Spiking Neural Networks

Deep Learning

Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions

Causal Inference

Action Centered Contextual Bandits

Deep Learning

BlockDrop: Dynamic Inference Paths in Residual Networks

Computer Vision

Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning

Robustness Natural Language Processing

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Efficient AI Deep Learning

Learning to Separate Object Sounds by Watching Unlabeled Video

Computer Vision

The Sound of Pixels

Multimodal Learning Computer Vision

Learning to Teach in Cooperative Multiagent Reinforcement Learning

Multi-agent Systems Reinforcement Learning

Dialog-based Interactive Image Retrieval

Computer Vision

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation

Computer Vision Generative Models

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

Optimization Deep Learning

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

Robustness Optimization

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Computer Vision Few-shot Learning

Structured Adversarial Attack: Towards General Implementation and Better Interpretability

Robustness Explainability

Controllable Image-to-Video Translation: A Case Study on Facial Expression Generation

Generative Models

Deriving Machine Attention from Human Rationales

Deep Rationalization Natural Language Processing

emrQA: A Large Corpus for Question Answering on Electronic Medical Records

AI in Healthcare Natural Language Processing

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

Generative Models Graph Deep Learning

Learning Entropic Wasserstein Embeddings

Machine Learning Optimal Transport

signSGD via Zeroth-Order Oracle

Optimization Robustness

Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

Neuro-Symbolic AI Computer Vision

MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

AI in Healthcare Deep Learning

Experimental Design for Cost-Aware Learning of Causal Graphs

Causal Inference

StNet: Local and Global Spatial-Temporal Modeling for Action Recognition

Computer Vision Time Series

Co-regularized Alignment for Unsupervised Domain Adaptation

Transfer Learning Deep Learning

Unsupervised learning with contrastive latent variable models

Unsupervised Learning

Collective Online Learning of Gaussian Processes in Massive Multi-Agent Systems

Multi-agent Systems

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Generative Models Explainability

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks

Robustness

Scalable Graph Learning for Anti-Money Laundering: A First Look

AI in Finance Graph Deep Learning

Neural Network Robustness Certification with General Activation Functions

Robustness Deep Learning

Weakly Supervised Dense Event Captioning in Videos

Computer Vision

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

Robustness

Tight Certificates of Adversarial Robustness

Cybersecurity NeurIPS

Structural Supervision Improves Learning of Non-Local Grammatical Dependencies

Natural Language Processing

Revisiting RCNN: On Awakening the Classification Power of Faster RCNN

Computer Vision

Unsupervised learning by competing hidden units

PNAS Unsupervised Learning

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

Neuro-Symbolic AI Computer Vision

Bayesian Nonparametric Federated Learning of Neural Networks

Federated Learning

Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

Graph Deep Learning Natural Language Processing

Variational Russian Roulette for Deep Bayesian Nonparametrics

Deep Learning Bayesian Modeling

Write, Execute, Assess: Program Synthesis with a REPL

Program Synthesis

Deep Leakage from Gradients

Robustness Deep Learning

Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering

Computer Vision Time Series

Neural language models as psycholinguistic subjects: Representations of syntactic state

Natural Language Processing Time Series

Local Unsupervised Learning for Image Analysis

Unsupervised Learning Computer Vision

Defensive Quantization: When Efficiency Meets Robustness

Efficient AI Robustness

Watch, Reason and Code: Learning to Represent Videos Using Program

Computer Vision

Seeing What a GAN Cannot Generate

Generative Models

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

Lifelong Learning Transfer Learning

The Future of Work: How New Technologies Are Transforming Tasks

Future of Work

Cross-channel Communication Networks

Deep Learning Computer Vision

SimVAE: Simulator-Assisted Training for Interpretable Generative Models

Generative Models Explainability

Reverse-engineering causal graphs with soft interventions

Causal Inference

New tricks from old dogs: multi-source transfer learning

Transfer Learning Explainability

Class-wise rationalization: teaching AI to weigh pros and cons

Natural Language Processing Deep Rationalization

Causal inference is expensive. Here’s an algorithm for fixing that.

Causal Inference

Visual Concept-Metaconcept Learning

Neuro-Symbolic AI

Alleviating label switching with optimal transport

Optimal Transport

Topics are more meaningful than words. AI for comparative literature.

Natural Language Processing Optimal Transport

Imitation learning from observations

Deep Learning

Using geometry to understand documents

Natural Language Processing

SPAHM: Parameter matching for model fusion

Bayesian Modeling

Big-Little-Video-Net: Work smarter, not harder, for video understanding

Computer Vision

ZO-AdaMM: Derivative-free optimization for black-box problems

Optimization NeurIPS

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

Deep Learning Bayesian Modeling

Embedding Compression with Isotropic Iterative Quantization

Natural Language Processing

Automating machine learning with a joint selection framework

AutoML Efficient AI

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

Graph Deep Learning AAAI

A content-aware attack generator for AI cybersecurity

Adversarial Machine Learning Cybersecurity

A unifying framework for expectation-aware AI planning

Automated Planning

Reading between the lines with graph deep learning for NLP

Natural Language Processing AAAI

Online AI planning with graph neural networks and adaptive scheduling

Automated Planning Graph Deep Learning

On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization

Optimization

Sentence Embedding Alignment for Lifelong Relation Extraction

Natural Language Processing Lifelong Learning

Moments in Time Dataset: one million videos for event understanding

Computer Vision Multimodal Learning

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

AI in Finance Graph Deep Learning

Self-supervised Moving Vehicle Tracking with Stereo Sound

Multimodal Learning Computer Vision

The sound of motions

Computer Vision

TSM: Temporal Shift Module for Efficient Video Understanding

Efficient AI Computer Vision

Graph Convolutional Networks for Temporal Action Localization

Graph Deep Learning Computer Vision

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method

Optimization Robustness

Reasoning about Human-Object Interactions through Dual Attention Networks

Computer Vision

LaSO: Label-Set Operations networks for multi-label few-shot learning

Computer Vision Few-shot Learning

SpotTune: Transfer Learning through Adaptive Fine-tuning

Computer Vision Transfer Learning

RepMet: Representative-based metric learning for classification and one-shot object detection

Computer Vision

ObjectNet: A bias-controlled dataset object recognition

Computer Vision NeurIPS

Point-Voxel CNN for Efficient 3D Deep Learning

Efficient AI Deep Learning

CASTER: An AI framework for preventing adverse reactions to medication

AI in Healthcare AAAI

Adversarial Robustness vs Model Compression, or Both?

Robustness

Reshaping Diverse Planning

Automated Planning

Deep Symbolic Superoptimization Without Human Knowledge

Neuro-Symbolic AI Optimization

A Closer Look at Deep Policy Gradients

Optimization ICLR

Deep Audio Priors Emerge From Harmonic Convolutional Networks

Audio Processing Deep Learning

Once for All: Train One Network and Specialize it for Efficient Deployment

Efficient AI ICLR

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

Reinforcement Learning Optimization

Generative Ratio Matching Networks

Generative Models Deep Learning

Learning Rate Rewinding for elegant neural network pruning

Efficient AI Deep Learning

Layer-wise federated learning with FedMA

Federated Learning

Learning to learn with distributional signatures for text data

Natural Language Processing Transfer Learning

Fast and efficient black-box testing for AI cybersecurity

Cybersecurity Robustness

CLEVRER: The first video dataset for neuro-symbolic reasoning

Neuro-Symbolic AI Computer Vision

Why Gradient Clipping accelerates training for neural networks

Optimization Efficient AI

SenSR: the first practical algorithm for individual fairness

AI Fairness Robustness

Sign-OPT: Defending the hard-label black-box cyber attack

Cybersecurity Adversarial Machine Learning

Bio-Inspired Hashing for Unsupervised Similarity Search

ICML Neuroscience

Universal Domain Adaptation through Self Supervision

Transfer Learning Unsupervised Learning

MCUNet: Tiny Deep Learning on IoT Devices

Deep Learning Efficient AI

Approximate Cross-Validation for Structured Models

Bayesian Modeling

AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

Computer Vision Multimodal Learning

Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation

NeurIPS

Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes

NeurIPS

The Lottery Ticket Hypothesis for the Pre-trained BERT Networks

Efficient AI

Continuous Regularized Wasserstein Barycenters

Optimal Transport

Tiny Transfer Learning: Towards Memory-Efficient On-Device Learning

Efficient AI

Auxiliary Task Reweighting for Minimum-data Learning

NeurIPS

Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment

NeurIPS

Simulating a Primate Visual Cortex at the Front of CNNs Improves Robustness to Adversarial Attacks and Image Corruptions

Neuroscience

Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance

Bayesian Modeling

Training Stronger Baselines for Learning to Optimize

Optimization

Applications of Common Entropy in Causal Inference

Causal Inference

Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning

Causal Inference

Entropic Causal Inference: Identifiability and Finite Sample Results

Causal Inference

Higher-Order Certification For Randomized Smoothing

Optimization

Debiased Contrastive Learning

NeurIPS

Learning Restricted Boltzmann Machines With Sparse Latent Variables

NeurIPS

Differentiable Augmentation for Data-Efficient GAN Training

Optimization

Robust Federated Learning: The Case of Affine Distribution Shifts

Federated Learning

Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth

NeurIPS

Online Bayesian Goal Inference for Boundedly-Rational Planning Agents

NeurIPS

Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models

NeurIPS

Active Structure Learning of Causal DAGs via Directed Clique Trees

Causal Inference

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models

NeurIPS

Fairness in Streaming Submodular Maximization: Algorithms and Hardness

NeurIPS

Testing Determinantal Point Processes

NeurIPS

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

NeurIPS

Learning Physical Graph Representations from Visual Scenes

NeurIPS

Black Loans Matter: Fighting Bias for AI Fairness in Lending

AI Fairness AI in Finance

The Computational Limits of Deep Learning

Efficient AI Deep Learning

Do Neural Networks Really Need to Be So Big?

Efficient AI Deep Learning

Can a Fruit Fly Learn Word Embeddings?

ICLR Computation and Launguage

Large Associative Memory Problem in Neurobiology and Machine Learning

ICLR

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

ICML Machine Learning

Dense Associative Memory for Pattern Recognition

NeurIPS Neural and Evolutionary Computing

Adversarial Option-Aware Hierarchical Imitation Learning

ICML Machine Learning

Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study

TACL Computation and Launguage

Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations

NAACL Computation and Launguage

Multilingual BERT Post-Pretraining Alignment

NAACL Computation and Launguage

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning

EMNLP Computation and Launguage

Outlier-Robust Optimal Transport

ICML

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

ICML

Auto-NBA: Efficient and Effective Search Over The Joint Space of Networks, Bitwidths, and Accelerators

ICML

Global Prosody Style Transfer Without Text Transcriptions

ICML

AGENT: A Benchmark for Core Psychological Reasoning

ICML Artificial Intelligence

Complementary Evidence Identification in Open-Domain Question Answering

EACL Computation and Launguage

Learning-based Support Estimation In Sublinear Time

ICLR

Anycost GANs for Interactive Image Synthesis and Editing

CVPR Computer Vision

Black-box Explanation of Object Detectors via Saliency Maps

CVPR Computer Vision

Fair Selective Classification Via Sufficiency

ICML

Statistical inference for individual fairness

ICLR Machine Learning

Individually Fair Rankings

ICLR AI Fairness

Individually Fair Gradient Boosting

ICLR Machine Learning

SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness

ICLR Machine Learning

MVFNet: Multi-View Fusion Network for Efficient Video Recognition

AAAI Computer Vision

Augmenting Policy Learning with Routines Discovered from a Demonstration

AAAI Machine Learning

RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning.

AAAI Computer Vision

Learning Task Decomposition with Ordered Memory Policy Network

ICLR

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

ICLR Computer Vision

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics.

ICLR Machine Learning

Hidden Cost of Randomized Smoothing

AISTATS Machine Learning

Neural Network Control Policy Verification with Persistent Adversarial Perturbations

ICML Machine Learning

Fine-grained Angular Contrastive Learning with Coarse Labels

CVPR Computer Vision

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

ECCV Computer Vision

Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions

ICML

Why Do These Match? Explaining the Behavior of Image Similarity Models

ECCV Computer Vision

Self-Progressing Robust Training

AAAI Machine Learning

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

CVPR Computer Vision

Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules

CVPR Computer Vision

Separating Skills and Concepts for Novel Visual Question Answering

CVPR

High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation

AISTATS Machine Learning

Parameter-Efficient Transfer Learning with Diff Pruning

Computation and Launguage

Sequence-Level Mixed Sample Data Augmentation

EMNLP Computation and Launguage

Generating Adversarial Computer Programs using Optimized Obfuscations

ICLR Machine Learning

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

ICLR Machine Learning

Robust Overfitting may be mitigated by properly learned smoothening

ICLR

Ordering-based causal structure learning in the presence of latent variables

AISTATS Statistics

Causal structure discovery from distributions arising from mixtures of DAGs

ICML Machine Learning

Online Optimal Control with Affine Constraints

AAAI

A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving

AAAI Artificial Intelligence

Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition

CVPR Computer Vision

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices

AAAI Machine Learning

Lite Transformer with Long-Short Range Attention

ICLR Computation and Launguage

GAN Compression: Efficient Architectures for Interactive Conditional GANs

CVPR Computer Vision

Wasserstein Style Transfer

AISTATS Machine Learning

Unsupervised Hierarchical Matching with Optimal Transport over Hyperbolic Spaces

AISTATS

Heterogeneous Knowledge Transfer via Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning

AAAI

Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics

ICLR

Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors

AAAI Machine Learning

Understanding Behavior of Clinical Models under Domain Shifts

Machine Learning Artificial Intelligence

Fashion IQ: A New Dataset towards Retrieving Images by Natural Language Feedback

CVPR Computer Vision

We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos

ECCV Computer Vision

StarNet: towards weakly supervised few-shot detection and explainable few-shot classification

AAAI Computer Vision

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

CVPR Computer Vision

Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation

ECCV Computer Vision

Do GANs always have Nash equilibria?

ICML

TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

ECCV Computer Vision

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

ECCV Computer Vision

A Broader Study of Cross-Domain Few-Shot Learning

ECCV Computer Vision

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

ECCV

Foley Music: Learning to Generate Music from Videos

ECCV Computer Vision

Two Simple Ways to Learn Individual Fairness Metrics from Data

ICML Machine Learning

Semi-Supervised Action Recognition with Temporal Contrastive Learning

CVPR Computer Vision

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

Computation and Launguage Machine Learning

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

ECCV Computer Vision

Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning

CVPR Computer Vision

Non-Adversarial Video Synthesis with Learned Priors

CVPR Computer Vision

NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search

AAAI Computer Vision

VA-RED^2: Video Adaptive Redundancy Reduction

ICLR Computer Vision

AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition

ICLR Computer Vision

Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning

ICLR

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

ECCV Computer Vision

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

ECCV

Adversarial T-shirt! Evading Person Detectors in A Physical World

ECCV Computer Vision

Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport

AAAI Machine Learning

Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models

Machine Learning Social Networks

Linear Mode Connectivity and The Lottery Ticket Hypothesis

ICML Machine Learning

Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case

ICML Machine Learning

Curvature-corrected learning dynamics in deep neural networks

ICML

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing

ICML Machine Learning

Model Fusion with Kullback–Leibler Divergence

ICML

MSRP Industry Night: Career Exploration with IBM