Papers
Thu 3 Jun 2021
212 papers
- Offline Reinforcement Learning as One Big Sequence Modeling ProblemWorld models → Latent dynamics models and model-based RL +1
- Defending Against Backdoor Attacks in Natural Language GenerationLLM safety and security → Backdoor and data poisoning attacks
- E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Feeling of Presence Maximization: mmWave-Enabled Virtual Reality Meets Deep Reinforcement Learning
- Nonuniform Defocus Removal for Image Classification
- Realistic molecule optimization on a learned graph manifold
- Surgical task expertise detected by a self-organizing neural network map
- A Framework for Discovering Optimal Solutions in Photonic Inverse Design
- MICo: Improved representations via sampling-based state similarity for Markov decision processes
- PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking (Accepted as an extended abstract in JRDB-ACT Workshop at CVPR21)
- Attention mechanisms and deep learning for machine vision: A survey of the state of the art
- Self-Guided Contrastive Learning for BERT Sentence Representations
- Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems
- Causality in Neural Networks -- An Extended Abstract
- Decentralised Approach for Multi Agent Path Finding
- Fair Machine Learning under Limited Demographically Labeled Data
- Stochastic Whitening Batch Normalization
- Influence Estimation and Maximization via Neural Mean-Field Dynamics
- Defending Democracy: Using Deep Learning to Identify and Prevent Misinformation
- Homological Time Series Analysis of Sensor Signals from Power Plants
- Linear regression with partially mismatched data: local search with theoretical guarantees
- Learning from Counterfactual Links for Link Prediction
- nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?
- Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation
- Modeling Communication to Coordinate Perspectives in Cooperation
- Privately Learning Mixtures of Axis-Aligned Gaussians
- Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey
- The Signed Cumulative Distribution Transform for 1-D Signal Analysis and Classification
- Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention
- Syntax-augmented Multilingual BERT for Cross-lingual Transfer
- The Algorithmic Phase Transition of Random k-SAT for Low Degree Polynomials
- A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms
- How to Adapt Your Pretrained Multilingual Model to 1600 Languages
- A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
- A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals
- Winning the War by (Strategically) Losing Battles: Settling the Complexity of Grundy-Values in Undirected Geography
- Finding and Fixing Spurious Patterns with Explanations
- Influence of cognitive, geographical, and collaborative proximity on knowledge production of Canadian nanotechnology
- Embedded Deep Regularized Block HSIC Thermomics for Early Diagnosis of Breast Cancer
- A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks
- Semi-Empirical Objective Functions for MCMC Proposal Optimization
- Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels
- A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
- Shape-Preserving Dimensionality Reduction : An Algorithm and Measures of Topological Equivalence
- Adaptive Epidemic Forecasting and Community Risk Evaluation of COVID-19
- Unsupervised Learning of General-Purpose Embeddings for Code Changes
- A diachronic evaluation of gender asymmetry in euphemism
- Language Embeddings for Typology and Cross-lingual Transfer Learning
- Solving Schr"odinger Bridges via Maximum Likelihood
- Improving Neural Network Robustness via Persistency of Excitation
- LGBTQ-AI? Exploring Expressions of Gender and Sexual Orientation in Chatbots
- Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
- Learning to Draw: Emergent Communication through Sketching
- The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
- Towards Learning to Play Piano with Dexterous Hands and Touch
- Anticipative Video Transformer
- DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
- Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits
- Single Image Depth Prediction with Wavelet Decomposition
- Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
- Nonlinear Matrix Approximation with Radial Basis Function Components
- A Dataset and Baselines for Multilingual Reply Suggestion
- Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability
- Attack Prediction using Hidden Markov Model
- Provably Secure Generative Linguistic Steganography
- A Case Study of Spanish Text Transformations for Twitter Sentiment Analysis
- Individual vs. Joint Perception: a Pragmatic Model of Pointing as Communicative Smithian Helping
- Toward Explainable Users: Using NLP to Enable AI to Understand Users' Perceptions of Cyber Attacks
- Gradient Boosted Binary Histogram Ensemble for Large-scale Regression
- Gaussian Processes on Hypergraphs
- ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics
- CCPM: A Chinese Classical Poetry Matching Dataset
- DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations
- Safe RAN control: A Symbolic Reinforcement Learning Approach
- Machine Learning and Variational Algorithms for Lattice Field Theory
- SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain
- NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
- Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
- A Survey on Optimal Transport for Machine Learning: Theory and Applications
- LyricJam: A system for generating lyrics for live instrumental music
- Multiplierless MP-Kernel Machine For Energy-efficient Edge Devices
- Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
- The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models
- The Smoothed Satisfaction of Voting Axioms
- Causal Effect Inference for Structured Treatments
- An Improved Model for Voicing Silent Speech
- A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
- GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
- Sample Selection Bias in Evaluation of Prediction Performance of Causal Models
- Convolutional Neural Network(CNN/ConvNet) in Stock Price Movement Prediction
- SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networks
- Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
- You Never Cluster Alone
- Robotic Inspection of Underground Utilities for Construction Survey Using a Ground Penetrating Radar
- Bayesian Inference for Gamma Models
- Representing Syntax and Composition with Geometric Transformations
- Denoising and Optical and SAR Image Classifications Based on Feature Extraction and Sparse Representation
- SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
All 212
- Simultaneous Multi-View Object Recognition and Grasping in Open-Ended Domains
- Heart Sound Classification Considering Additive Noise and Convolutional Distortion
- Robust Reference-based Super-Resolution via C2-Matching
- Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks
- Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation
- Statistical embedding: Beyond principal components
- Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning
- Continual Learning in Deep Networks: an Analysis of the Last Layer
- Effort-free Automated Skeletal Abnormality Detection of Rat Fetuses on Whole-body Micro-CT Scans
- Towards a Mathematical Theory of Abstraction
- Exploring Distantly-Labeled Rationales in Neural Network Models
- MINIMALIST: Mutual INformatIon Maximization for Amortized Likelihood Inference from Sampled Trajectories
- Partial Graph Reasoning for Neural Network Regularization
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
- TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data
- Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
- What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data
- The Contestation of Tech Ethics: A Sociotechnical Approach to Technology Ethics in Practice
- Machine learning models for DOTA 2 outcomes prediction
- Preparation of Many-body Ground States by Time Evolution with Variational Microscopic Magnetic Fields and Incomplete Interactions
- Bayesian Classifier Fusion with an Explicit Model of Correlation
- Less is More: Sparse Sampling for Dense Reaction Predictions
- Near Optimal Stochastic Algorithms for Finite-Sum Unbalanced Convex-Concave Minimax Optimization
- Template-Based Named Entity Recognition Using BART
- Reordering Examples Helps during Priming-based Few-Shot Learning
- Modeling Influencer Marketing Campaigns in Social Networks
- Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
- Lifetime policy reuse and the importance of task capacity
- Advances in Classifying the Stages of Diabetic Retinopathy Using Convolutional Neural Networks in Low Memory Edge Devices
- Auto-tagging of Short Conversational Sentences using Transformer Methods
- Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer
- Drivers' Manoeuvre Modelling and Prediction for Safe HRI
- Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
- GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture
- Fast improvement of TEM image with low-dose electrons by deep learning
- Towards urban scenes understanding through polarization cues
- Optimization Variance: Exploring Generalization Properties of DNNs
- Active learning for structural reliability: survey, general framework and benchmark
- Efficient methods for Gaussian Markov random fields under sparse linear constraints
- Lymph Node Graph Neural Networks for Cancer Metastasis Prediction
- SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction
- Semi-supervised Learning with Missing Values Imputation
- EmoDNN: Understanding emotions from short texts through a deep neural network ensemble
- Fingerprinting Fine-tuned Language Models in the Wild
- PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support
- Machine Learning Based Texture Analysis of Patella from X-Rays for Detecting Patellofemoral Osteoarthritis
- Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
- AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba
- Rich dynamics caused by known biological brain network features resulting in stateful networks
- Probabilistic Gradient Boosting Machines for Large-Scale Probabilistic Regression
- Convergent Graph Solvers
- Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism
- JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu
- APES: Audiovisual Person Search in Untrimmed Video
- Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot's Self-Disclosure in Conversational Recommendations
- Bandit Phase Retrieval
- Generalized Domain Adaptation
- Hierarchical Representation Learning for Markov Decision Processes
- Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
- Learning and Executing Re-usable Behaviour Trees from Natural Language Instruction
- LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification
- Corporate core values and social responsibility: What really matters to whom
- Projection-free Graph-based Classifier Learning using Gershgorin Disc Perfect Alignment
- Deceptive Level Generation for Angry Birds
- Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children's mindreading ability
- Cybersecurity Information Exchange with Privacy (CYBEX-P) and TAHOE -- A Cyberthreat Language
- Semantic Palette: Guiding Scene Generation with Class Proportions
- Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
- Sleeping Combinatorial Bandits
- Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
- Transferable Adversarial Examples for Anchor Free Object Detection
- Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout
- Imperceptible Adversarial Examples for Fake Image Detection
- NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
- Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
- A Discussion On the Validity of Manifold Learning
- Grounding Complex Navigational Instructions Using Scene Graphs
- Exploring Memorization in Adversarial Training
- Noisy student-teacher training for robust keyword spotting
- CT-Net: Channel Tensorization Network for Video Classification
- Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
- Automatically Detecting Cyberbullying Comments on Online Game Forums
- ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
- Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation
- Data-Driven Design-by-Analogy: State of the Art and Future Directions
- SIMLR: Machine Learning inside the SIR model for COVID-19 Forecasting
- A Systematic Investigation of KB-Text Embedding Alignment at Scale
- A Subspace-based Approach for Dimensionality Reduction and Important Variable Selection
- Cross-Network Learning with Partially Aligned Graph Convolutional Networks
- To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text
- The Limitations of Limited Context for Constituency Parsing
- A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes
- Discriminative Reasoning for Document-level Relation Extraction
- Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?
- CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
- Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
- Comparing Acoustic-based Approaches for Alzheimer's Disease Detection
- Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
- When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
- SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation
- MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding
- Luna: Linear Unified Nested Attention
- PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
- BERT meets LIWC: Exploring State-of-the-Art Language Models for Predicting Communication Behavior in Couples' Conflict Interactions
- Deconfounded Video Moment Retrieval with Causal Intervention
- Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting
- Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs
- Normalizing Flows for Knockoff-free Controlled Feature Selection
- "You made me feel this way": Investigating Partners' Influence in Predicting Emotions in Couples' Conflict Interactions using Speech Data
- Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution
- Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework
- Question Answering Over Temporal Knowledge Graphs