Papers
Sat 5 Jun 2021
100 papers
- Zero-shot Task Adaptation using Natural LanguageOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- A Variational Perspective on Diffusion-Based Generative Models and Score MatchingDiffusion models → Diffusion foundations and sampling
- VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds
- MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning
- Identifying Linked Fraudulent Activities Using GraphConvolution Network
- MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph
- Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
- Virtual Screening of Pharmaceutical Compounds with hERG Inhibitory Activity (Cardiotoxicity) using Ensemble Learning
- Impact of data-splits on generalization: Identifying COVID-19 from cough and context
- Multi-Task Hierarchical Learning Based Network Traffic Analytics
- Causal Bandits with Unknown Graph Structure
- Escaping Saddle Points Faster with Stochastic Momentum
- Sensor Fusion-based GNSS Spoofing Attack Detection Framework for Autonomous Vehicles
- Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms
- Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks
- Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
- Forced Variational Integrator Networks for Prediction and Control of Mechanical Systems
- FedNL: Making Newton-Type Methods Applicable to Federated Learning
- Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
- Extracting Weighted Automata for Approximate Minimization in Language Modelling
- A Review of Machine Learning Classification Using Quantum Annealing for Real-world Applications
- Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
- Denoising Word Embeddings by Averaging in a Shared Space
- Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
- Controller Synthesis for Omega-Regular and Steady-State Specifications
- Neural dSCA: demixing multimodal interaction among brain areas during naturalistic experiments
- Learning Routines for Effective Off-Policy Reinforcement Learning
- Same State, Different Task: Continual Reinforcement Learning without Interference
- Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning
- k-Mixup Regularization for Deep Learning via Optimal Transport
- Spectral Temporal Graph Neural Network for Trajectory Prediction
- IM-META: Influence Maximization Using Node Metadata in Networks With Unknown Topology
- Tensor Normal Training for Deep Learning Models
- Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularization
- Empirically Evaluating Creative Arc Negotiation for Improvisational Decision-making
- Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
- BERTnesia: Investigating the capture and forgetting of knowledge in BERT
- Hierarchical Temperature Imaging Using Pseudo-Inversed Convolutional Neural Network Aided TDLAS Tomography
- Differentially Private Multi-Armed Bandits in the Shuffle Model
- Dynamic Resolution Network
- Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping
- Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
- Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization
- Context-Aware Sparse Deep Coordination Graphs
- Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
- A Deep Variational Bayesian Framework for Blind Image Deblurring
- Graph Infomax Adversarial Learning for Treatment Effect Estimation with Networked Observational Data
- A Generative Node-attribute Network Model for Detecting Generalized Structure
- Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
- RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
- Integrating Auxiliary Information in Self-supervised Learning
- Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness
- Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning
- An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification
- Convolutional Neural Networks with Gated Recurrent Connections
- Reinforcement Learning for Assignment Problem with Time Constraints
- Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?
- Region-aware Adaptive Instance Normalization for Image Harmonization
- Patch Slimming for Efficient Vision Transformers
- Tetrad: Actively Secure 4PC for Secure Training and Inference
- Numerical Composition of Differential Privacy
- Navigating to the Best Policy in Markov Decision Processes
- Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
- Multi-Camera Vehicle Counting Using Edge-AI
- Constrained Generalized Additive 2 Model with Consideration of High-Order Interactions
- On the Role of Entropy-based Loss for Learning Causal Structures with Continuous Optimization
- MergeDistill: Merging Pre-trained Language Models using Distillation
- Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation
- Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning
- Lifelong Learning of Hate Speech Classification on Social Media
- GraphMI: Extracting Private Graph Data from Graph Neural Networks
- Variational Leakage: The Role of Information Complexity in Privacy Leakage
- ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks
- Machine learning equipped web based disease prediction and recommender system
- An Attribute-Aligned Strategy for Learning Speech Representation
- T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing
- Points2Polygons: Context-Based Segmentation from Weak Labels Using Adversarial Networks
- Network Estimation by Mixing: Adaptivity and More
- Trajectory Optimization of Chance-Constrained Nonlinear Stochastic Systems for Motion Planning Under Uncertainty
- AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images
- Neural Distributed Source Coding
- Principal Bit Analysis: Autoencoding with Schur-Concave Loss
- Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding
- Solving hybrid machine learning tasks by traversing weight space geodesics
- Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains
- Motion Planning Transformers: A Motion Planning Framework for Mobile Robots
- BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
- On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
- IPS300+: a Challenging Multimodal Dataset for Intersection Perception System
- Learning Treatment Effects in Panels with General Intervention Patterns
- Radar-Camera Pixel Depth Association for Depth Completion
- Immediate Proximity Detection Using Wi-Fi-Enabled Smartphones
- Visual communication of object concepts at different levels of abstraction
- Robust Model Selection and Nearly-Proper Learning for GMMs
- GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
- PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
- Deep Bayesian Active Learning for Accelerating Stochastic Simulation
- Privacy-Preserving Training of Tree Ensembles over Continuous Data
- Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
- Heuristic-Guided Reinforcement Learning