Papers
Thu 12 May 2022
160 papers
- KASAM: Spline Additive Models for Function ApproximationLLM safety and security → Machine unlearning
- How to Combine Membership-Inference Attacks on Multiple Updated ModelsLLM safety and security → Membership inference attacks
- Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-IdentificationKnowledge distillation → General knowledge distillation methods
- A Generalist AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
- e-CARE: a New Dataset for Exploring Explainable Causal ReasoningLLM reasoning → Causal reasoning in LLMs
- The Different Faces of AI Ethics Across the World: A Principle-Implementation Gap Analysis
- Global geomagnetic perturbation forecasting using Deep Learning
- Vision Transformer: Vit and its Derivatives
- Evolving SimGANs to Improve Abnormal Electrocardiogram Classification
- Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
- Deep Learning of Chaotic Systems from Partially-Observed Data
- Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
- ScAN: Suicide Attempt and Ideation Events Dataset
- Mondrian Forest for Data Stream Classification Under Memory Constraints
- Unsupervised Driving Behavior Analysis using Representation Learning and Exploiting Group-based Training
- Near out-of-distribution detection for low-resolution radar micro-Doppler signatures
- Minimal Neural Network Models for Permutation Invariant Agents
- Feature and Instance Joint Selection: A Reinforcement Learning Perspective
- Relating Information and Proof
- Distribution-Aware Graph Representation Learning for Transient Stability Assessment of Power System
- Outlier Detection for Multi-Network Data
- LANTERN-RD: Enabling Deep Learning for Mitigation of the Invasive Spotted Lanternfly
- α-GAN: Convergence and Estimation Guarantees
- PVS Embeddings of Propositional and Quantified Modal Logic
- Deep Learning for Prawn Farming: Forecasting and Anomaly Detection
- Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages
- Warm-starting DARTS using meta-learning
- Interpretable Climate Change Modeling With Progressive Cascade Networks
- On the Economics of Multilingual Few-shot Learning: Modeling the Cost-Performance Trade-offs of Machine Translated and Manual Data
- Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
- Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations
- Collaborative Multi-agent Stochastic Linear Bandits
- Multi-Environment Meta-Learning in Stochastic Linear Bandits
- Noun2Verb: Probabilistic frame semantics for word class conversion
- Detailed Balanced Chemical Reaction Networks as Generalized Boltzmann Machines
- Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments
- An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings
- Probabilistic Estimation of Instantaneous Frequencies of Chirp Signals
- Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
- Overparameterization Improves StyleGAN Inversion
- Using Natural Sentences for Understanding Biases in Language Models
- Improving Sequential Query Recommendation with Immediate User Feedback
- Integrating User and Item Reviews in Deep Cooperative Neural Networks for Movie Recommendation
- Adaptive Block Floating-Point for Analog Deep Learning Hardware
- Topologically-Aware Deformation Fields for Single-View 3D Reconstruction
- Lifting the Curse of Multilinguality by Pre-training Modular Transformers
- ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training
- FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue
- Computing Programs for Generalized Planning as Heuristic Search
- 3D Moments from Near-Duplicate Photos
- Learned Vertex Descent: A New Direction for 3D Human Model Fitting
- What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics
- Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?
- SIBILA: A novel interpretable ensemble of general-purpose machine learning models applied to medical contexts
- Simple Open-Vocabulary Object Detection with Vision Transformers
- The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning
- Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets
- Exploiting symmetry in variational quantum machine learning
- Contingency-constrained economic dispatch with safe reinforcement learning
- CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
- kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval
- F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
- Predicting Human Psychometric Properties Using Computational Language Models
- Embodied vision for learning object representations
- Image Segmentation with Topological Priors
- Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection
- Using dependency parsing for few-shot learning in distributional semantics
- Dynamic Prefix-Tuning for Generative Template-based Event Extraction
- Localized Vision-Language Matching for Open-vocabulary Object Detection
- Neural Network-based OFDM Receiver for Resource Constrained IoT Devices
- Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
- TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
- Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?
- Multimodal Indoor Localisation for Measuring Mobility in Parkinson's Disease using Transformers
- Fair NLP Models with Differentially Private Text Encoders
- Framework for inferring empirical causal graphs from binary data to support multidimensional poverty analysis
- Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models
- Addressing Census data problems in race imputation via fully Bayesian Improved Surname Geocoding and name supplements
- Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
- One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
- Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction
- Findings of the Shared Task on Offensive Span Identification from Code-Mixed Tamil-English Comments
- Secure Aggregation for Federated Learning in Flower
- Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language
- Equivariant quantum circuits for learning on weighted graphs
- Social learning via actions in bandit environments
- Tensor-based Emotion Editing in the StyleGAN Latent Space
- Deep morphological recognition of kidney stones using intra-operative endoscopic digital videos
- SimRelUz: Similarity and Relatedness scores as a Semantic Evaluation dataset for Uzbek language
- Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
- Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation
- Efficient and Training-Free Control of Language Generation
- D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation
- DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain
- Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling
- Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization
- Learning Generalized Policies Without Supervision Using GNNs
- Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
- Blueprint Separable Residual Network for Efficient Image Super-Resolution
- Controlling Formality in Low-Resource NMT with Domain Adaptation and Re-Ranking: SLT-CDT-UoS at IWSLT2022
All 160
- Towards Answering Open-ended Ethical Quandary Questions
- Controlling chaotic itinerancy in laser dynamics for reinforcement learning
- "Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation
- MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
- TaDeR: A New Task Dependency Recommendation for Project Management Platform
- A Computational Acquisition Model for Multimodal Word Categorization
- Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer
- FPSRS: A Fusion Approach for Paper Submission Recommendation System
- GPN: A Joint Structural Learning Framework for Graph Neural Networks
- Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning
- Subgroup discovery of Parkinson's Disease by utilizing a multi-modal smart device system
- Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects
- Communicative Subgraph Representation Learning for Multi-Relational Inductive Drug-Gene Interaction Prediction
- Automated Audio Captioning: An Overview of Recent Progress and New Challenges
- Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
- SimCPSR: Simple Contrastive Learning for Paper Submission Recommendation System
- Ensemble Clustering via Co-association Matrix Self-enhancement
- Virtual twins of nonlinear vibrating multiphysics microstructures: physics-based versus deep learning-based approaches
- Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images
- Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation
- Group R-CNN for Weakly Semi-supervised Object Detection with Points
- Fall detection using multimodal data
- Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry
- Building Facade Parsing R-CNN
- Comments on: "Hybrid Semiparametric Bayesian Networks"
- Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real World
- Machine Learning Workflow to Explain Black-box Models for Early Alzheimer's Disease Classification Evaluated for Multiple Datasets
- NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension
- Mitigating Gender Stereotypes in Hindi and Marathi
- Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation
- Weakly-Supervised Action Detection Guided by Audio Narration
- Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction
- A Chit-Chats Enhanced Task-Oriented Dialogue Corpora for Fuse-Motive Conversation Systems
- E-Mail Assistant -- Automation of E-Mail Handling and Management using Robotic Process Automation
- Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation
- Training Uncertainty-Aware Classifiers with Conformalized Deep Learning
- Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating
- Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio
- View Synthesis with Sculpted Neural Points
- Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
- AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling
- S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization
- Comparing Open Arabic Named Entity Recognition Tools
- Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos
- AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
- An MMSE Lower Bound via Poincar'e Inequality
- Bi-level Alignment for Cross-Domain Crowd Counting
- A Survey of Risk-Aware Multi-Armed Bandits
- Supplementary Material: Implementation and Experiments for GAU-based Model
- Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images
- Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound
- NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition
- Feature Extractor Stacking for Cross-domain Few-shot Learning
- Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling
- Privacy-Preserving Distributed Machine Learning Made Faster
- Continuous wavelet transform of multiview images using wavelets based on voxel patterns
- Representation Learning for Context-Dependent Decision-Making
- Open Vocabulary Extreme Classification Using Generative Models
- Performing Video Frame Prediction of Microbial Growth with a Recurrent Neural Network
- AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task