Papers
Tue 18 Oct 2022
242 papers
- JECC: Commonsense Reasoning Tasks Derived from Interactive FictionsLLM reasoning → Reasoning benchmarks and evaluation
- Aligning MAGMA by Few-Shot Learning and FinetuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
- Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy LearningOffline RL and imitation learning from data → Imitation learning methods
- ELASTIC: Numerical Reasoning with Adaptive Symbolic CompilerLLM reasoning → Mathematical reasoning
- Perceptual Grouping in Contrastive Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Differentially Private Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Not All Poisons are Created Equal: Robust Training against Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
- On effects of Knowledge Distillation on Transfer LearningKnowledge distillation → General knowledge distillation methods
- Improving Adversarial Robustness by Contrastive Guided Diffusion ProcessDiffusion models → Robustness, privacy and adversarial aspects
- SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLPKnowledge distillation → Graph neural network distillation
- Planning for Sample Efficient Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- Fine-mixing: Mitigating Backdoors in Fine-tuned Language ModelsLLM safety and security → Backdoor and data poisoning attacks
- Hierarchical Model-Based Imitation Learning for Planning in Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Deep Data Augmentation for Weed Recognition Enhancement: A Diffusion Probabilistic Model and Transfer Learning Based ApproachDiffusion models → Inverse problems and image restoration
- Large Discourse Treebanks from Scalable Distant Supervision
- Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
- Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters
- PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction
- DAGKT: Difficulty and Attempts Boosted Graph-based Knowledge Tracing
- Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
- Using Deep Learning to Find the Next Unicorn: A Practical Synthesis
- Kurdish Handwritten Character Recognition using Deep Learning Techniques
- Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
- Generalization Properties of Decision Trees on Real-valued and Categorical Features
- An out-of-distribution discriminator based on Bayesian neural network epistemic uncertainty
- Analysis of Master Vein Attacks on Finger Vein Recognition Systems
- Soil moisture estimation from Sentinel-1 interferometric observations over arid regions
- Deep Multi-Representation Model for Click-Through Rate Prediction
- Towards Practical Explainability with Cluster Descriptors
- Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification
- Multi-Source Transformer Architectures for Audiovisual Scene Classification
- Catch-22s of reservoir computing
- Exclusive Supermask Subnetwork Training for Continual Learning
- Optimizing Hierarchical Image VAEs for Sample Quality
- Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation
- Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
- BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds
- Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
- Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation
- Simple and Effective Unsupervised Speech Translation
- Application Performance Modeling via Tensor Completion
- Landmark Enforcement and Style Manipulation for Generative Morphing
- Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training
- Inference in conditioned dynamics through causality restoration
- Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering
- Intra-Source Style Augmentation for Improved Domain Generalization
- Granger causal inference on DAGs identifies genomic loci regulating transcription
- MedCLIP: Contrastive Learning from Unpaired Medical Images and Text
- Computational pathology in renal disease: a comprehensive perspective
- Nonparametric Quantile Regression: Non-Crossing Constraints and Conformal Prediction
- Uncertainty in Extreme Multi-label Classification
- TEFL: Turbo Explainable Federated Learning for 6G Trustworthy Zero-Touch Network Slicing
- Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs
- Graph Attention Networks Unveil Determinants of Intra- and Inter-city Health Disparity
- Class-Level Confidence Based 3D Semi-Supervised Learning
- PERI: Part Aware Emotion Recognition In The Wild
- Proximal Learning With Opponent-Learning Awareness
- Interpolated SelectionConv for Spherical Images and Surfaces
- Initial Orbit Determination from Only Heading Measurements
- Transferable Unlearnable Examples
- Trixi the Librarian
- A Survey of Active Learning for Natural Language Processing
- Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
- Optimisation & Generalisation in Networks of Neurons
- How to Boost Face Recognition with StyleGAN?
- Auditing YouTube's Recommendation Algorithm for Misinformation Filter Bubbles
- Why people judge humans differently from machines: The role of perceived agency and experience
- Detecting and analyzing missing citations to published scientific entities
- Multivariate outlier explanations using Shapley values and Mahalanobis distances
- Combination of Raman spectroscopy and chemometrics: A review of recent studies published in the Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy Journal
- Explainable bilevel optimization: an application to the Helsinki deblur challenge
- Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
- A Tri-Layer Plugin to Improve Occluded Detection
- SafeText: A Benchmark for Exploring Physical Safety in Language Models
- Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion
- Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning
- The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks
- How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
- ARAH: Animatable Volume Rendering of Articulated Human SDFs
- Understanding COVID-19 Vaccine Campaign on Facebook using Minimal Supervision
- Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR
- ULN: Towards Underspecified Vision-and-Language Navigation
- Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation
- On Classification Thresholds for Graph Attention with Edge Features
- Log-linear Guardedness and its Implications
- Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis
- Otsu based Differential Evolution Method for Image Segmentation
- k-Means Clustering for Persistent Homology
- Locally Smoothed Gaussian Process Regression
- Optimal Event Monitoring through Internet Mashup over Multivariate Time Series
- Post-hoc analysis of Arabic transformer models
- Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages
- Risk of re-identification for shared clinical speech recordings
- Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
- On the Information Content of Predictions in Word Analogy Tests
- Transfer-learning for video classification: Video Swin Transformer on multiple domains
- Nighttime Dehaze-Enhancement
- Rethinking Value Function Learning for Generalization in Reinforcement Learning
All 242
- Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder
- Layer-wise Relevance Propagation for Echo State Networks applied to Earth System Variability
- Contextual bandits with concave rewards, and an application to fair ranking
- SQ Lower Bounds for Learning Single Neurons with Massart Noise
- Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation
- MMGA: Multimodal Learning with Graph Alignment
- Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition
- A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
- Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective
- Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature
- Research of an optimization model for servicing a network of ATMs and information payment terminals
- RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
- Generalizing in the Real World with Representation Learning
- Predicting Winning Regions in Parity Games via Graph Neural Networks (Extended Abstract)
- Zero-shot point cloud segmentation by transferring geometric primitives
- Few-Shot Learning of Compact Models via Task-Specific Meta Distillation
- Finite-time analysis of single-timescale actor-critic
- Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
- Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity
- Controllable Fake Document Infilling for Cyber Deception
- Measure-Theoretic Probability of Complex Co-occurrence and E-Integral
- Leveraging Cluster Analysis to Understand Educational Game Player Experiences and Support Design
- Uncertainty estimation for out-of-distribution detection in computational histopathology
- MaSS: Multi-attribute Selective Suppression
- Online Convex Optimization with Unbounded Memory
- SA-DNet: A on-demand semantic object registration network adapting to non-rigid deformation
- Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions
- MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos
- Random Orthogonalization for Federated Learning in Massive MIMO Systems
- Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus
- Unsupervised visualization of image datasets using contrastive learning
- Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts
- Sequence and Circle: Exploring the Relationship Between Patches
- Towards Efficient and Effective Self-Supervised Learning of Visual Representations
- Scaling Adversarial Training to Large Perturbation Bounds
- Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention
- BIOWISH: Biometric Recognition using Wearable Inertial Sensors detecting Heart Activity
- Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging
- Deep Scattering Spectrum germaneness to Fault Detection and Diagnosis for Component-level Prognostics and Health Management (PHM)
- On-the-go Reflectance Transformation Imaging with Ordinary Smartphones
- Eye-tracking based classification of Mandarin Chinese readers with and without dyslexia using neural sequence models
- Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
- Universal hidden monotonic trend estimation with contrastive learning
- Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics
- Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel
- Domain Specific Sub-network for Multi-Domain Neural Machine Translation
- Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis
- HistoStarGAN: A Unified Approach to Stain Normalisation, Stain Transfer and Stain Invariant Segmentation in Renal Histopathology
- Inception-Based Crowd Counting -- Being Fast while Remaining Accurate
- Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
- Bagged k-Distance for Mode-Based Clustering Using the Probability of Localized Level Sets
- Generalized Many-Body Dispersion Correction through Random-phase Approximation for Chemically Accurate Density Functional Theory
- Machine-Learning-Optimized Perovskite Nanoplatelet Synthesis
- Decoupling Features in Hierarchical Propagation for Video Object Segmentation
- Compact multi-scale periocular recognition using SAFE features
- Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
- EventGraph at CASE 2021 Task 1: A General Graph-based Approach to Protest Event Extraction
- STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games
- Generative models uncertainty estimation
- DAGAD: Data Augmentation for Graph Anomaly Detection
- Very Low-Resolution Iris Recognition Via Eigen-Patch Super-Resolution and Matcher Fusion
- Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
- A Real-Time Fusion Framework for Long-term Visual Localization
- Simultaneous Translation for Unsegmented Input: A Sliding Window Approach
- A Socially Assistive Robot using Automated Planning in a Paediatric Clinical Setting
- Transfer learning with affine model transformation
- A Dashboard to Analysis and Synthesis of Dimensionality Reduction Methods in Remote Sensing
- Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation
- Clustering-based Aggregations for Prediction in Event Streams
- HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
- 3D Scalable Quantum Convolutional Neural Networks for Point Cloud Data Processing in Classification Applications
- Textual Entailment Recognition with Semantic Features from Empirical Text Representation
- A Comprehensive Analysis of Acknowledgement Texts in Web of Science: a case study on four scientific domains
- Fine-tune your Classifier: Finding Correlations With Temperature
- Importance Weighting Correction of Regularized Least-Squares for Target Shift
- HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning
- ATCON: Attention Consistency for Vision Models
- Weakly Supervised Learning with Automated Labels from Radiology Reports for Glioma Change Detection
- Consistent Multiclass Algorithms for Complex Metrics and Constraints
- TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis
- Nirdizati: an Advanced Predictive Process Monitoring Toolkit
- Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task
- Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities
- Hierarchical Normalization for Robust Monocular Depth Estimation
- ROSE: Robust Selective Fine-tuning for Pre-trained Language Models
- WINE: Wavelet-Guided GAN Inversion and Editing for High-Fidelity Refinement
- RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
- Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages
- Clustering Categorical Data: Soft Rounding k-modes
- Improving GANs with a Feature Cycling Generator
- Split-KalmanNet: A Robust Model-Based Deep Learning Approach for SLAM
- DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
- 1st Place Solutions for the UVO Challenge 2022
- FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences
- Deep Black-Box Reinforcement Learning with Movement Primitives
- Object Recognition in Different Lighting Conditions at Various Angles by Deep Learning Method
- Protecting Split Learning by Potential Energy Loss
- Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
- Degradation-invariant Enhancement of Fundus Images via Pyramid Constraint Network
- Perceptual Multi-Exposure Fusion
- Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs
- ODEs learn to walk: ODE-Net based data-driven modeling for crowd dynamics
- Denoising Enhanced Distantly Supervised Ultrafine Entity Typing
- Soft-Labeled Contrastive Pre-training for Function-level Code Representation
- Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
- Summary Workbench: Unifying Application and Evaluation of Text Summarization Models
- NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task
- A Novel Feature Representation for Malware Classification
- Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
- ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
- Spatio-Temporal-based Context Fusion for Video Anomaly Detection
- Simple Emergent Action Representations from Multi-Task Policy Training
- Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting
- FedForgery: Generalized Face Forgery Detection with Residual Federated Learning
- Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder
- Bag of Tricks for Developing Diabetic Retinopathy Analysis Framework to Overcome Data Scarcity
- Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
- A novel statistical methodology for quantifying the spatial arrangements of axons in peripheral nerves
- DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation
- Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
- An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks
- Less is More: A Lightweight and Robust Neural Architecture for Discourse Parsing
- Graph Anomaly Detection with Unsupervised GNNs
- A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4
- SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning
- Agglomerative Hierarchical Clustering with Dynamic Time Warping for Household Load Curve Clustering
- A Practical, Progressively-Expressive GNN
- Using Language to Extend to Unseen Domains
- Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue
- Towards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting
- An enhanced method of initial cluster center selection for K-means algorithm
- No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective
- CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
- Towards Fair Classification against Poisoning Attacks
- A Human-ML Collaboration Framework for Improving Video Content Reviews
- Enabling Heterogeneous Domain Adaptation in Multi-inhabitants Smart Home Activity Learning
- CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations
- 5th Place Solution to Kaggle Google Universal Image Embedding Competition
- Systematicity in GPT-3's Interpretation of Novel English Noun Compounds
- Semi-Supervised Domain Adaptation with Auto-Encoder via Simultaneous Learning
- FPGA Hardware Acceleration for Feature-Based Relative Navigation Applications
- RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction