Papers
Thu 14 Jul 2022
179 papers
- Confident Adaptive Language ModelingEfficient LLM inference and serving → Early exit and edge inference
- Language models show human-like content effects on reasoning tasksLLM reasoning → Reasoning benchmarks and evaluation
- Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech ModelsKnowledge distillation → Speech and audio distillation
- Large-scale Knowledge Distillation with Elastic Heterogeneous Computing ResourcesKnowledge distillation → General knowledge distillation methods
- EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential EquationsDiffusion models → Diffusion foundations and sampling
- T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXitEfficient LLM inference and serving → Early exit and edge inference
- Vehicle-road Cooperative Simulation and 3D Visualization System
- Asset Allocation: From Markowitz to Deep Reinforcement Learning
- Areas of Strategic Visibility: Disability Bias in Biometrics
- Tutorial on the development of AI models for medical image analysis
- Component twin-width as a parameter for BINARY-CSP and its semiring generalisations
- Combing for Credentials: Active Pattern Extraction from Smart Reply
- Session-based Cyberbullying Detection in Social Media: A Survey
- EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System
- Unified 2D and 3D Pre-Training of Molecular Representations
- Efficient One Sided Kolmogorov Approximation
- Few-shot bioacoustic event detection at the DCASE 2022 challenge
- Improving Multi-Interest Network with Stable Learning
- Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model
- Rethinking Attention Mechanism in Time Series Classification
- QSAN: A Near-term Achievable Quantum Self-Attention Network
- Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network
- Emotion Recognition in Conversation using Probabilistic Soft Logic
- Single Model Uncertainty Estimation via Stochastic Data Centering
- Lipschitz Bound Analysis of Neural Networks
- Accelerated Federated Learning with Decoupled Adaptive Optimization
- Assortment Optimization with Customer Choice Modeling in a Crowdfunding Setting
- On the Selection of Tuning Parameters for Patch-Stitching Embedding Methods
- Attention, Filling in The Gaps for Generalization in Routing Problems
- Sound Randomized Smoothing in Floating-Point Arithmetics
- Provably Adversarially Robust Nearest Prototype Classifiers
- Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
- NASRec: Weight Sharing Neural Architecture Search for Recommender Systems
- Contrastive Adapters for Foundation Model Group Robustness
- Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data
- Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
- K-level Reasoning for Zero-Shot Coordination in Hanabi
- Audio-guided Album Cover Art Generation with Genetic Algorithms
- Case study on quantum convolutional neural network scalability
- Making Linear MDPs Practical via Contrastive Representation Learning
- Bootstrapped Masked Autoencoders for Vision BERT Pretraining
- XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
- Fine-grained Few-shot Recognition by Deep Object Parsing
- Benchmarking Omni-Vision Representation through the Lens of Visual Realms
- Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata
- Relighting4D: Neural Relightable Human from Videos
- ReAct: Temporal Action Detection with Relational Queries
- Explaining Image Enhancement Black-Box Methods through a Path Planning Based Algorithm
- A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse Representation Based Domain Adaption to Energy Efficient Abnormal Beat Detection for Practical ECG Surveillance
- Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
- An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
- Towards Grand Unification of Object Tracking
- Egocentric Scene Understanding via Multimodal Spatial Rectifier
- Adversarial Sign-Corrupted Isotonic Regression
- A Query-Optimal Algorithm for Finding Counterfactuals
- Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey
- On the Strong Correlation Between Model Invariance and Generalization
- Semi-Supervised Temporal Action Detection with Proposal-Free Masking
- How do tuna schools associate to dFADs? A study using echo-sounder buoys to identify global patterns
- Leakage and the Reproducibility Crisis in ML-based Science
- Convolutional Bypasses Are Better Vision Transformer Adapters
- SHAP-XRT: The Shapley Value Meets Conditional Independence Testing
- u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality
- Developing a Series of AI Challenges for the United States Department of the Air Force
- Adversarial Attacks on Monocular Pose Estimation
- Early Detection of Ovarian Cancer by Wavelet Analysis of Protein Mass Spectra
- MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images
- Learning to translate by learning to communicate
- Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Sets
- Language Modelling with Pixels
- Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
- ObjectBox: From Centers to Boxes for Anchor-Free Object Detection
- Multitrack Music Transformer
- Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification
- DASS: Differentiable Architecture Search for Sparse neural networks
- Scene Text Recognition with Permuted Autoregressive Sequence Models
- AutoMerge: A Framework for Map Assembling and Smoothing in City-scale Environments
- Forming Trees with Treeformers
- Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction
- Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts
- Learning Implicit Templates for Point-Based Clothed Human Modeling
- Tackling Background Distraction in Video Object Segmentation
- Using Model-Based Trees with Boosting to Fit Low-Order Functional ANOVA Models
- Seeking the Truth Beyond the Data. An Unsupervised Machine Learning Approach
- Insurgency as Complex Network: Image Co-Appearance and Hierarchy in the PKK
- Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
- PASHA: Efficient HPO and NAS with Progressive Resource Allocation
- Real-time Streaming Video Denoising with Bidirectional Buffers
- Multi-Level Branched Regularization for Federated Learning
- Uncertainty quantification for predictions of atomistic neural networks
- Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation
- Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language
- E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow
- Distance Learner: Incorporating Manifold Prior to Model Training
- Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languages
- Recurrent Memory Transformer
- BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
- Data Augmentation for Low-Resource Quechua ASR Improvement
- Immunofluorescence Capillary Imaging Segmentation: Cases Study
- RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks
All 179
- Low-Precision Arithmetic for Fast Gaussian Processes
- AIParsing: Anchor-free Instance-level Human Parsing
- Covy: An AI-powered Robot with a Compound Vision System for Detecting Breaches in Social Distancing
- Deep Dictionary Learning with An Intra-class Constraint
- Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model
- Instance Selection Mechanisms for Human-in-the-Loop Systems in Few-Shot Learning
- Enforcing connectivity of 3D linear structures using their 2D projections
- iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
- Pose-based Tremor Classification for Parkinson's Disease Diagnosis from Video
- Point-to-Box Network for Accurate Object Detection via Single Point Supervision
- Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
- DEXTER: An end-to-end system to extract table contents from electronic medical health documents
- Anomal-E: A Self-Supervised Network Intrusion Detection System based on Graph Neural Networks
- Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
- BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling
- Comparing the latent space of generative models
- In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory
- FFTc: An MLIR Dialect for Developing HPC Fast Fourier Transform Libraries
- GrabQC: Graph based Query Contextualization for automated ICD coding
- MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation
- Neural apparent BRDF fields for multiview photometric stereo
- Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
- An Empirical Evaluation of Four Off-the-Shelf Proprietary Visual-Inertial Odometry Systems
- Strain-Minimizing Hyperbolic Network Embeddings with Landmarks
- Semi-supervised cross-lingual speech emotion recognition
- GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling
- Neighbor Correspondence Matching for Flow-based Video Frame Synthesis
- Work In Progress: Safety and Robustness Verification of Autoencoder-Based Regression Models using the NNV Tool
- Verification of Sigmoidal Artificial Neural Networks using iSAT
- E2-AEN: End-to-End Incremental Learning with Adaptively Expandable Network
- Single-Pixel Image Reconstruction Based on Block Compressive Sensing and Deep Learning
- TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
- Differentiable Logics for Neural Network Training and Verification
- Semi-supervised Vector-Quantization in Visual SLAM using HGCN
- ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images
- Open Terminology Management and Sharing Toolkit for Federation of Terminology Databases
- Octuplet Loss: Make Face Recognition Robust to Image Resolution
- Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
- Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021
- problexity -- an open-source Python library for binary classification problem complexity assessment
- SHREC 2022 Track on Online Detection of Heterogeneous Gestures
- DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding
- Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
- Breaking Correlation Shift via Conditional Invariant Regularizer
- Subgraph Frequency Distribution Estimation using Graph Neural Networks
- Equivariant Hypergraph Diffusion Neural Operators
- Learning to Prove Trigonometric Identities
- Deep Learning Methods for Protein Family Classification on PDB Sequencing Data
- A Meta-learning Formulation of the Autoencoder Problem for Non-linear Dimensionality Reduction
- Reinforced Path Reasoning for Counterfactual Explainable Recommendation
- Detecting Volunteer Cotton Plants in a Corn Field with Deep Learning on UAV Remote-Sensing Imagery
- Two-Pass Low Latency End-to-End Spoken Language Understanding
- Golden Reference-Free Hardware Trojan Localization using Graph Convolutional Network
- Deep Point-to-Plane Registration by Efficient Backpropagation for Error Minimizing Function
- Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization
- Universal Adaptive Data Augmentation
- Exploration of an End-to-End Automatic Number-plate Recognition neural network for Indian datasets
- Improving the Accuracy of Marginal Approximations in Likelihood-Free Inference via Localisation
- Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation
- Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model
- Have we been Naive to Select Machine Learning Models? Noisy Data are here to Stay!
- PIAT: Physics Informed Adversarial Training for Solving Partial Differential Equations
- DropNet: Reducing Neural Network Complexity via Iterative Pruning
- Source-Free Domain Adaptation for Real-world Image Dehazing
- Identifying Orientation-specific Lipid-protein Fingerprints using Deep Learning
- Continuous Facial Motion Deblurring
- Perception-Oriented Stereo Image Super-Resolution
- Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement
- Deepfake Video Detection with Spatiotemporal Dropout Transformer
- Rethinking Super-Resolution as Text-Guided Details Generation
- Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
- Near-Optimal Bounds for Testing Histogram Distributions
- Few-Shot Specific Emitter Identification via Deep Metric Ensemble Learning
- A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America
- Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
- Soil Erosion in the United States. Present and Future (2020-2050)
- Virtual stain transfer in histology via cascaded deep neural networks
- Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
- MDEAW: A Multimodal Dataset for Emotion Analysis through EDA and PPG signals from wireless wearable low-cost off-the-shelf Devices