Papers
Mon 11 Jul 2022
161 papers
- Language Models (Mostly) Know What They KnowLLM reasoning → Test-time compute and efficient thinking
- UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
- No Language Left Behind: Scaling Human-Centered Machine TranslationMixture-of-experts → MoE large language models
- A Secure Fingerprinting Framework for Distributed Image ClassificationLLM safety and security → Watermarking generated content and models
- Learning Large-scale Universal User Representation with Sparse Mixture of ExpertsMixture-of-experts → MoE large language models
- On the Principles of Parsimony and Self-Consistency for the Emergence of IntelligenceLLM reasoning → Reasoning benchmarks and evaluation
- 2nd Place Solution to Google Landmark Retrieval 2020
- Efficient Learning of Accurate Surrogates for Simulations of Complex Systems
- LIP: Lightweight Intelligent Preprocessor for meaningful text-to-speech
- Interference-Limited Ultra-Reliable and Low-Latency Communications: Graph Neural Networks or Stochastic Geometry?
- Physics Informed Symbolic Networks
- Distribution-Free Stochastic Analysis and Robust Multilevel Vector Field Anomaly Detection
- FD-GATDR: A Federated-Decentralized-Learning Graph Attention Network for Doctor Recommendation Using EHR
- A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection
- Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
- Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
- Brain-inspired Graph Spiking Neural Networks for Commonsense Knowledge Representation and Reasoning
- PoeticTTS -- Controllable Poetry Reading for Literary Studies
- Susceptibility of Continual Learning Against Adversarial Attacks
- Bootstrapping a User-Centered Task-Oriented Dialogue System
- Grounding Aleatoric Uncertainty for Unsupervised Environment Design
- Shapley Computations Using Surrogate Model-Based Trees
- Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
- Scaling Novel Object Detection with Weakly Supervised Detection Transformers
- The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues
- Real-Time And Robust 3D Object Detection with Roadside LiDARs
- Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting
- Towards Neural Numeric-To-Text Generation From Temporal Personal Health Data
- Patch-level instance-group discrimination with pretext-invariant learning for colitis scoring
- Knowledge Graph Induction enabling Recommending and Trend Analysis: A Corporate Research Community Use Case
- Fine-grained Activities of People Worldwide
- Denoising single images by feature ensemble revisited
- Machine Learning Security in Industry: A Quantitative Survey
- What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
- Accelerated Deep Lossless Image Coding with Unified Paralleleized GPU Coding Architecture
- UrduFake@FIRE2021: Shared Track on Fake News Identification in Urdu
- Towards Personalized Healthcare in Cardiac Population: The Development of a Wearable ECG Monitoring System, an ECG Lossy Compression Schema, and a ResNet-Based AF Detector
- Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistency
- Overview of the Shared Task on Fake News Detection in Urdu at FIRE 2021
- Dev2vec: Representing Domain Expertise of Developers in an Embedding Space
- RUSH: Robust Contrastive Learning via Randomized Smoothing
- An Interpretable Joint Nonnegative Matrix Factorization-Based Point Cloud Distance Measure
- A Macrocolumn Architecture Implemented with Spiking Neurons
- Learning an evolved mixture model for task-free continual learning
- Horizontal Federated Learning and Secure Distributed Training for Recommendation System with Intel SGX
- Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring
- Online Continual Learning of End-to-End Speech Recognition Models
- Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation
- Few-Shot Semantic Relation Prediction across Heterogeneous Graphs
- Demystifying Unsupervised Semantic Correspondence Estimation
- Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations
- A Federated Cox Model with Non-Proportional Hazards
- Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
- Audio-Visual Segmentation
- Parallel Bayesian Optimization of Agent-based Transportation Simulation
- Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
- PSP-HDRI+: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models
- Intra-Modal Constraint Loss For Image-Text Retrieval
- STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining
- Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning
- Boosting Heterogeneous Catalyst Discovery by Structurally Constrained Deep Learning Models
- A Learned Radiance-Field Representation for Complex Luminaires
- A description of Turkish Discourse Bank 1.2 and an examination of common dependencies in Turkish discourse
- TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
- Consistency is the key to further mitigating catastrophic forgetting in continual learning
- A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision
- Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
- Embedding Recycling for Language Models
- What AI can do for horse-racing ?
- Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings
- Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning
- Dual Vision Transformer
- Sparsifying Binary Networks
- From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process
- Structural Inference of Networked Dynamical Systems with Universal Differential Equations
- Learning Mutual Fund Categorization using Natural Language Processing
- Neural and spectral operator surrogates: unified construction and expression rate bounds
- TweetDIS: A Large Twitter Dataset for Natural Disasters Built using Weak Supervision
- SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
- Wavelet Conditional Renormalization Group
- Multilevel Geometric Optimization for Regularised Constrained Linear Inverse Problems
- Stochastic Gradient Descent and Anomaly of Variance-flatness Relation in Artificial Neural Networks
- On uniform-in-time diffusion approximation for stochastic gradient descent
- Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
- Detection of Condensed Vehicle Gas Exhaust in LiDAR Point Clouds
- HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation
- Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model
- Exploring Length Generalization in Large Language Models
- Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility
- Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
- The Mean Dimension of Neural Networks -- What causes the interaction effects?
- SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fields
- LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
- Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems
- RRMSE Voting Regressor: A weighting function based improvement to ensemble regression
- Speaker Anonymization with Phonetic Intermediate Representations
- Classification and Generation of real-world data with an Associative Memory Model
- Forward Error Correction applied to JPEG-XS codestreams
- Long-term Reproducibility for Neural Architecture Search
- Assessing Ranking and Effectiveness of Evolutionary Algorithm Hyperparameters Using Global Sensitivity Analysis Methodologies
All 161
- Cross-modal Prototype Driven Network for Radiology Report Generation
- On the vulnerability of fingerprint verification systems to fake fingerprint attacks
- A clinically motivated self-supervised approach for content-based image retrieval of CT liver images
- Fingerprint Liveness Detection Based on Quality Measures
- CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
- Repairing Neural Networks by Leaving the Right Past Behind
- TArC: Tunisian Arabish Corpus First complete release
- PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification
- DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
- SALSA: Attacking Lattice Cryptography with Transformers
- MT-Net Submission to the Waymo 3D Detection Leaderboard
- Whois? Deep Author Name Disambiguation using Bibliographic Data
- Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
- A Late Fusion Framework with Multiple Optimization Methods for Media Interestingness
- Snow Mask Guided Adaptive Residual Network for Image Snow Removal
- Geometry-aware Single-image Full-body Human Relighting
- DeepSNR: A deep learning foundation for offline gravitational wave detection
- On Computing Relevant Features for Explaining NBCs
- Interpretability by design using computer vision for behavioral sensing in child and adolescent psychiatry
- Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture
- Identifying public values and spatial conflicts in urban planning
- Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
- GMN: Generative Multi-modal Network for Practical Document Information Extraction
- Matching Normalizing Flows and Probability Paths on Manifolds
- A Baselined Gated Attention Recurrent Network for Request Prediction in Ridesharing
- Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning
- Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition
- Exploring Contextual Relationships for Cervical Abnormal Cell Detection
- PUF-Phenotype: A Robust and Noise-Resilient Approach to Aid Intra-Group-based Authentication with DRAM-PUFs Using Machine Learning
- Dynamic Budget Throttling in Repeated Second-Price Auctions
- (Nearly) Optimal Private Linear Regression via Adaptive Clipping
- Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage
- Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
- COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
- CAMS: An Annotated Corpus for Causal Analysis of Mental Health Issues in Social Media Posts
- Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation
- An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
- SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder
- Topic-Grained Text Representation-based Model for Document Retrieval
- Personalizing Federated Medical Image Segmentation via Local Calibration
- A Lexicon and Depth-wise Separable Convolution Based Handwritten Text Recognition System
- A Dual-Polarization Information Guided Network for SAR Ship Classification
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
- Partial Resampling of Imbalanced Data
- Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting
- Deep neural network based adaptive learning for switched systems
- Edge-preserving Near-light Photometric Stereo with Neural Surfaces
- Instance Shadow Detection with A Single-Stage Detector
- Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution Regression
- Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
- A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models
- SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning
- Adaptive Fine-Grained Predicates Learning for Scene Graph Generation
- Optimal Clustering by Lloyd Algorithm for Low-Rank Mixture Model
- Learned Video Compression via Heterogeneous Deformable Compensation Network
- Multi-Study Boosting: Theoretical Considerations for Merging vs. Ensembling
- Gradual Domain Adaptation without Indexed Intermediate Domains
- A multi-level interpretable sleep stage scoring system by infusing experts' knowledge into a deep network architecture
- How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies
- A Waste Copper Granules Rating System Based on Machine Vision
- Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease