Papers
Fri 5 Aug 2022
131 papers
- Lethal Dose Conjecture on Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
- Atlas: Few-shot Learning with Retrieval Augmented Language ModelsRetrieval-augmented generation → Generation and context integration
- Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation ProcessesKnowledge distillation → Graph neural network distillation
- Task-Balanced Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Abstract Interpretation for Generalized Heuristic Search in Model-Based PlanningWorld models → World models for language agents
- Graph neural networks for materials science and chemistry
- A novel solution of deep learning for enhanced support vector machine for predicting the onset of type 2 diabetes
- Deep Learning Neural Network for Lung Cancer Classification: Enhanced Optimization Function
- NRBdMF: A recommendation algorithm for predicting drug effects considering directionality
- DIVISION: Memory Efficient Training via Dual Activation Precision
- DP2-VAE: Differentially Private Pre-trained Variational Autoencoders
- A novel deep learning-based approach for sleep apnea detection using single-lead ECG signals
- An Overview of Structural Coverage Metrics for Testing Neural Networks
- Slice-level Detection of Intracranial Hemorrhage on CT Using Deep Descriptors of Adjacent Slices
- LCCDE: A Decision-Based Ensemble Framework for Intrusion Detection in The Internet of Vehicles
- Bayesian predictive modeling of multi-source multi-way data
- Chronological Self-Training for Real-Time Speaker Diarization
- Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions
- Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
- A Survey on Visual Map Localization Using LiDARs and Cameras
- Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter
- A Computational Exploration of Emerging Methods of Variable Importance Estimation
- Sublinear Time Algorithm for Online Weighted Bipartite Matching
- GLASS: Global to Local Attention for Scene-Text Spotting
- Deep Learning for Material Decomposition in Photon-Counting CT
- Perceptual Artifacts Localization for Inpainting
- A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch
- Active Learning for Non-Parametric Choice Models
- IDLat: An Importance-Driven Latent Generation Method for Scientific Data
- Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers
- Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images
- Variational Autoencoders for Anomaly Detection in Respiratory Sounds
- Isoform Function Prediction Using a Deep Neural Network
- Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution
- DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space
- Discovery of partial differential equations from highly noisy and sparse data with physics-informed information criterion
- A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
- Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions
- Accelerating discrete dislocation dynamics simulations with graph neural networks
- Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
- Convolutional Ensembling based Few-Shot Defect Detection Technique
- Interpretable Uncertainty Quantification in AI for HEP
- A Holistic Approach to Undesired Content Detection in the Real World
- Towards Antisymmetric Neural Ansatz Separation
- 3D Pose Based Feedback for Physical Exercises
- Parameter Averaging for Feature Ranking
- An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms
- Non-Asymptotic Analysis of Ensemble Kalman Updates: Effective Dimension and Localization
- Real-time Gesture Animation Generation from Speech for Virtual Human Interaction
- Learning programs with magic values
- Defining Cases and Variants for Object-Centric Event Data
- Driving Points Prediction For Abdominal Probabilistic Registration
- Improving Task Generalization via Unified Schema Prompt
- Construction of English Resume Corpus and Test with Pre-trained Language Models
- RadTex: Learning Efficient Radiograph Representations from Text Reports
- Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation
- Why do networks have inhibitory/negative connections?
- Bias and Fairness in Computer Vision Applications of the Criminal Justice System
- Neighborhood Collective Estimation for Noisy Label Identification and Correction
- Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shifts
- Brain Lesion Synthesis via Progressive Adversarial Variational Auto-Encoder
- Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey
- COPER: Continuous Patient State Perceiver
- BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
- Catoni-style Confidence Sequences under Infinite Variance
- FBI: Fingerprinting models with Benign Inputs
- Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
- Discover the Mysteries of the Maya: Selected Contributions from the Machine Learning Challenge & The Discovery Challenge Workshop at ECML PKDD 2021
- Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations
- Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks
- BoxShrink: From Bounding Boxes to Segmentation Masks
- Machine Learning and Bioinformatics for Diagnosis Analysis of Obesity Spectrum Disorders
- Out of the BLEU: how should we assess quality of the Code Generation models?
- A Lightweight Machine Learning Pipeline for LiDAR-simulation
- Motivating explanations in Bayesian networks using MAP-independence
- Multi-fidelity surrogate modeling using long short-term memory networks
- On the non-universality of deep learning: quantifying the cost of symmetry
- Explanation of Machine Learning Models of Colon Cancer Using SHAP Considering Interaction Effects
- Data-free Backdoor Removal based on Channel Lipschitzness
- MorDeephy: Face Morphing Detection Via Fused Classification
- Fixed-Point Automatic Differentiation of Forward--Backward Splitting Algorithms for Partly Smooth Functions
- Planning and Scheduling in Digital Health with Answer Set Programming
- An ASP Framework for Efficient Urban Traffic Optimization
- Tools and Methodologies for Verifying Answer Set Programs
- A Model-Oriented Approach for Lifting Symmetries in Answer Set Programming
- Knowledge Authoring with Factual English
- A Gaze into the Internal Logic of Graph Neural Networks, with Logic
- On Model Reconciliation: How to Reconcile When Robot Does not Know Human's Model?
- Tree-Like Justification Systems are Consistent
- A Fixpoint Characterization of Three-Valued Disjunctive Hybrid MKNF Knowledge Bases
- Deep Feature Learning for Medical Acoustics
- Conflict-free joint sampling for preference satisfaction through quantum interference
- Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
- Cohort comfort models -- Using occupants' similarity to predict personal thermal preference with less data
- Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning
- Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity
- Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
- Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
All 131
- Sinusoidal Sensitivity Calculation for Line Segment Geometries
- Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognition
- Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
- Low-Light Hyperspectral Image Enhancement
- Blockwise Temporal-Spatial Pathway Network
- ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding
- Compressing (Multidimensional) Learned Bloom Filters
- Multimodal Brain Disease Classification with Functional Interaction Learning from Single fMRI Volume
- Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data
- Phrase translation using a bilingual dictionary and n-gram data: A case study from Vietnamese to English
- Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle
- Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution
- Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN
- TransMatting: Enhancing Transparent Objects Matting with Transformers
- A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning
- Localized Sparse Incomplete Multi-view Clustering
- Learning to Coordinate for a Worker-Station Multi-robot System in Planar Coverage Tasks
- Analyzing the Impact of Shape & Context on the Face Recognition Performance of Deep Networks
- Covariant-Contravariant Refinement Modal μ-calculus
- An Efficient Person Clustering Algorithm for Open Checkout-free Groceries
- Memory-Guided Collaborative Attention for Nighttime Thermal Infrared Image Colorization
- Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss
- Meaning without reference in large language models
- ZLPR: A Novel Loss for Multi-label Classification
- A Novel Enhanced Convolution Neural Network with Extreme Learning Machine: Facial Emotional Recognition in Psychology Practices
- Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification
- Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation
- Learning to Generate 3D Shapes from a Single Example
- Applied monocular reconstruction of parametric faces with domain engineering
- A Noise-Robust Loss for Unlabeled Entity Problem in Named Entity Recognition
- Model Blending for Text Classification