Papers
Sat 12 Nov 2022
96 papers
- DriftRec: Adapting diffusion models to blind JPEG restorationDiffusion models → Inverse problems and image restoration
- Provable Membership Inference PrivacyLLM safety and security → Membership inference attacks
- Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- The Expertise Problem: Learning from Specialized FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- A Self-Adjusting Fusion Representation Learning Model for Unaligned Text-Audio Sequences
- Development of a Neural Network-Based Mathematical Operation Protocol for Embedded Hexadecimal Digits Using Neural Architecture Search (NAS)
- How to Backpropagate through Hungarian in Your DETR?
- DeltaNet:Conditional Medical Report Generation for COVID-19 Diagnosis
- LLEDA -- Lifelong Self-Supervised Domain Adaptation
- Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
- CXTrack: Improving 3D Point Cloud Tracking with Contextual Information
- Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
- PhysiQ: Off-site Quality Assessment of Exercise in Physical Therapy
- Motif-topology improved Spiking Neural Network for the Cocktail Party Effect and McGurk Effect
- Improving Deep Facial Phenotyping for Ultra-rare Disorder Verification Using Model Ensembles
- Few-Shot Learning for Biometric Verification
- Integrating Transformer and Autoencoder Techniques with Spectral Graph Algorithms for the Prediction of Scarcely Labeled Molecular Data
- Seamful XAI: Operationalizing Seamful Design in Explainable AI
- The generalised distribution semantics and projective families of distributions
- Human Autonomy as a Design Principle for Socially Assistive Robots
- Task Tree Retrieval Algorithms for Robotic Cooking Using The Functional Object-Oriented Network
- Deep Unsupervised Key Frame Extraction for Efficient Video Classification
- Partial Binarization of Neural Networks for Budget-Aware Efficient Learning
- Formalizing the presumption of independence
- Structural constrained virtual histology staining for human coronary imaging using deep learning
- Deep Reinforcement Learning with Vector Quantized Encoding
- MultiCrossViT: Multimodal Vision Transformer for Schizophrenia Prediction using Structural MRI and Functional Network Connectivity Data
- Using Features at Multiple Temporal and Spatial Resolutions to Predict Human Behavior in Real Time
- Auto Lead Extraction and Digitization of ECG Paper Records using cGAN
- Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis
- A Pipeline for Business Intelligence and Data-Driven Root Cause Analysis on Categorical Data
- PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference
- Bayesian Learning of Coupled Biogeochemical-Physical Models
- Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
- Multistep feature aggregation framework for salient object detection
- Illumination-Based Color Reconstruction for the Dynamic Vision Sensor
- Pain Detection in Masked Faces during Procedural Sedation
- TINC: Tree-structured Implicit Neural Compression
- Partial Visual-Semantic Embedding: Fashion Intelligence System with Sensitive Part-by-Part Learning
- A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction
- AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
- Learning dynamical systems: an example from open quantum system dynamics
- Privacy-Preserving Credit Card Fraud Detection using Homomorphic Encryption
- A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges
- NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
- Addressing Segmentation Ambiguity in Neural Linguistic Steganography
- Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
- Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique
- Learning Neuro-symbolic Programs for Language Guided Robot Manipulation
- NLPeer: A Unified Resource for the Computational Study of Peer Review
- Line Drawing Guided Progressive Inpainting of Mural Damage
- DATa: Domain Adaptation-Aided Deep Table Detection Using Visual-Lexical Representations
- Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings
- Kinematics Transformer: Solving The Inverse Modeling Problem of Soft Robots using Transformers
- ConceptX: A Framework for Latent Concept Analysis
- Prediction of Geometric Transformation on Cardiac MRI via Convolutional Neural Network
- Modular Clinical Decision Support Networks (MoDN) -- Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments
- MARLIN: Masked Autoencoder for facial video Representation LearnINg
- CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality
- A Radiogenomics Pipeline for Lung Nodules Segmentation and Prediction of EGFR Mutation Status from CT Scans
- Empirical Risk Minimization with Relative Entropy Regularization
- Robust Training of Graph Neural Networks via Noise Governance
- Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
- AU-Aware Vision Transformers for Biased Facial Expression Recognition
- Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts
- Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective
- On the High Symmetry of Neural Network Functions
- OpenGait: Revisiting Gait Recognition Toward Better Practicality
- ABCAS: Adaptive Bound Control of spectral norm as Automatic Stabilizer
- Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling
- DEYO: DETR with YOLO for Step-by-Step Object Detection
- 3D-Aware Encoding for Style-based Neural Radiance Fields
- Variational Augmentation for Enhancing Historical Document Image Binarization
- Explainable Artificial Intelligence: Precepts, Methods, and Opportunities for Research in Construction
- Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation
- Generating Textual Adversaries with Minimal Perturbation
- End-to-End Machine Learning Framework for Facial AU Detection in Intensive Care Units
- RISE: Robust Individualized Decision Learning with Sensitive Variables
- Online Search with Predictions: Pareto-optimal Algorithm and its Applications in Energy Markets
- Innovative Drug-like Molecule Generation from Flow-based Generative Model
- MSLKANet: A Multi-Scale Large Kernel Attention Network for Scene Text Removal
- Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement
- Explainable Artificial Intelligence in Construction: The Content, Context, Process, Outcome Evaluation Framework
- PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization
- Lifelong and Continual Learning Dialogue Systems
- Collecting Interactive Multi-modal Datasets for Grounded Language Understanding
- TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
- Self-Supervised Graph Structure Refinement for Graph Neural Networks
- Correcting Faulty Road Maps by Image Inpainting
- Dark patterns in e-commerce: a dataset and its baseline evaluations
- Improving the Efficiency of the PC Algorithm by Using Model-Based Conditional Independence Tests
- A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units
- Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
- Actionable Recourse via GANs for Mobile Health
- Quantum Split Neural Network Learning using Cross-Channel Pooling
- Deep Learning Generates Synthetic Cancer Histology for Explainability and Education