Papers
Thu 12 Jan 2023
118 papers
- Blind Judgement: Agent-Based Supreme Court Modelling With GPTLLM agents and tool use → Social simulation and multi-agent debate
- See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual ReasoningLLM reasoning → Multimodal reasoning
- Open-vocabulary Object Segmentation with Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Progress measures for grokking via mechanistic interpretabilityMechanistic interpretability → Circuits and mechanistic analysis
- Thompson Sampling with Diffusion Generative PriorDiffusion models → Diffusion and flow policies for robotics
- Effective Decision Boundary Learning for Class Incremental LearningKnowledge distillation → Distillation for continual learning
- Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic ImagesDiffusion models → Medical imaging and segmentation
- Predictive World Models from Real-World Partial ObservationsWorld models → World models for language agents
- Accordion: A Communication-Aware Machine Learning Framework for Next Generation Networks
- CovidRhythm: A Deep Learning Model for Passive Prediction of Covid-19 using Biobehavioral Rhythms Derived from Wearable Physiological Data
- Dirac signal processing of higher-order topological signals
- Fair and skill-diverse student group formation via constrained k-way graph partitioning
- A Cohesive Distillation Architecture for Neural Language Models
- Model-agnostic machine learning of conservation laws from data
- Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
- confidence-planner: Easy-to-Use Prediction Confidence Estimation and Sample Size Planning
- OpenTwins: An open-source framework for the design, development and integration of effective 3D-IoT-AI-powered digital twins
- On the explainability of quantum neural networks based on variational quantum circuits
- Detection problems in the spiked matrix models
- Salient Object Detection for Images Taken by People With Vision Impairments
- Language-Informed Transfer Learning for Embodied Household Activities
- GH-Feat: Learning Versatile Generative Hierarchical Features from GANs
- Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components
- Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections
- HTTE: A Hybrid Technique For Travel Time Estimation In Sparse Data Environments
- A Novel Framework for Handling Sparse Data in Traffic Forecast
- Inaccessible Neural Language Models Could Reinvigorate Linguistic Nativism
- Security-Aware Approximate Spiking Neural Networks
- A Scalable Technique for Weak-Supervised Learning with Domain Constraints
- Jamming Attacks on Decentralized Federated Learning in General Multi-Hop Wireless Networks
- Online Class-Incremental Learning For Real-World Food Image Classification
- Equivariant Representation Learning in the Presence of Stabilizers
- Domain Expansion of Image Generators
- NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants
- Adversarial Adaptation for French Named Entity Recognition
- Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
- Learning to Summarize Videos by Contrasting Clips
- Accidental Light Probes
- ImMesh: An Immediate LiDAR Localization and Meshing Framework
- Multi-Power Level Q-Learning Algorithm for Random Access in NOMA mMTC Systems
- A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild
- Scene-Aware 3D Multi-Human Motion Capture from a Single Camera
- Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study
- Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning
- Signed Directed Graph Contrastive Learning with Laplacian Augmentation
- SemPPL: Predicting pseudo-labels for better contrastive representations
- Statistical Learning with Sublinear Regret of Propagator Models
- Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing
- Heuristic for Diverse Kemeny Rank Aggregation based on Quantum Annealing
- Is AI Art Another Industrial Revolution in the Making?
- Toward Theoretical Guidance for Two Common Questions in Practical Cross-Validation based Hyperparameter Selection
- Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History
- Explaining ELH Concept Descriptions through Counterfactual Reasoning
- Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data
- Improvement of Computational Performance of Evolutionary AutoML in a Heterogeneous Environment
- Improving Inference Performance of Machine Learning with the Divide-and-Conquer Principle
- Asynchronous training of quantum reinforcement learning
- Approximate Information States for Worst-Case Control and Learning in Uncertain Systems
- Discovering and Explaining Driver Behaviour under HoS Regulations
- Deep learning enhanced noise spectroscopy of a spin qubit environment
- Kinematic Evidence of an Embedded Protoplanet in HD 142666 Identified by Machine Learning
- Wildfire Smoke Detection with Computer Vision
- Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks
- Tracr: Compiled Transformers as a Laboratory for Interpretability
- Open SESAME: Fighting Botnets with Seed Reconstructions of Domain Generation Algorithms
- Persistence-Based Discretization for Learning Discrete Event Systems from Time Series
- Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information
- Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly
- Explicit Context Integrated Recurrent Neural Network for Sensor Data Applications
- Fairly Private: Investigating The Fairness of Visual Privacy Preservation Algorithms
- Machine learning methods for prediction of breakthrough curves in reactive porous media
- Against Algorithmic Exploitation of Human Vulnerabilities
- Study of software developers' experience using the Github Copilot Tool in the software development process
- Unsupervised Driving Event Discovery Based on Vehicle CAN-data
- Modeling the evolution of temporal knowledge graphs with uncertainty
- Hierarchical Dynamic Masks for Visual Explanation of Neural Networks
- A Dataset of Kurdish (Sorani) Named Entities -- An Amendment to Kurdish-BLARK Named Entities
- Graph Laplacian for Semi-Supervised Learning
- Reaching the Edge of the Edge: Image Analysis in Space
- ViTs for SITS: Vision Transformers for Satellite Image Time Series
- Safe Policy Improvement for POMDPs via Finite-State Controllers
- Density-based clustering with fully-convolutional networks for crowd flow detection from drones
- A Stochastic Proximal Polyak Step Size
- CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
- Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
- Lesion-aware Dynamic Kernel for Polyp Segmentation
- Stretched and measured neural predictions of complex network dynamics
- Learning Partial Differential Equations by Spectral Approximates of General Sobolev Spaces
- SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images
- ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation
- Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networks
- Explainable Ponzi Schemes Detection on Ethereum
- Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
- Semantic Segmentation via Pixel-to-Center Similarity Calculation
- Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation
- Edge Preserving Implicit Surface Representation of Point Clouds
- Neural Spline Search for Quantile Probabilistic Modeling
- Multimodal Deep Learning
- Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure
- Real-time FPGA implementation of the Semi-Global Matching stereo vision algorithm for a 4K/UHD video stream
All 118
- SACDNet: Towards Early Type 2 Diabetes Prediction with Uncertainty for Electronic Health Records
- Towards High Performance One-Stage Human Pose Estimation
- LB-SimTSC: An Efficient Similarity-Aware Graph Neural Network for Semi-Supervised Time Series Classification
- Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
- A Network Science perspective of Graph Convolutional Networks: A survey
- Data-centric AI: Perspectives and Challenges
- Deformation measurement of a soil mixing retaining wall using terrestrial laser scanning
- DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
- Adaptive Context Selection for Polyp Segmentation
- 1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track
- 1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track
- LiteLSTM Architecture Based on Weights Sharing for Recurrent Neural Networks
- Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction
- On the Structural Generalization in Text-to-SQL
- Language Cognition and Language Computation -- Human and Machine Language Understanding
- Phase-shifted Adversarial Training
- Variational Inference: Posterior Threshold Improves Network Clustering Accuracy in Sparse Regimes
- KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution