Papers
Thu 20 Apr 2023
215 papers
- Diffusion-based Generative AI for Exploring Transition States from 2D Molecular GraphsDiffusion models → Flow matching, time series and science
- Meta Semantics: Towards better natural language understanding and reasoningLLM reasoning → Reasoning benchmarks and evaluation
- Word Sense Induction with Knowledge Distillation from BERTKnowledge distillation → Knowledge distillation for LLMs
- "HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social mediaLLM safety and security → Safety alignment, refusal and guardrails
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics +1
- Sparsity in neural networks can improve their privacyLLM safety and security → Membership inference attacks
- Farm3D: Learning Articulated 3D Animals by Distilling 2D DiffusionDiffusion models → 3D, point cloud and scene generation
- Collaborative Diffusion for Multi-Modal Face Generation and EditingDiffusion models → Image generation, text-to-image and editing
- CKBP v2: Better Annotation and Reasoning for Commonsense Knowledge Base PopulationLLM reasoning → Reasoning benchmarks and evaluation
- FIANCEE: Faster Inference of Adversarial Networks via Conditional Early ExitsEfficient LLM inference and serving → Early exit and edge inference
- Decouple Non-parametric Knowledge Distillation For End-to-end Speech TranslationKnowledge distillation → Speech and audio distillation
- Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art AnalysisDiffusion models → Image generation, text-to-image and editing
- Image retrieval outperforms diffusion models on data augmentationDiffusion models → Image generation, text-to-image and editing
- SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control
- NELoRa-Bench: A Benchmark for Neural-enhanced LoRa Demodulation
- Accurate ignition detection of solid fuel particles using machine learning
- MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning
- Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search
- eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators
- SALSA: Simulated Annealing based Loop-Ordering Scheduler for DNN Accelerators
- Medical Image Deidentification, Cleaning and Compression Using Pylogik
- Performance of ChatGPT on the US Fundamentals of Engineering Exam: Comprehensive Assessment of Proficiency and Potential Implications for Professional Environmental Engineering Practice
- TempoRL: laser pulse temporal shape optimization with Deep Reinforcement Learning
- DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
- Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK
- Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images
- Is Cross-modal Information Retrieval Possible without Training?
- Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects
- OLISIA: a Cascade System for Spoken Dialogue State Tracking
- CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering
- Using Mobile Data and Deep Models to Assess Auditory Verbal Hallucinations
- Light-weight Deep Extreme Multilabel Classification
- Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training
- Backpropagation-free Training of Deep Physical Neural Networks
- Emotional Expression Detection in Spoken Language Employing Machine Learning Algorithms
- A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications
- Deep reproductive feature generation framework for the diagnosis of COVID-19 and viral pneumonia using chest X-ray images
- Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing
- Edge-Aware Image Color Appearance and Difference Modeling
- Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
- Feature point detection in HDR images based on coefficient of variation
- A Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion
- Scaling ML Products At Startups: A Practitioner's Guide
- The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
- Learning a quantum computer's capability
- Activity Classification Using Unsupervised Domain Transfer from Body Worn Sensors
- Distributed Linear Solvers and Data Heterogeneity
- Multi-module based CVAE to predict HVCM faults in the SNS accelerator
- Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning
- IXA/Cogcomp at SemEval-2023 Task 2: Context-enriched Multilingual Named Entity Recognition using Knowledge Bases
- Ellipsoid fitting with the Cayley transform
- HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer
- Enhancing object detection robustness: A synthetic and natural perturbation approach
- Multi-domain learning CNN model for microscopy image classification
- An Attention Free Conditional Autoencoder For Anomaly Detection in Cryptocurrencies
- Debiasing Conditional Stochastic Optimization
- Joint Repetition Suppression and Content Moderation of Large Language Models
- Causal Analysis of Customer Churn Using Deep Learning
- Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models
- Enhancing Artificial intelligence Policies with Fusion and Forecasting: Insights from Indian Patents Using Network Analysis
- MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
- A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
- Invariant Scattering Transform for Medical Imaging
- B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding
- Using Z3 for Formal Modeling and Verification of FNN Global Robustness
- An Introduction to Transformers
- A Reference Model for Collaborative Business Intelligence Virtual Assistants
- Approximation and interpolation of deep neural networks
- MIPI 2023 Challenge on RGBW Remosaic: Methods and Results
- Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels
- Learning Neural Duplex Radiance Fields for Real-Time View Synthesis
- Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
- Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs
- Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance
- Multidimensional Uncertainty Quantification for Deep Neural Networks
- A User-Driven Framework for Regulating and Auditing Social Media
- Learning Narrow One-Hidden-Layer ReLU Networks
- GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
- Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
- Segment Anything Model for Medical Image Analysis: an Experimental Study
- Why Does ChatGPT Fall Short in Providing Truthful Answers?
- "Can We Detect Substance Use Disorder?": Knowledge and Time Aware Classification on Social Media from Darkweb
- Censoring chemical data to mitigate dual use risk
- Projective Proximal Gradient Descent for A Class of Nonconvex Nonsmooth Optimization Problems: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property
- Reconstructing Signing Avatars From Video Using Linguistic Priors
- Efficient Deep Reinforcement Learning Requires Regulating Overfitting
- Implicit Temporal Modeling with Learnable Alignment for Video Recognition
- Learning to Plan with Natural Language
- Angle based dynamic learning rate for gradient descent
- Phoenix: Democratizing ChatGPT across Languages
- ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects
- Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health
- Certified Adversarial Robustness Within Multiple Perturbation Bounds
- Securing Neural Networks with Knapsack Optimization
- OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
- A Study on Reproducibility and Replicability of Table Structure Recognition Methods
- Gauge-equivariant pooling layers for preconditioners in lattice QCD
- Safety Assessment of Chinese Large Language Models
- GPT-NER: Named Entity Recognition via Large Language Models
- On the Potential of Artificial Intelligence Chatbots for Data Exploration of Federated Bioinformatics Knowledge Graphs
All 215
- Fully Autonomous Programming with Large Language Models
- SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation
- NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results
- How the Move Acceptance Hyper-Heuristic Copes With Local Optima: Drastic Differences Between Jumps and Cliffs
- Attention Scheme Inspired Softmax Regression
- Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
- LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
- Multi-label Node Classification On Graph-Structured Data
- Breast cancer detection using deep learning
- PDL on Steroids: on Expressive Extensions of PDL with Intersection and Converse
- Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning
- Prompt-Learning for Cross-Lingual Relation Extraction
- Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning
- Interventional Probing in High Dimensions: An NLI Case Study
- DocMAE: Document Image Rectification via Self-supervised Representation Learning
- Prediction of the evolution of the nuclear reactor core parameters using artificial neural network
- Controllable Neural Symbolic Regression
- A baseline on continual learning methods for video action recognition
- Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition
- Learning Cellular Coverage from Real Network Configurations using GNNs
- Towards a Benchmark for Scientific Understanding in Humans and Machines
- Ensembling Instance and Semantic Segmentation for Panoptic Segmentation
- DropDim: A Regularization Method for Transformer Networks
- Adaptive Consensus Optimization Method for GANs
- Search-Map-Search: A Frame Selection Paradigm for Action Recognition
- Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining
- LA3: Efficient Label-Aware AutoAugment
- Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning
- Feature-compatible Progressive Learning for Video Copy Detection
- Optimal Activation of Halting Multi-Armed Bandit Models
- SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning
- OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structures
- Aiding reinforcement learning for set point control
- A Meta-heuristic Approach to Estimate and Explain Classifier Uncertainty
- Is augmentation effective to improve prediction in imbalanced text datasets?
- The Seven Worlds and Experiences of the Wireless Metaverse: Challenges and Opportunities
- Robust nonlinear set-point control with reinforcement learning
- Observer-Feedback-Feedforward Controller Structures in Reinforcement Learning
- PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image
- Social Distance Detection Using Deep Learning And Risk Management System
- Indian Sign Language Recognition Using Mediapipe Holistic
- PED-ANOVA: Efficiently Quantifying Hyperparameter Importance in Arbitrary Subspaces
- Image-text Retrieval via Preserving Main Semantics of Vision
- Towards replacing precipitation ensemble predictions systems using machine learning
- Revisiting Implicit Neural Representations in Low-Level Vision
- Hotelling Deflation on Large Symmetric Spiked Tensors
- Filter-Aware Model-Predictive Control
- Omni Aggregation Networks for Lightweight Image Super-Resolution
- Fourier Neural Operator Surrogate Model to Predict 3D Seismic Waves Propagation
- A geometry-aware deep network for depth estimation in monocular endoscopy
- Domain Generalization for Mammographic Image Analysis with Contrastive Learning
- Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?
- Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision Boundary
- Exploring Paracrawl for Document-level Neural Machine Translation
- The impact of the AI revolution on asset management
- Spiking-Fer: Spiking Neural Network for Facial Expression Recognition With Event Cameras
- Non-destructive Fault Diagnosis of Electronic Interconnects by Learning Signal Patterns of Reflection Coefficient in the Frequency Domain
- CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval
- Efficient Uncertainty Estimation in Spiking Neural Networks via MC-dropout
- Using Text-to-Image Generation for Architectural Design Ideation
- Cyber Security in Smart Manufacturing (Threats, Landscapes Challenges)
- SCoDA: Domain Adaptive Shape Completion for Real Scans
- Regularizing Second-Order Influences for Continual Learning
- Robust Deep Reinforcement Learning Scheduling via Weight Anchoring
- Automated Dynamic Bayesian Networks for Predicting Acute Kidney Injury Before Onset
- High-Fidelity and Freely Controllable Talking Head Video Generation
- Analyzing FOMC Minutes: Accuracy and Constraints of Language Models
- Deep-Q Learning with Hybrid Quantum Neural Network on Solving Maze Problems
- Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages
- Motion Artifacts Detection in Short-scan Dental CBCT Reconstructions
- On the Independence of Association Bias and Empirical Fairness in Language Models
- Flexible K Nearest Neighbors Classifier: Derivation and Application for Ion-mobility Spectrometry-based Indoor Localization
- Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks
- Diversifying the High-level Features for better Adversarial Transferability
- Learning Bottleneck Concepts in Image Classification
- Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
- Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One
- Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning
- Linear Convergence of Reshuffling Kaczmarz Methods With Sparse Constraints
- Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk
- SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation
- Reinforcement Learning for Picking Cluttered General Objects with Dense Object Descriptors
- Automatic Procurement Fraud Detection with Machine Learning
- eTag: Class-Incremental Learning with Embedding Distillation and Task-Oriented Generation
- Federated Compositional Deep AUC Maximization
- Two-Memory Reinforcement Learning
- Scene Style Text Editing
- Clustered-patch Element Connection for Few-shot Learning
- Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition
- MIPI 2023 Challenge on RGBW Fusion: Methods and Results
- NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering
- Dynamic Graph Representation Learning via Edge Temporal States Modeling and Structure-reinforced Transformer
- Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
- Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
- Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis
- Fruit Picker Activity Recognition with Wearable Sensors and Machine Learning
- Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation
- Understanding Accelerated Gradient Methods: Lyapunov Analyses and Hamiltonian Assisted Interpretations
- Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size
- Optimality of Robust Online Learning
- Complex Mixer for MedMNIST Classification Decathlon
- HyperTuner: A Cross-Layer Multi-Objective Hyperparameter Auto-Tuning Framework for Data Analytic Services
- Neural Radiance Fields: Past, Present, and Future
- Optimal Kernel for Kernel-Based Modal Statistical Methods
- ID-MixGCL: Identity Mixup for Graph Contrastive Learning
- Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives
- Brain tumor multi classification and segmentation in MRI images using deep learning
- Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
- Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations
- Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networks
- Jedi: Entropy-based Localization and Removal of Adversarial Patches
- Identification and multiply robust estimation in causal mediation analysis across principal strata
- Too sick for surveillance: Can federal HIV service data improve federal HIV surveillance efforts?
- A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices
- Digital Twin Graph: Automated Domain-Agnostic Construction, Fusion, and Simulation of IoT-Enabled World