Papers
Tue 11 Apr 2023
208 papers
- Revisiting Single-gated Mixtures of ExpertsMixture-of-experts → MoE theory and gating functions
- CamDiff: Camouflage Image Augmentation via Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image ModelsDiffusion models → Image generation, text-to-image and editing
- Diffusion Models for Constrained DomainsDiffusion models → Diffusion foundations and sampling
- ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal SimilarityMultimodal LLMs / vision-language models → Medical vision-language models
- RRHF: Rank Responses to Align Language Models with Human Feedback without tearsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Graph-based Topology Reasoning for Driving ScenesEnd-to-end autonomous driving → VLMs for autonomous driving
- Mask-conditioned latent diffusion for generating gastrointestinal polyp imagesDiffusion models → Medical imaging and segmentation
- Multi-step Jailbreaking Privacy Attacks on ChatGPTLLM safety and security → Prompt injection and agent security
- Improving Image Recognition by Retrieving from Web-Scale Image-Text DataRetrieval-augmented generation → Multimodal RAG
- Curriculum-Based Imitation of Versatile SkillsMixture-of-experts → MoE in reinforcement learning and robotics
- Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturingDiffusion models → Flow matching, time series and science
- Teaching Large Language Models to Self-DebugLLM reasoning → Reasoning for agents, planning and code +1
- SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRIDiffusion models → Medical imaging and segmentation
- SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image ReconstructionKnowledge distillation → General knowledge distillation methods
- FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and BeyondDiffusion models → Image generation, text-to-image and editing
- Model Sparsity Can Simplify Machine UnlearningLLM safety and security → Machine unlearning
- Tensor PCA from basis in tensor space
- Neural Network Accelerated Process Design of Polycrystalline Microstructures
- ChatGPT is all you need to decolonize sub-Saharan Vocational Education
- Ensemble CNNs for Breast Tumor Classification
- SamurAI: A Versatile IoT Node With Event-Driven Wake-Up and Embedded ML Acceleration
- Prediction of brain tumor recurrence location based on multi-modal fusion and nonlinear correlation learning
- Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach
- Privacy-Preserving Matrix Factorization for Recommendation Systems using Gaussian Mechanism
- Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation
- A Corpus-based Analysis of Attitudinal Changes in Lin Yutang's Self-translation of Between Tears and Laughter
- Can sparsity improve the privacy of neural networks?
- Late Breaking Results: Scalable and Efficient Hyperdimensional Computing for Network Intrusion Detection
- Variations of Squeeze and Excitation networks
- Equivalent and Compact Representations of Neural Network Controllers With Decision Trees
- RELS-DQN: A Robust and Efficient Local Search Framework for Combinatorial Optimization
- PD-ADSV: An Automated Diagnosing System Using Voice Signals and Hard Voting Ensemble Method for Parkinson's Disease
- Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning
- DartsReNet: Exploring new RNN cells in ReNet architectures
- A Game-theoretic Framework for Privacy-preserving Federated Learning
- ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
- Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis
- SceneCalib: Automatic Targetless Calibration of Cameras and Lidars in Autonomous Driving
- Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box
- Understanding Causality with Large Language Models: Feasibility and Opportunities
- MoMo: A shared encoder Model for text, image and multi-Modal representations
- Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model
- Mathematical and Linguistic Characterization of Orhan Pamuk's Nobel Works
- Training Large Language Models Efficiently with Sparsity and Dataflow
- chatClimate: Grounding Conversational AI in Climate Science
- Control invariant set enhanced reinforcement learning for process control: improved sampling efficiency and guaranteed stability
- DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
- Machine learning for structure-property relationships: Scalability and limitations
- GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery
- Optimizing Data-driven Causal Discovery Using Knowledge-guided Search
- Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training
- User Adaptive Language Learning Chatbots with a Curriculum
- Computational Pathology: A Survey Review and The Way Forward
- Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
- A Survey of Resources and Methods for Natural Language Processing of Serbian Language
- UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series
- An Automatic Guidance and Quality Assessment System for Doppler Imaging of Umbilical Artery
- Zero-shot Temporal Relation Extraction with ChatGPT
- Scale-Space Hypernetworks for Efficient Biomedical Imaging
- Collaborative Machine Learning Model Building with Families Using Co-ML
- PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors
- Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation
- Differentiable graph-structured models for inverse design of lattice materials
- The MONET dataset: Multimodal drone thermal dataset recorded in rural scenarios
- Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search
- Boosting Cross-task Transferability of Adversarial Patches with Visual Relations
- Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies
- Human-AI Co-Creation Approach to Find Forever Chemicals Replacements
- MOST: Multiple Object localization with Self-supervised Transformers for object discovery
- ChemCrow: Augmenting large-language models with chemistry tools
- Overload: Latency Attacks on Object Detection for Edge Devices
- A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation
- The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
- Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling
- A comparative study between paired and unpaired Image Quality Assessment in Low-Dose CT Denoising
- Bayesian Optimization of Catalysis With In-Context Learning
- Unified Multi-Modal Image Synthesis for Missing Modality Imputation
- Deep-learning Assisted Detection and Quantification of (oo)cysts of Giardia and Cryptosporidium on Smartphone Microscopy Images
- Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages
- Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
- Emergent autonomous scientific research capabilities of large language models
- OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
- Neural Delay Differential Equations: System Reconstruction and Image Classification
- Generative Modeling via Hierarchical Tensor Sketching
- TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning
- Estimation of Vehicular Velocity based on Non-Intrusive stereo camera
- EvAC3D: From Event-based Apparent Contours to 3D Models via Continuous Visual Hulls
- A Comprehensive Study on Object Detection Techniques in Unconstrained Environments
- Selecting Robust Features for Machine Learning Applications using Multidata Causal Discovery
- Equivariant Graph Neural Networks for Charged Particle Tracking
- MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos
- Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
- Automaton-Guided Curriculum Generation for Reinforcement Learning Agents
- An Entity-based Claim Extraction Pipeline for Real-world Biomedical Fact-checking
- Controllable Textual Inversion for Personalized Text-to-Image Generation
- Prompt Learning for News Recommendation
- Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
- Multi-granulariy Time-based Transformer for Knowledge Tracing
All 208
- Density Map Distillation for Incremental Object Counting
- Approximating Online Human Evaluation of Social Chatbots with Prompting
- OpenAL: Evaluation and Interpretation of Active Learning Strategies
- r-softmax: Generalized Softmax with Controllable Sparsity Rate
- Lady and the Tramp Nextdoor: Online Manifestations of Economic Inequalities in the Nextdoor Social Network
- Inhomogeneous graph trend filtering via a l2,0 cardinality penalty
- Towards preserving word order importance through Forced Invalidation
- BanditQ: Fair Bandits with Guaranteed Rewards
- Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis
- Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond
- A Billion-scale Foundation Model for Remote Sensing Images
- Open Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecture
- CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs
- The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
- LBMT team at VLSP2022-Abmusu: Hybrid method with text correlation and generative models for Vietnamese multi-document summarization
- TinyReptile: TinyML with Federated Meta-Learning
- Multi-scale Fusion Fault Diagnosis Method Based on Two-Dimensionaliztion Sequence in Complex Scenarios
- HPN: Personalized Federated Hyperparameter Optimization
- Automatic Gradient Descent: Deep Learning without Hyperparameters
- Wearable multi-color RAPD screening device
- Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph
- Electricity Demand Forecasting with Hybrid Statistical and Machine Learning Algorithms: Case Study of Ukraine
- LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images
- SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes
- Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification
- Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class
- Accelerating Globally Optimal Consensus Maximization in Geometric Vision
- Regression-based Deep-Learning predicts molecular biomarkers from pathology slides
- PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices
- Artificial Collective Intelligence Engineering: a Survey of Concepts and Perspectives
- Loop Closure Detection Based on Object-level Spatial Layout and Semantic Consistency
- NeAT: Neural Artistic Tracing for Beautiful Style Transfer
- RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
- Lecture Notes: Neural Network Architectures
- Balancing Privacy and Performance for Private Federated Learning Algorithms
- Online Spatio-Temporal Learning with Target Projection
- Pointless Global Bundle Adjustment With Relative Motions Hessians
- Evaluation of Differentially Constrained Motion Models for Graph-Based Trajectory Prediction
- Towards systematic intraday news screening: a liquidity-focused approach
- Video Event Restoration Based on Keyframes for Video Anomaly Detection
- Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums
- Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks
- Feudal Graph Reinforcement Learning
- Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection
- One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field
- Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection
- Generative modeling for time series via Schr"odinger bridge
- Actually Sparse Variational Gaussian Processes
- CrowdSim2: an Open Synthetic Benchmark for Object Detectors
- WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
- A Self-attention Knowledge Domain Adaptation Network for Commercial Lithium-ion Batteries State-of-health Estimation under Shallow Cycles
- Investigating Imbalances Between SAR and Optical Utilization for Multi-Modal Urban Mapping
- TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification
- If consciousness is dynamically relevant, artificial intelligence isn't conscious
- A Tale of Sampling and Estimation in Discounted Reinforcement Learning
- Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm
- Artificial intelligence based prediction on lung cancer risk factors using deep learning
- Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
- A Comprehensive Survey on Deep Graph Representation Learning
- Simultaneous Adversarial Attacks On Multiple Face Recognition System Components
- Semi-Supervised Relational Contrastive Learning
- A Hybrid Approach combining ANN-based and Conventional Demapping in Communication for Efficient FPGA-Implementation
- What Food Do We Tweet about on a Rainy Day?
- Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery
- Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond
- Learning Optimal Fair Scoring Systems for Multi-Class Classification
- A Deep Analysis of Transfer Learning Based Breast Cancer Detection Using Histopathology Images
- Continual Semantic Segmentation with Automatic Memory Sample Selection
- Human-machine cooperation for semantic feature listing
- Towards an Understanding and Explanation for Mixed-Initiative Artificial Scientific Text Detection
- Habits and goals in synergy: a variational Bayesian framework for behavior
- Bayes correlated equilibria, no-regret dynamics in Bayesian games, and the price of anarchy
- Relational Context Learning for Human-Object Interaction Detection
- Neural Multi-network Diffusion towards Social Recommendation
- Sim-T: Simplify the Transformer Network by Multiplexing Technique for Speech Recognition
- Detecting Anomalous Microflows in IoT Volumetric Attacks via Dynamic Monitoring of MUD Activity
- Efficient Feature Description for Small Body Relative Navigation using Binary Convolutional Neural Networks
- Biological Factor Regulatory Neural Network
- StageInteractor: Query-based Object Detector with Cross-stage Interaction
- Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR
- Federated Learning with Classifier Shift for Class Imbalance
- GRIL: A 2-parameter Persistence Based Vectorization for Machine Learning
- Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising
- Computer Vision-Aided Intelligent Monitoring of Coffee: Towards Sustainable Coffee Production
- A priori compression of convolutional neural networks for wave simulators
- PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region
- Mask-Based Modeling for Neural Radiance Fields
- Panoramic Image-to-Image Translation
- Multi-Graph Convolution Network for Pose Forecasting
- Data-Efficient Image Quality Assessment with Attention-Panel Decoder
- Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
- Sentence-Level Relation Extraction via Contrastive Learning with Descriptive Relation Prompts
- Reinforcement Learning Tutor Better Supported Lower Performers in a Math Task
- Robust Dequantization of the Quantum Singular value Transformation and Quantum Machine Learning Algorithms
- Life Regression based Patch Slimming for Vision Transformers
- Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPT
- Explicit and Implicit Semantic Ranking Framework
- Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair
- A Data-Driven State Aggregation Approach for Dynamic Discrete Choice Models
- AffectMachine-Classical: A novel system for generating affective classical music
- Regulatory Markets: The Future of AI Governance
- Financial Time Series Forecasting using CNN and Transformer
- Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator
- SATR: Zero-Shot Semantic Segmentation of 3D Shapes
- Improving Vision-and-Language Navigation by Generating Future-View Image Semantics
- Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing
- Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning
- Efficiently Collecting Training Dataset for 2D Object Detection by Online Visual Feedback