Papers
Tue 4 Apr 2023
226 papers
- Quantum Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image EditingDiffusion models → 3D, point cloud and scene generation
- Multi-Class Unlearning for Image Classification via Weight FilteringLLM safety and security → Machine unlearning
- Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
- REFINER: Reasoning Feedback on Intermediate RepresentationsLLM reasoning → Test-time compute and efficient thinking
- PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image DiffusionDiffusion models → 3D, point cloud and scene generation
- Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory DiffusionDiffusion models → Diffusion and flow policies for robotics
- CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and GeneralizationDiffusion models → Medical imaging and segmentation
- Using Language Models For Knowledge Acquisition in Natural Language Reasoning ProblemsLLM reasoning → Reasoning benchmarks and evaluation
- Black Box Few-Shot Adaptation for Vision-Language modelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good TeacherKnowledge distillation → Federated, robust and private distillation
- Denoising Diffusion Probabilistic Models to Predict the Density of Molecular CloudsDiffusion models → Diffusion foundations and sampling
- Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural NetworksLLM reasoning → Reasoning benchmarks and evaluation
- A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and MaterialDiffusion models → Flow matching, time series and science
- Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
- Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Exploring Vision-Language Models for Imbalanced LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- The power of motifs as inductive bias for learning molecular distributions
- Optimizing Group Utility in Itinerary Planning: A Strategic and Crowd-Aware Approach
- DiaTrend: A dataset from advanced diabetes technology to enable development of novel analytic solutions
- One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era
- On algorithmically boosting fixed-point computations
- Safe Explicable Planning
- Online Learning for Scheduling MIP Heuristics
- Adaptive Feature Fusion: Enhancing Generalization in Deep Learning Models
- VISHIEN-MAAT: Scrollytelling visualization design for explaining Siamese Neural Network concept to non-technical users
- FedBot: Enhancing Privacy in Chatbots with Federated Learning
- Adaptive Ensemble Learning: Boosting Model Performance through Intelligent Feature Fusion in Deep Neural Networks
- Competitive plasticity to reduce the energetic costs of learning
- Fully Variational Noise-Contrastive Estimation
- Learning to Predict Short-Term Volatility with Order Flow Image Representation
- Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model
- I2I: Initializing Adapters with Improvised Knowledge
- GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
- Learning to Recover Spectral Reflectance from RGB Images
- Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT
- Can Adversarial Networks Make Uninformative Colonoscopy Video Frames Clinically Informative?
- Re-Evaluating LiDAR Scene Flow for Autonomous Driving
- ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention
- Structure Learning with Continuous Optimization: A Sober Look and Beyond
- A Data Fusion Framework for Multi-Domain Morality Learning
- Sequential Linearithmic Time Optimal Unimodal Fitting When Minimizing Univariate Linear Losses
- Geotechnical Parrot Tales (GPT): Harnessing Large Language Models in geotechnical engineering
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- OpenContrails: Benchmarking Contrail Detection on GOES-16 ABI
- Initialization Approach for Nonlinear State-Space Identification via the Subspace Encoder Approach
- DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation
- Deep learning for diffusion in porous media
- MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations
- Uncertainty estimation in Deep Learning for Panoptic segmentation
- The CAMELS project: Expanding the galaxy formation model space with new ASTRID and 28-parameter TNG and SIMBA suites
- Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search
- Decentralized and Privacy-Preserving Learning of Approximate Stackelberg Solutions in Energy Trading Games with Demand Response Aggregators
- EduceLab-Scrolls: Verifiable Recovery of Text from Herculaneum Papyri using X-ray CT
- Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data
- GUTS: Generalized Uncertainty-Aware Thompson Sampling for Multi-Agent Active Search
- Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
- Generating Continual Human Motion in Diverse 3D Scenes
- Deep Learning for Automated Experimentation in Scanning Transmission Electron Microscopy
- Effective Theory of Transformers at Initialization
- Bounding probabilities of causation through the causal marginal problem
- Online Joint Assortment-Inventory Optimization under MNL Choices
- NPC: Neural Point Characters from Video
- EGC: Image Generation and Classification via a Diffusion Energy-Based Model
- FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer
- Multi-Level Contrastive Learning for Dense Prediction Task
- OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
- GlueStick: Robust Image Matching by Sticking Points and Lines Together
- Risk-Aware Distributed Multi-Agent Reinforcement Learning
- MonoHuman: Animatable Human Neural Field from Monocular Video
- Revisiting the Evaluation of Image Synthesis with GANs
- ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
- Cross-modulated Few-shot Image Generation for Colorectal Tissue Classification
- Side Channel-Assisted Inference Leakage from Machine Learning-based ECG Classification
- SM/VIO: Robust Underwater State Estimation Switching Between Model-based and Visual Inertial Odometry
- USTC FLICAR: A Sensors Fusion Dataset of LiDAR-Inertial-Camera for Heavy-duty Autonomous Aerial Work Robots
- Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
- Dialogue-Contextualized Re-ranking for Medical History-Taking
- ERM++: An Improved Baseline for Domain Generalization
- MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities
- Model-corrected learned primal-dual models for fast limited-view photoacoustic tomography
- Ethylene Leak Detection Based on Infrared Imaging: A Benchmark
- AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation
- Randomized Adversarial Style Perturbations for Domain Generalization
- LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
- High-Throughput Vector Similarity Search in Knowledge Graphs
- Resources and Few-shot Learners for In-context Learning in Slavic Languages
- Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
- On the Variance of Neural Network Training with respect to Test Sets and Distributions
- Leveraging Deep Learning Approaches for Deepfake Detection: A Review
- Torch-Choice: A PyTorch Package for Large-Scale Choice Modeling with Python
- Cross-Class Feature Augmentation for Class Incremental Learning
- InfluencerRank: Discovering Effective Influencers via Graph Convolutional Attentive Recurrent Neural Networks
- Robustness Benchmark of Road User Trajectory Prediction Models for Automated Driving
- San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants
- Sociocultural knowledge is needed for selection of shots in hate speech detection tasks
- Measure theoretic results for approximation by neural networks with limited weights
- Incremental Verification of Neural Networks
- Deep-BIAS: Detecting Structural Bias using Explainable AI
- SportsPose -- A Dynamic 3D sports pose dataset
All 226
- A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancement
- Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
- Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning
- Evaluating Synthetic Pre-Training for Handwriting Processing Tasks
- BugNIST -- a Large Volumetric Dataset for Object Detection under Domain Shift
- Neural Field Convolutions by Repeated Differentiation
- Learning to Name Classes for Vision and Language Models
- A Survey on Vertical Federated Learning: From a Layered Perspective
- Learning Stable and Robust Linear Parameter-Varying State-Space Models
- CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networks
- Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
- HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
- Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training
- Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification
- Machine Learning Discovery of Optimal Quadrature Rules for Isogeometric Analysis
- Locality-constrained autoregressive cum conditional normalizing flow for lattice field theory simulations
- Influence of Myocardial Infarction on QRS Properties: A Simulation Study
- Mixing predictions for online metric algorithms
- A User-Centered, Interactive, Human-in-the-Loop Topic Modelling System
- A differentiable programming framework for spin models
- Convergence of alternating minimisation algorithms for dictionary learning
- Incorporating Unlabelled Data into Bayesian Neural Networks
- Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition
- Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation
- Adaptive learning of effective dynamics: Adaptive real-time, online modeling for complex systems
- Characterizing the contribution of dependent features in XAI methods
- Decoupling Dynamic Monocular Videos for Dynamic View Synthesis
- Towards Open-Vocabulary Video Instance Segmentation
- Rumour Detection and Analysis on Twitter
- Learning and Concentration for High Dimensional Linear Gaussians: an Invariant Subspace Approach
- Cross-modal tumor segmentation using generative blending augmentation and self training
- Optimal Transport for Correctional Learning
- Inverse Unscented Kalman Filter
- HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering
- High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
- Can BERT eat RuCoLA? Topological Data Analysis to Explain
- Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking
- Re-thinking Model Inversion Attacks Against Deep Neural Networks
- A Survey on Contextualised Semantic Shift Detection
- An Embedding-based Approach to Inconsistency-tolerant Reasoning with Inconsistent Ontologies
- On the Stability-Plasticity Dilemma of Class-Incremental Learning
- Cross-Domain Image Captioning with Discriminative Finetuning
- Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas
- SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering
- Multidimensional Perceptron for Efficient and Explainable Long Text Classification
- Label-guided Attention Distillation for Lane Segmentation
- De-novo Identification of Small Molecules from Their GC-EI-MS Spectra
- Equivariant Parameter Sharing for Porous Crystalline Materials
- Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
- An interpretability framework for Similar case matching
- SimCSum: Joint Learning of Simplification and Cross-lingual Summarization for Cross-lingual Science Journalism
- Image Blind Denoising Using Dual Convolutional Neural Network with Skip Connection
- EDeR: A Dataset for Exploring Dependency Relations Between Events
- Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder
- Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA
- Primitive Simultaneous Optimization of Similarity Metrics for Image Registration
- MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network
- Unsupervised Improvement of Factual Knowledge in Language Models
- PAC-Based Formal Verification for Out-of-Distribution Data Detection
- Multi-Channel Time-Series Person and Soft-Biometric Identification
- HALO: Hazard-Aware Landing Optimization for Autonomous Systems
- Untargeted Near-collision Attacks on Biometrics: Real-world Bounds and Theoretical Limits
- MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan
- The expressive power of pooling in Graph Neural Networks
- Spatiotemporal and Semantic Zero-inflated Urban Anomaly Prediction
- Arrhythmia Classifier Based on Ultra-Lightweight Binary Neural Network
- A real-time algorithm for human action recognition in RGB and thermal video
- Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment
- Optimal rates of approximation by shallow ReLUk neural networks and applications to nonparametric regression
- G2PTL: A Pre-trained Model for Delivery Address and its Applications in Logistics System
- Real-time Driver Monitoring Systems on Edge AI Device
- MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds
- Heating and dynamics of the Solar atmosphere
- Meta-Learning with a Geometry-Adaptive Preconditioner
- Regularization of the policy updates for stabilizing Mean Field Games
- Effects of spatiotemporal correlations in wind data on neural network-based wind predictions
- A Brief Review of Explainable Artificial Intelligence in Healthcare
- Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation
- Implementing Dynamic Programming in Computability Logic Web
- PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
- FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
- IterativePFN: True Iterative Point Cloud Filtering
- Online Learning with Adversaries: A Differential-Inclusion Analysis
- FisHook -- An Optimized Approach to Marine Specie Classification using MobileNetV2
- LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation
- Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation
- Robust Outlier Rejection for 3D Registration with Variational Bayes
- Handling Concept Drift in Global Time Series Forecasting
- EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition
- RARE: Robust Masked Graph Autoencoder
- OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting
- GPT-4 to GPT-3.5: 'Hold My Scalpel' -- A Look at the Competency of OpenAI's GPT on the Plastic Surgery In-Service Training Exam
- SLPerf: a Unified Framework for Benchmarking Split Learning
- Physics-aware Roughness Optimization for Diffractive Optical Neural Networks
- DCANet: Dual Convolutional Neural Network with Attention for Image Blind Denoising
- A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection
- Multi model LSTM architecture for Track Association based on Automatic Identification System Data
- Improved Visual Fine-tuning with Natural Language Supervision
- End-to-End Latency Optimization of Multi-view 3D Reconstruction for Disaster Response
- To ChatGPT, or not to ChatGPT: That is the question!
- Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision
- Blockwise Compression of Transformer-based Models without Retraining
- Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
- The Vector Grounding Problem
- FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction
- Unsupervised Brain Tumor Segmentation with Image-based Prompts
- DLRover-RM: Resource Optimization for Deep Recommendation Models Training in the Cloud
- Time-space-frequency feature Fusion for 3-channel motor imagery classification
- Attention Map Guided Transformer Pruning for Edge Device
- Clustering Validation with The Area Under Precision-Recall Curves
- Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning
- Virtual Avatar Stream: a cost-down approach to the Metaverse experience
- NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression
- A Deep Multi-Modal Cyber-Attack Detection in Industrial Control Systems
- Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos
- Optimizing Irrigation Efficiency using Deep Reinforcement Learning in the Field
- VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
- TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
- Reducing Discretization Error in the Frank-Wolfe Method
- Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots
- Learning from data with structured missingness
- Learned Tree Search for Long-Horizon Social Robot Navigation in Shared Airspace
- Conformalized Unconditional Quantile Regression
- CascadeNS: Confidence-Cascaded Neurosymbolic Model for Sarcasm Detection
- Thematic context vector association based on event uncertainty for Twitter
- Scientists' Perspectives on the Potential for Generative AI in their Fields