Papers
Mon 21 Nov 2022
263 papers
- Investigating Prompt Engineering in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- SinFusion: Training Diffusion Models on a Single Image or VideoDiffusion models → Video generation
- Robotic Skill Acquisition via Instruction Augmentation with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Multitask Vision-Language Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Exploring Discrete Diffusion Models for Image CaptioningDiffusion models → Image generation, text-to-image and editing
- SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated OptimizationLLM safety and security → Federated unlearning and poisoning
- Neural Meta-Symbolic Reasoning and LearningLLM reasoning → Reasoning benchmarks and evaluation
- Model-based Trajectory Stitching for Improved Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Improving Multimodal Interactive Agents with Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- ClipCrop: Conditioned Cropping Driven by Vision-Language ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Backdoor Attacks on Multiagent Collaborative SystemsLLM safety and security → Prompt injection and agent security
- DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative AdapterDiffusion models → Image generation, text-to-image and editing
- VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space ModelsState-space sequence models (S4, Mamba) → Physiological signal modeling
- You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language ModelMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
- Doubly Contrastive End-to-End Semantic Segmentation for Autonomous Driving under Adverse WeatherEnd-to-end autonomous driving → VLMs for autonomous driving
- Resolving Uncertain Case Identifiers in Interaction Logs: A User Study
- EVNet: An Explainable Deep Network for Dimension Reduction
- Classification of Human Monkeypox Disease Using Deep Learning Models and Attention Mechanisms
- Validating Large Language Models with ReLM
- Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning
- Arbitrarily Large Labelled Random Satisfiability Formulas for Machine Learning Training
- Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization
- The applicability of transperceptual and deep learning approaches to the study and mimicry of complex cartilaginous tissues
- AICOM-MP: an AI-based Monkeypox Detector for Resource-Constrained Environments
- A Brief Overview of AI Governance for Responsible Machine Learning Systems
- Safe Optimization of an Industrial Refrigeration Process Using an Adaptive and Explorative Framework
- Identifying gender bias in blockbuster movies through the lens of machine learning
- PiRL: Participant-Invariant Representation Learning for Healthcare
- Neural Dependencies Emerging from Learning Massive Categories
- PreMa: Predictive Maintenance of Solenoid Valve in Real-Time at Embedded Edge-Level
- EM's Convergence in Gaussian Latent Tree Models
- FLEX: Full-Body Grasping Without Full-Body Grasps
- Evaluating the Knowledge Dependency of Questions
- Private Ad Modeling with DP-SGD
- Equality of Effort via Algorithmic Recourse
- A Bi-level Nonlinear Eigenvector Algorithm for Wasserstein Discriminant Analysis
- TEMPERA: Test-Time Prompting via Reinforcement Learning
- Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition
- Addressing Mistake Severity in Neural Networks with Semantic Knowledge
- Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
- Classification of Melanocytic Nevus Images using BigTransfer (BiT)
- LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation
- Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks
- Bayesian Learning for Neural Networks: an algorithmic survey
- Twin-S: A Digital Twin for Skull-base Surgery
- Learnable Graph Convolutional Attention Networks
- Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformers
- AdaFocal: Calibration-aware Adaptive Focal Loss
- Towards Live 3D Reconstruction from Wearable Video: An Evaluation of V-SLAM, NeRF, and Videogrammetry Techniques
- Fairness Increases Adversarial Vulnerability
- High-Perceptual Quality JPEG Decoding via Posterior Sampling
- Multi-Directional Subspace Editing in Style-Space
- CONFIG: Constrained Efficient Global Optimization for Closed-Loop Control System Optimization with Unmodeled Constraints
- Machine-learned climate model corrections from a global storm-resolving model
- RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network
- Sample-optimal classical shadows for pure states
- Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning
- Self-Supervised Pre-training of 3D Point Cloud Networks with Image Data
- Unsupervised extraction, labelling and clustering of segments from clinical notes
- Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions
- Multi-Spectral Image Classification with Ultra-Lean Complex-Valued Models
- The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts
- DS-GPS : A Deep Statistical Graph Poisson Solver (for faster CFD simulations)
- Hierarchical Graph Structures for Congestion and ETA Prediction
- From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
- A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
- Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
- A Graph Regularized Point Process Model For Event Propagation Sequence
- Last-Mile Embodied Visual Navigation
- Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes
- SceneComposer: Any-Level Semantic Image Synthesis
- SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
- SPARF: Neural Radiance Fields from Sparse and Noisy Poses
- PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation
- Teaching Structured Vision&Language Concepts to Vision&Language Models
- Parametric Classification for Generalized Category Discovery: A Baseline Study
- Legal and Political Stance Detection of SCOTUS Language
- First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
- Neural tangent kernel analysis of PINN for advection-diffusion equation
- CLAWSAT: Towards Both Robust and Accurate Code Models
- Adaptive Stochastic Optimisation of Nonconvex Composite Objectives
- ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
- Towards continually learning new languages
- Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
- High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data
- Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)
- Disentangled Representation Learning
- TinyQMIX: Distributed Access Control for mMTC via Multi-agent Reinforcement Learning
- Deep Signature Algorithm for Multi-dimensional Path-Dependent Options
- Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
- Unsupervised Echocardiography Registration through Patch-based MLPs and Transformers
- PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
- Multiresolution kernel matrix algebra
- Constructing Effective Machine Learning Models for the Sciences: A Multidisciplinary Perspective
- Mean Shift Mask Transformer for Unseen Object Instance Segmentation
- Measuring Harmful Representations in Scandinavian Language Models
- Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
- Representational dissimilarity metric spaces for stochastic neural networks
- Implicit Training of Energy Model for Structure Prediction
All 263
- Benchmarking Edge Computing Devices for Grape Bunches and Trunks Detection using Accelerated Object Detection Single Shot MultiBox Deep Learning Models
- NeRF-RPN: A general framework for object detection in NeRFs
- Parametric information geometry with the package Geomstats
- Normalizing Flow with Variational Latent Representation
- Understanding and Improving Visual Prompting: A Label-Mapping Perspective
- Improved Touchless Respiratory Rate Sensing
- PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
- Active Discrimination Learning for Gaussian Process Models
- Linear Stability Hypothesis and Rank Stratification for Nonlinear Models
- Simultaneously Updating All Persistence Values in Reinforcement Learning
- CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation
- Improving multiple-try Metropolis with local balancing
- Plug and Play Active Learning for Object Detection
- Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering
- Deformable Voxel Grids for Shape Comparisons
- Semantic Segmentation for Fully Automated Macrofouling Analysis on Coatings after Field Exposure
- Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks
- Guided Depth Super-Resolution by Deep Anisotropic Diffusion
- DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder
- Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching
- Neural network based generation of a 1-dimensional stochastic field with turbulent velocity statistics
- SLLEN: Semantic-aware Low-light Image Enhancement Network
- Neural networks trained with SGD learn distributions of increasing complexity
- Decomposing 3D Neuroimaging into 2+1D Processing for Schizophrenia Recognition
- Programming by Example and Text-to-Code Translation for Conversational Code Generation
- PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings
- Efficient Second-Order Plane Adjustment
- Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning
- ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation
- Bursting the Burden Bubble? An Assessment of Sharma et al.'s Counterfactual-based Fairness Metric
- Segmentation, Classification, and Quality Assessment of UW-OCTA Images for the Diagnosis of Diabetic Retinopathy
- Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
- Differentiable Physics-based Greenhouse Simulation
- Compositional Scene Modeling with Global Object-Centric Representations
- Self-Adaptive, Dynamic, Integrated Statistical and Information Theory Learning
- Efficient Generalization Improvement Guided by Random Weight Perturbation
- Deanthropomorphising NLP: Can a Language Model Be Conscious?
- Applications of statistical causal inference in software engineering
- A Dataset for Greek Traditional and Folk Music: Lyra
- Background-Mixed Augmentation for Weakly Supervised Change Detection
- Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning
- 3D Detection and Characterisation of ALMA Sources through Deep Learning
- Exhaustive Symbolic Regression
- Motor Imagery Decoding Using Ensemble Curriculum Learning and Collaborative Training
- Methodology for Holistic Reference Modeling in Systems Engineering
- Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint
- SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training
- Place Recognition under Occlusion and Changing Appearance via Disentangled Representations
- N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution
- ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
- Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
- MATE: Masked Autoencoders are Online 3D Test-Time Learners
- Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
- Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
- Data Leakage and Evaluation Issues in Micro-Expression Analysis
- Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation
- Blur Interpolation Transformer for Real-World Motion from Blur
- SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
- L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages
- DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata
- RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
- Structural Optimization of Factor Graphs for Symbol Detection via Continuous Clustering and Machine Learning
- General time-reversal equivariant neural network potential for magnetic materials
- An Implicit Parametric Morphable Dental Model
- Learning Low-Rank Representations for Model Compression
- A Curriculum-Training-Based Strategy for Distributing Collocation Points during Physics-Informed Neural Network Training
- Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels
- TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis
- PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism
- LISA: Localized Image Stylization with Audio via Implicit Neural Representation
- Self adaptive global-local feature enhancement for radiology report generation
- Modelling spatiotemporal turbulent dynamics with the convolutional autoencoder echo state network
- Learning on tree architectures outperforms a convolutional feedforward network
- Enterprise Model Library for Business-IT-Alignment
- Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models
- High-Order Optimization of Gradient Boosted Decision Trees
- cegpy: Modelling with Chain Event Graphs in Python
- AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model
- Crowdsensing-based Road Damage Detection Challenge (CRDDC-2022)
- Extended Multilingual Protest News Detection -- Shared Task 1, CASE 2021 and 2022
- Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2022): Workshop and Shared Task Report
- Blind Knowledge Distillation for Robust Image Classification
- Object-level 3D Semantic Mapping using a Network of Smart Edge Sensors
- Are All Combinations Equal? Combining Textual and Visual Features with Multiple Space Learning for Text-Based Video Retrieval
- Rooms with Text: A Dataset for Overlaying Text Detection
- Data-Driven Offline Decision-Making via Invariant Representation Learning
- Orientation recognition and correction of Cardiac MRI with deep neural network
- Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation
- OPTION: OPTImization Algorithm Benchmarking ONtology
- Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
- A Generalized EigenGame with Extensions to Multiview Representation Learning
- SPIN: Simulated Poisoning and Inversion Network for Federated Learning-Based 6G Vehicular Networks
- Recovering Fine Details for Neural Implicit Surface Reconstruction
- DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
- EHSNet: End-to-End Holistic Learning Network for Large-Size Remote Sensing Image Semantic Segmentation
- Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
- Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
- H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions
- Novel transfer learning schemes based on Siamese networks and synthetic data
- TCBERT: A Technical Report for Chinese Topic Classification BERT
- Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
- Exploring Physical Latent Spaces for High-Resolution Flow Restoration
- In-sample Curriculum Learning by Sequence Completion for Natural Language Generation
- SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes
- Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer
- Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challenge
- Intelligent Computing: The Latest Advances, Challenges and Future
- POSSE-kNN: Pathwise Out-of-Bag Selected Subspace Ensembles for Binary Classification
- DrapeNet: Garment Generation and Self-Supervised Draping
- VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
- LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN
- Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier
- Discovering Evolution Strategies via Meta-Black-Box Optimization
- From Traditional Adaptive Data Caching to Adaptive Context Caching: A Survey
- Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations
- UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
- Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection
- Video Background Music Generation: Dataset, Method and Evaluation
- LSTM based models stability in the context of Sentiment Analysis for social media
- Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning
- L-MAE: Masked Autoencoders are Semantic Segmentation Datasets Augmenter
- RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments
- Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
- Explainable Model-specific Algorithm Selection for Multi-Label Classification
- Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams
- TimbreCLIP: Connecting Timbre to Text and Images
- Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images
- Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis System
- STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction
- Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret
- Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task
- SegNeRF: 3D Part Segmentation with Neural Radiance Fields
- DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
- Contrastive Masked Autoencoders for Self-Supervised Video Hashing
- Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
- Cultural Re-contextualization of Fairness Research in Language Technologies in India
- FLNeRF: 3D Facial Landmarks Estimation in Neural Radiance Fields
- Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance
- Cross-Modal Contrastive Learning for Robust Reasoning in VQA
- Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision
- L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi
- DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation
- Causal Fairness Assessment of Treatment Allocation with Electronic Health Records
- Deep Projective Rotation Estimation through Relative Supervision
- A review of laser scanning for geological and geotechnical applications in underground mining
- Spatio-temporal point processes with deep non-stationary kernels
- NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
- CoPEM: Cooperative Perception Error Models for Autonomous Driving
- Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning
- HARL: Hierarchical Adaptive Reinforcement Learning Based Auto Scheduler for Neural Networks
- The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
- Vision Transformer with Super Token Sampling
- A Benchmark of Video-Based Clothes-Changing Person Re-Identification
- Unsupervised Explanation Generation via Correct Instantiations
- Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation
- Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification
- From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition
- Unifying Vision-Language Representation Space with Single-tower Transformer
- Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution
- Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training
- Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
- Enhancing Accuracy and Robustness of Steering Angle Prediction with Attention Mechanism
- Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training