Papers
Thu 6 Apr 2023
210 papers
- RoSteALS: Robust Steganography using Autoencoder Latent SpaceLLM safety and security → Watermarking generated content and models
- Towards Coherent Image Inpainting Using Denoising Diffusion Implicit ModelsDiffusion models → 3D, point cloud and scene generation
- Explainable AI And Visual Reasoning: Insights From RadiologyLLM reasoning → Clinical and biomedical applications
- Diffusion Models as Masked AutoencodersDiffusion models → Diffusion foundations and sampling
- When do you need Chain-of-Thought Prompting for ChatGPT?LLM reasoning → Prompting and chain-of-thought reasoning
- Inst-Inpaint: Instructing to Remove Objects with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic ExpertsMixture-of-experts → Medical and biomedical MoE
- Face Animation with an Attribute-Guided Diffusion ModelDiffusion models → Audio, speech and music
- SketchFFusion: Sketch-guided image editing with diffusion modelDiffusion models → Image generation, text-to-image and editing
- Continual Detection Transformer for Incremental Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Inductive Graph UnlearningLLM safety and security → Graph unlearning
- Investigating Chain-of-thought with ChatGPT for Stance Detection on Social MediaLLM reasoning → Causal reasoning in LLMs
- Benchmarking Robustness to Text-Guided CorruptionsDiffusion models → Robustness, privacy and adversarial aspects
- GIF: A General Graph Unlearning Strategy via Influence FunctionLLM safety and security → Graph unlearning
- Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity ModelingMixture-of-experts → MoE for time series and graphs
- End-to-end Manipulator Calligraphy Planning via Variational Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Ultra-Fast Zernike Moments using FFT and GPU
- ElegansNet: a brief scientific report and initial experiments
- A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction
- Low-Latency Online Multiplier with Reduced Activities and Minimized Interconnect for Inner Product Arrays
- A Framework for Combustion Chemistry Acceleration with DeepONets
- ChatGPT: More than a Weapon of Mass Deception, Ethical challenges and responses from the Human-Centered Artificial Intelligence (HCAI) perspective
- Stock Price Predictability and the Business Cycle via Machine Learning
- Robust Calibrate Proxy Loss for Deep Metric Learning
- Attentive Q-Matrix Learning for Knowledge Tracing
- Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories
- Inductive biases in deep learning models for weather prediction
- Conformal Regression in Calorie Prediction for Team Jumbo-Visma
- Biological Sequence Kernels with Guaranteed Flexibility
- Therbligs in Action: Video Understanding through Motion Primitives
- To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement
- Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Start
- InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning
- R2Former: Unified Retrieval and Reranking Transformer for Place Recognition
- Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks
- Adoption of AI Technology in the Music Mixing Workflow: An Investigation
- Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
- Noise-Robust Dense Retrieval via Contrastive Alignment Post Training
- Using LSTM and GRU With a New Dataset for Named Entity Recognition in the Arabic Language
- Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning
- Deep Learning for Opinion Mining and Topic Classification of Course Reviews
- Personalising Digital Health Behaviour Change Interventions using Machine Learning and Domain Knowledge
- Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval
- InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference
- Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training
- Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery
- Scalable Causal Discovery with Score Matching
- Self-Supervised Video Similarity Learning
- Interpretable statistical representations of neural population dynamics and geometry
- Handling Wikidata Qualifiers in Reasoning
- Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization
- Training-Free Layout Control with Cross-Attention Guidance
- TopNet: Transformer-based Object Placement Network for Image Compositing
- Reliable learning in challenging environments
- EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation
- From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management
- Decision-Focused Model-based Reinforcement Learning for Reward Transfer
- NMR shift prediction from small data quantities
- Towards Interpretable Mental Health Analysis with Large Language Models
- Graph Collaborative Signals Denoising and Augmentation for Recommendation
- Spintronic Physical Reservoir for Autonomous Prediction and Long-Term Household Energy Load Forecasting
- Maximal Ordinal Two-Factorizations
- On the Learnability of Multilabel Ranking
- ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about
- DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection
- Adaptive Decision-Making with Constraints and Dependent Losses: Performance Guarantees and Applications to Online and Nonlinear Identification
- Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
- Neural Operator Learning for Ultrasound Tomography Inversion
- What makes a good data augmentation for few-shot unsupervised image anomaly detection?
- SE-shapelets: Semi-supervised Clustering of Time Series Using Representative Shapelets
- DC2: Dual-Camera Defocus Control by Learning to Refocus
- SegGPT: Segmenting Everything In Context
- Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention
- LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis
- Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
- Instruction Tuning with GPT-4
- That's What I Said: Fully-Controllable Talking Face Generation
- DiffMimic: Efficient Motion Mimicking with Differentiable Physics
- Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
- Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
- Causal Discovery with Score Matching on Additive Models with Arbitrary Noise
- ImageEye: Batch Image Processing Using Program Synthesis
- SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
- A Bayesian Framework for Causal Analysis of Recurrent Events with Timing Misalignment
- Large language models effectively leverage document-level context for literary translation, but critical errors persist
- Synthetic Data in Healthcare
- Assessing the Reproducibility of Machine-learning-based Biomarker Discovery in Parkinson's Disease
- Anomaly Detection via Gumbel Noise Score Matching
- Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Models
- On the Pareto Front of Multilingual Neural Machine Translation
- Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching
- Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster
- SLM: End-to-end Feature Selection via Sparse Learnable Masks
- HOTGP -- Higher-Order Typed Genetic Programming
- RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networks
- Micron-BERT: BERT-based Facial Micro-Expression Recognition
- Improving automatic endoscopic stone recognition using a multi-view fusion approach enhanced with two-step transfer learning
- Krylov Methods are (nearly) Optimal for Low-Rank Approximation
- The Concept of Forward-Forward Learning Applied to a Multi Output Perceptron
- Pairwise Ranking with Gaussian Kernels
All 210
- Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream
- Deep learning-based image exposure enhancement as a pre-processing for an accurate 3D colon surface reconstruction
- CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition
- Synthesizing Anyone, Anywhere, in Any Pose
- Bridging the Language Gap: Knowledge Injected Multilingual Question Answering
- Patch-wise Features for Blur Image Classification
- Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
- Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions
- Parameterized Approximation Schemes for Clustering with General Norm Objectives
- Evaluating the Robustness of Machine Reading Comprehension Models to Low Resource Entity Renaming
- BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning
- From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection
- VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
- Spike Stream Denoising via Spike Camera Simulation
- Is it conceivable that neurogenesis, neural Darwinism, and species evolution could all serve as inspiration for the creation of evolutionary deep neural networks?
- Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
- Efficient SAGE Estimation via Causal Structure Learning
- Geometric-aware Pretraining for Vision-centric 3D Object Detection
- Retention Is All You Need
- Multi-task learning for tissue segmentation and tumor detection in colorectal cancer histology slides
- Static Fuzzy Bag-of-Words: a lightweight sentence embedding algorithm
- Spectral Gap Regularization of Neural Networks
- PopulAtion Parameter Averaging (PAPA)
- Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects
- Data-driven HVAC Control Using Symbolic Regression: Design and Implementation
- Adaptive Student's t-distribution with method of moments moving estimator for nonstationary time series
- An experimental study in Real-time Facial Emotion Recognition on new 3RL dataset
- Almost optimal manipulation of a pair of alternatives
- Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms
- Generalization with Reverse-Calibration of Well and Seismic Data Using Machine Learning Methods for Complex Reservoirs Predicting During Early-Stage Geological Exploration Oil Field
- ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
- Multi-Linear Kernel Regression and Imputation in Data Manifolds
- Modelling customer lifetime-value in the retail banking industry
- Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
- Compression of enumerations and gain
- Tensor Slicing and Optimization for Multicore NPUs
- PointCAT: Cross-Attention Transformer for point cloud
- IoT Federated Blockchain Learning at the Edge
- Visualizing Skiers' Trajectories in Monocular Videos
- Natural Language Robot Programming: NLP integrated with autonomous robotic grasping
- Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation
- Leveraging Social Interactions to Detect Misinformation on Social Media
- Spritz-PS: Validation of Synthetic Face Images Using a Large Dataset of Printed Documents
- Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions
- Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations
- Deep Long-Short Term Memory networks: Stability properties and Experimental validation
- Training a Two Layer ReLU Network Analytically
- Synthetic Hard Negative Samples for Contrastive Learning
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
- When approximate design for fast homomorphic computation provides differential privacy guarantees
- Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
- FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
- Adaptable and Interpretable Framework for Novelty Detection in Real-Time IoT Systems
- Multi-label classification of open-ended questions with BERT
- InterFormer: Real-time Interactive Image Segmentation
- Dr. KID: Direct Remeshing and K-set Isometric Decomposition for Scalable Physicalization of Organic Shapes
- All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes
- Boundary-Denoising for Video Activity Localization
- Convolutional neural networks for crack detection on flexible road pavements
- Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
- Mask Detection and Classification in Thermal Face Images
- Computer-aided Diagnosis of Malaria through Transfer Learning using the ResNet50 Backbone
- The Governance of Physical Artificial Intelligence
- Super-Resolving Face Image by Facial Parsing Information
- Efficient Audio Captioning Transformer with Patchout and Text Guidance
- Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
- Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks
- MemeFier: Dual-stage Modality Fusion for Image Meme Classification
- Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry
- SpanRE: Entities and Overlapping Relations Extraction Based on Spans and Entity Attention
- Variable-Complexity Weighted-Tempered Gibbs Samplers for Bayesian Variable Selection
- Affect as a proxy for literary mood
- Object-centric Inference for Language Conditioned Placement: A Foundation Model based Approach
- Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
- ViralVectors: Compact and Scalable Alignment-free Virome Feature Generation
- Automatic ICD-10 Code Association: A Challenging Task on French Clinical Texts
- GA-HQS: MRI reconstruction via a generically accelerated unfolding approach
- Tag that issue: Applying API-domain labels in issue tracking systems
- Protecting User Privacy in Online Settings via Supervised Learning
- Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection
- Learning to Learn with Indispensable Connections
- Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal
- MULLER: Multilayer Laplacian Resizer for Vision
- A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation
- Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
- Logistic-Normal Likelihoods for Heteroscedastic Label Noise
- Patch-aware Batch Normalization for Improving Cross-domain Robustness
- Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
- Synthetic Sample Selection for Generalized Zero-Shot Learning
- Robust Neural Architecture Search
- Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
- NTK-SAP: Improving neural network pruning by aligning training dynamics
- Whose Text Is It Anyway? Exploring BigCode, Intellectual Property, and Ethics
- TBDetector:Transformer-Based Detector for Advanced Persistent Threats with Provenance Graph
- Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
- Probing the Purview of Neural Networks via Gradient Analysis
- DoUnseen: Tuning-Free Class-Adaptive Object Detection of Unseen Objects for Robotic Grasping
- Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing
- SoK: Machine Learning for Continuous Integration
- Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
- DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model
- Approach Intelligent Writing Assistants Usability with Seven Stages of Action
- GPT detectors are biased against non-native English writers
- 4D Agnostic Real-Time Facial Animation Pipeline for Desktop Scenarios
- Causal Repair of Learning-enabled Cyber-physical Systems
- Pragmatically Appropriate Diversity for Dialogue Evaluation
- HomPINNs: homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions
- Source-free Domain Adaptation Requires Penalized Diversity
- DeLiRa: Self-Supervised Depth, Light, and Radiance Fields