Papers
Tue 13 Dec 2022
160 papers
- CREPE: Can Vision-Language Foundation Models Reason Compositionally?Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image InpaintingDiffusion models → Image generation, text-to-image and editing
- Localized Latent Updates for Fine-Tuning Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- DifFace: Blind Face Restoration with Diffused Error ContractionDiffusion models → Inverse problems and image restoration
- HS-Diffusion: Semantic-Mixing Diffusion for Head SwappingDiffusion models → Image generation, text-to-image and editing
- DiffStack: A Differentiable and Modular Control Stack for Autonomous VehiclesEnd-to-end autonomous driving → End-to-end system architecture
- Score-based Generative Modeling Secretly Minimizes the Wasserstein DistanceDiffusion models → Diffusion foundations and sampling
- Temporal Weights
- Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence
- HeartBEiT: Vision Transformer for Electrocardiogram Data Improves Diagnostic Performance at Low Sample Sizes
- AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs
- Attentive Deep Neural Networks for Legal Document Retrieval
- Neural Cloth Simulation
- The Challenges of HTR Model Training: Feedback from the Project Donner le gout de l'archive a l'ere numerique
- Benchmarking Large Language Models for Automated Verilog RTL Code Generation
- Visual Analytics for Early Detection of Retinal Diseases
- Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images
- Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences
- Smart Journey in Istanbul: A Mobile Application in Smart Cities for Traffic Estimation by Harnessing Time Series
- IMAGINE: An Integrated Model of Artificial Intelligence-Mediated Communication Effects
- Foresight -- Generative Pretrained Transformer (GPT) for Modelling of Patient Timelines using EHRs
- Multi-Agent Dynamic Pricing in a Blockchain Protocol Using Gaussian Bandits
- Adversarially Robust Video Perception by Seeing Motion
- Heuristically Guided Compilation for Multi-Agent Path Finding
- Paraphrase Identification with Deep Learning: A Review of Datasets and Methods
- Generating extreme quantum scattering in graphene with machine learning
- On the Relationship Between Explanation and Prediction: A Causal View
- Losses over Labels: Weakly Supervised Learning via Direct Loss Construction
- Enabling the Wireless Metaverse via Semantic Multiverse Communication
- Bridging Graph Position Encodings for Transformers with Weighted Graph-Walking Automata
- In-Season Crop Progress in Unsurveyed Regions using Networks Trained on Synthetic Data
- Interactive Learning with Pricing for Optimal and Stable Allocations in Markets
- Are metaheuristics worth it? A computational comparison between nature-inspired and deterministic techniques on black-box optimization problems
- Statistical Safety and Robustness Guarantees for Feedback Motion Planning of Unknown Underactuated Stochastic Systems
- Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
- MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
- Deep Image Style Transfer from Freeform Text
- LidarCLIP or: How I Learned to Talk to Point Clouds
- Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputs
- Deep Neural Networks integrating genomics and histopathological images for predicting stages and survival time-to-event in colon cancer
- 3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding
- Multi-Target Decision Making under Conditions of Severe Uncertainty
- Classification of Distraction Levels Using Hybrid Deep Neural Networks From EEG Signals
- An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty
- Look Before You Match: Instance Understanding Matters in Video Object Segmentation
- Explanations Can Reduce Overreliance on AI Systems During Decision-Making
- Adversarial Attacks and Defences for Skin Cancer Classification
- Structured 3D Features for Reconstructing Controllable Avatars
- RT-1: Robotics Transformer for Real-World Control at Scale
- Real-Time Artificial Intelligence Assistance for Safe Laparoscopic Cholecystectomy: Early-Stage Clinical Evaluation
- Can a face tell us anything about an NBA prospect? -- A Deep Learning approach
- Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
- A fine-grained comparison of pragmatic language understanding in humans and language models
- Diverse Demonstrations Improve In-context Compositional Generalization
- AutoPV: Automated photovoltaic forecasts with limited information using an ensemble of pre-trained models
- GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
- Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
- Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
- Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results
- Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures
- Connectivity-constrained Interactive Panoptic Segmentation
- Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen Estimator
- FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data
- ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
- POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification
- What do Vision Transformers Learn? A Visual Exploration
- Semantic Brain Decoding: from fMRI to conceptually similar image reconstruction of visual stimuli
- Exploring Consequences of Privacy Policies with Narrative Generation via Answer Set Programming
- A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps
- CNN-transformer mixed model for object detection
- Structured Prompting: Scaling In-Context Learning to 1,000 Examples
- On Text-based Personality Computing: Challenges and Future Directions
- TIER: Text-Image Entropy Regularization for CLIP-style models
- A Novel Approach For Generating Customizable Light Field Datasets for Machine Learning
- Quantum Clustering with k-Means: a Hybrid Approach
- Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation
- Quantum Policy Gradient Algorithm with Optimized Action Decoding
- The Hateful Memes Challenge Next Move
- Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?
- Boosting Semi-Supervised Learning with Contrastive Complementary Labeling
- AWT -- Clustering Meteorological Time Series Using an Aggregated Wavelet Tree
- Simplicity Bias Leads to Amplified Performance Disparities
- Categorical Tools for Natural Language Processing
- Aligning Visual and Lexical Semantics
- DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo
- Improving Accuracy Without Losing Interpretability: A ML Approach for Time Series Forecasting
- Category Theory for Quantum Natural Language Processing
- OAMixer: Object-aware Mixing Layer for Vision Transformers
- FastMIM: Expediting Masked Image Modeling Pre-training for Vision
- On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
- Prescriptive Process Monitoring in Intelligent Process Automation with Chatbot Orchestration
- Exploring Fake News Detection with Heterogeneous Social Media Context Graphs
- Proximal Policy Optimization Based Reinforcement Learning for Joint Bidding in Energy and Frequency Regulation Markets
- Body Segmentation Using Multi-task Learning
- Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Division
- Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning
- Leave Graphs Alone: Addressing Over-Squashing without Rewiring
- On Mini-Batch Training with Varying Length Time Series
- SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance
- Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemble
All 160
- Overview of The MediaEval 2022 Predicting Video Memorability Task
- AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images
- Solving Sample-Level Out-of-Distribution Detection on 3D Medical Images
- Accelerated structured matrix factorization
- Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
- FNDaaS: Content-agnostic Detection of Fake News sites
- Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning
- Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO
- Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
- Lisan: Yemeni, Iraqi, Libyan, and Sudanese Arabic Dialect Copora with Morphological Annotations
- Edge Computing for Semantic Communication Enabled Metaverse: An Incentive Mechanism Design
- A Statistical Model for Predicting Generalization in Few-Shot Classification
- Improving generalization in reinforcement learning through forked agents
- Object-fabrication Targeted Attack for Object Detection
- Can recurrent neural networks learn process model structure?
- Coarse-to-Fine Contrastive Learning on Graphs
- How Does Independence Help Generalization? Sample Complexity of ERM on Product Distributions
- Graph Convolutional Networks for Traffic Forecasting with Missing Values
- One-shot Machine Teaching: Cost Very Few Examples to Converge Faster
- CropCat: Data Augmentation for Smoothing the Feature Distribution of EEG Signals
- Balloon-to-Balloon AdHoc Wireless Network Connectivity: Google Project Loon
- Improving Depression estimation from facial videos with face alignment, training optimization and scheduling
- Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis
- TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
- PV3D: A 3D Generative Model for Portrait Video Generation
- Towards a general purpose machine translation system for Sranantongo
- Self-adaptive algorithms for quasiconvex programming and applications to machine learning
- Robust Split Federated Learning for U-shaped Medical Image Networks
- InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation
- Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
- Technical Report -- Competition Solution for Prompt Tuning using Pretrained Language Model
- Single Cell Training on Architecture Search for Image Denoising
- ALRt: An Active Learning Framework for Irregularly Sampled Temporal Data
- Numerical Stability of DeepGOPlus Inference
- Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems
- A Review of Off-Policy Evaluation in Reinforcement Learning
- Dilation-Erosion for Single-Frame Supervised Temporal Action Localization
- Reliable extrapolation of deep neural operators informed by physics or sparse observations
- The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition
- Foveated Thermal Computational Imaging in the Wild Using All-Silicon Meta-Optics
- DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization
- PPO-UE: Proximal Policy Optimization via Uncertainty-Aware Exploration
- Regularized Optimal Transport Layers for Generalized Global Pooling Operations
- Minimax Optimal Estimation of Stability Under Distribution Shift
- Mixed Supervision of Histopathology Improves Prostate Cancer Classification from MRI
- CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion
- Auto-labelling of Bug Report using Natural Language Processing
- DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
- Generative artificial intelligence-enabled dynamic detection of nicotine-related circuits
- Nonparametric Independent Component Analysis for the Sources with Mixed Spectra
- AFLGuard: Byzantine-robust Asynchronous Federated Learning
- Privacy-Preserving Collaborative Learning through Feature Extraction
- Linear Convergence of ISTA and FISTA
- Policy learning for many outcomes of interest: Combining optimal policy trees with multi-objective Bayesian optimisation
- Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators
- MAntRA: A framework for model agnostic reliability analysis
- Egocentric Video Task Translation
- Accidental Turntables: Learning 3D Pose by Watching Objects Turn
- Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map
- Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety