Papers
Fri 7 Apr 2023
138 papers
- Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
- Why think step by step? Reasoning emerges from the locality of experienceLLM reasoning → Prompting and chain-of-thought reasoning
- Learning Robot Manipulation from Cross-Morphology DemonstrationOffline RL and imitation learning from data → Robot manipulation imitation learning
- ChiroDiff: Modelling chirographic data with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Zero-shot CT Field-of-view Completion with Unconditional Generative Diffusion PriorDiffusion models → Medical imaging and segmentation
- Probing Conceptual Understanding of Large Visual-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Generative Agents: Interactive Simulacra of Human BehaviorWorld models → World models for language agents +1
- Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4LLM reasoning → Reasoning benchmarks and evaluation
- Large-scale Online Ridesharing: The Effect of Assignment Optimality on System Performance
- Automated Solubility Analysis System and Method Using Computer Vision and Machine Learning
- Profiling the news spreading barriers using news headlines
- Halcyon -- A Pathology Imaging and Feature analysis and Management System
- Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems
- Comments on 'Fast and scalable search of whole-slide images via self-supervised deep learning'
- BS-GAT Behavior Similarity Based Graph Attention Network for Network Intrusion Detection
- Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey
- UAV Obstacle Avoidance by Human-in-the-Loop Reinforcement in Arbitrary 3D Environment
- Data-Driven Response Regime Exploration and Identification for Dynamical Systems
- SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning
- Similarity search in the blink of an eye with compressed indices
- Expectations over Unspoken Alternatives Predict Pragmatic Inferences
- A new perspective on building efficient and expressive 3D equivariant graph neural networks
- Event-based Camera Tracker by nablat NeRF
- Attention: Marginal Probability is All You Need?
- Neural Diffeomorphic Non-uniform B-spline Flows
- ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
- Masked Student Dataset of Expressions
- Conservative objective models are a special kind of contrastive divergence-based energy model
- SGDP: A Stream-Graph Neural Network Based Data Prefetcher
- Revisiting Deep Learning for Variable Type Recovery
- StepMix: A Python Package for Pseudo-Likelihood Estimation of Generalized Mixture Models with External Variables
- Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images
- Improving Identity-Robustness for Face Models
- WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
- Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions
- High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection
- Privacy-Preserving CNN Training with Transfer Learning: Multiclass Logistic Regression
- Correcting Model Misspecification via Generative Adversarial Networks
- Bridging Nations: Quantifying the Role of Multilinguals in Communication on Social Media
- Generative AI for learning: Investigating the potential of synthetic learning videos
- AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks
- A roadmap to fair and trustworthy prediction model validation in healthcare
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens
- Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following
- Test your samples jointly: Pseudo-reference for image quality evaluation
- Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting
- Replicability and stability in learning
- Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
- V3Det: Vast Vocabulary Visual Detection Dataset
- Perspectives on AI Architectures and Co-design for Earth System Predictability
- Assessing Perceived Fairness from Machine Learning Developer's Perspective
- Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models
- Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing
- Full Gradient Deep Reinforcement Learning for Average-Reward Criterion
- Interpretable Unified Language Checking
- Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data
- Representer Theorems for Metric and Preference Learning: Geometric Insights and Algorithms
- Integrating Edge-AI in Structural Health Monitoring domain
- On the Importance of Contrastive Loss in Multimodal Learning
- Meta-causal Learning for Single Domain Generalization
- Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge
- Deepfake Detection with Deep Learning: Convolutional Neural Networks versus Transformers
- MOPA: Modular Object Navigation with PointGoal Agents
- Model-Agnostic Gender Debiased Image Captioning
- Feature Mining for Encrypted Malicious Traffic Detection with Deep Learning and Other Machine Learning Algorithms
- EPINN-NSE: Enhanced Physics-Informed Neural Networks for Solving Navier-Stokes Equations
- BenCoref: A Multi-Domain Dataset of Nominal Phrases and Pronominal Reference Annotations
- Machine Learning with Requirements: a Manifesto
- Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
- Contraction-Guided Adaptive Partitioning for Reachability Analysis of Neural Network Controlled Systems
- DATE: Domain Adaptive Product Seeker for E-commerce
- A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation
- Fairness through Aleatoric Uncertainty
- A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints
- FedDiSC: A Computation-efficient Federated Learning Framework for Power Systems Disturbance and Cyber Attack Discrimination
- Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks
- Compressed Regression over Adaptive Networks
- A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
- Asynchronous Federated Continual Learning
- RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking
- What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory
- Look how they have grown: Non-destructive Leaf Detection and Size Estimation of Tomato Plants for 3D Growth Monitoring
- Revisiting Automated Prompting: Are We Actually Doing Better?
- ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation
- Pallet Detection from Synthetic Data Using Game Engines
- Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots
- Graphon Estimation in bipartite graphs with observable edge labels and unobservable node labels
- On Efficient Training of Large-Scale Deep Learning Models: A Literature Review
- Anomalous Sound Detection using Audio Representation with Machine ID based Contrastive Learning Pretraining
- ArmanTTS single-speaker Persian dataset
- Language-aware Multiple Datasets Detection Pretraining for DETRs
- Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational model
- β-Variational autoencoders and transformers for reduced-order modelling of fluid flows
- DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium
- Construction of unbiased dental template and parametric dental model for precision digital dentistry
- A physics-informed neural network framework for modeling obstacle-related equations
- Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
- GEMINI: Controlling the Sentence-level Writing Style for Abstractive Text Summarization
- AI Model Disgorgement: Methods and Choices
- InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
All 138
- HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular Datasets
- Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
- ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions
- Adjustable Privacy using Autoencoder-based Learning Structure
- Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images
- Leveraging GANs for data scarcity of COVID-19: Beyond the hype
- CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning
- Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction
- From Retrieval to Generation: Efficient and Effective Entity Set Expansion
- Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
- SSS at SemEval-2023 Task 10: Explainable Detection of Online Sexism using Majority Voted Fine-Tuned Transformers
- Hierarchical Catalogue Generation for Literature Review: A Benchmark
- Carrot Cure: A CNN based Application to Detect Carrot Disease
- Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study
- Local Rose Breeds Detection System Using Transfer Learning Techniques
- Distributional Signals for Node Classification in Graph Neural Networks
- F-RDW: Redirected Walking with Forecasting Future Position
- Architecture-Preserving Provable Repair of Deep Neural Networks
- Devil's on the Edges: Selective Quad Attention for Scene Graph Generation
- UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
- ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes
- ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels
- Can we learn better with hard samples?
- RED-PSM: Regularization by Denoising of Factorized Low Rank Models for Dynamic Imaging
- PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
- Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
- Linking Representations with Multimodal Contrastive Learning
- A Policy for Early Sequence Classification
- Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning
- Graph Enabled Cross-Domain Knowledge Transfer
- Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones
- Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts
- Towards Unified Scene Text Spotting based on Sequence Generation
- Domain Generalization In Robust Invariant Representation
- TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors
- Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts
- A modular framework for stabilizing deep reinforcement learning control
- Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder