Papers
Tue 18 Apr 2023
177 papers
- Think Before You Act: Unified Policy for Interleaving Language Reasoning with ActionsLLM reasoning → Reinforcement learning for reasoning
- Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated EnvironmentsOffline RL and imitation learning from data → Offline RL algorithms
- Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin DynamicsOffline RL and imitation learning from data → Inverse reinforcement learning
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing SynthesizersDiffusion models → Audio, speech and music
- Deep Collective Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose TransferDiffusion models → 3D, point cloud and scene generation
- Two-stage Denoising Diffusion Model for Source Localization in Graph Inverse ProblemsDiffusion models → Flow matching, time series and science
- Align your Latents: High-Resolution Video Synthesis with Latent Diffusion ModelsDiffusion models → Video generation
- Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled DatasetsOffline RL and imitation learning from data → Robot manipulation imitation learning
- Comparative study on Judgment Text Classification for Transformer Based Models
- 3D Patient-specific Modelling and Characterisation of Muscle-Skeletal Districts
- Suspicious Vehicle Detection Using Licence Plate Detection And Facial Feature Recognition
- Human activity recognition using deep learning approaches and single frame cnn and convolutional lstm
- Creating Large Language Model Resistant Exams: Guidelines and Strategies
- AI Product Security: A Primer for Developers
- Multimodal contrastive learning for diagnosing cardiovascular diseases from electrocardiography (ECG) signals and patient metadata
- HeRo: RoBERTa and Longformer Hebrew Language Models
- CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models
- Towards Designing a ChatGPT Conversational Companion for Elderly People
- Safer Conversational AI as a Source of User Delight
- A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classification
- Amplifying Sine Unit: An Oscillatory Activation Function for Deep Neural Networks to Recover Nonlinear Oscillations Efficiently
- Contactless Human Activity Recognition using Deep Learning with Flexible and Scalable Software Define Radio
- Application of Tensor Neural Networks to Pricing Bermudan Swaptions
- Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation
- The Unintended Consequences of Censoring Digital Technology -- Evidence from Italy's ChatGPT Ban
- Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models
- BIM-GPT: a Prompt-Based Virtual Assistant Framework for BIM Information Retrieval
- Learning to Transmit with Provable Guarantees in Wireless Federated Learning
- Federated Alternate Training (FAT): Leveraging Unannotated Data Silos in Federated Segmentation for Medical Imaging
- Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets
- Multi-Modality Multi-Scale Cardiovascular Disease Subtypes Classification Using Raman Image and Medical History
- Deep Dynamic Cloud Lighting
- Data and Knowledge Co-driving for Cancer Subtype Classification on Multi-Scale Histopathological Slides
- The Adaptive τ-Lasso: Robustness and Oracle Properties
- Searching for ribbons with machine learning
- CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation
- Integrity and Junkiness Failure Handling for Embedding-based Retrieval: A Case Study in Social Network Search
- Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
- A Data Driven Sequential Learning Framework to Accelerate and Optimize Multi-Objective Manufacturing Decisions
- Towards a Neural Lambda Calculus: Neurosymbolic AI Applied to the Foundations of Functional Programming
- Coarse race data conceals disparities in clinical risk score performance
- Heterogeneous Integration of In-Memory Analog Computing Architectures with Tensor Processing Units
- FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging
- IMAC-Sim: A Circuit-level Simulator For In-Memory Analog Computing Architectures
- Early Detection of Parkinson's Disease using Motor Symptoms and Machine Learning
- Text-guided Image-and-Shape Editing and Generation: A Short Survey
- Evaluation of a Canonical Image Representation for Sidescan Sonar
- A Framework for Analyzing Cross-correlators using Price's Theorem and Piecewise-Linear Decomposition
- The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions
- Machine Learning Applications in Studying Mental Health Among Immigrants and Racial and Ethnic Minorities: A Systematic Review
- Quantum machine learning for image classification
- Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks
- Generative models improve fairness of medical classifiers under distribution shifts
- SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks
- Token Imbalance Adaptation for Radiology Report Generation
- A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies
- Large Language Models Based Automatic Synthesis of Software Specifications
- Hyperbolic Image-Text Representations
- Optimal PAC Bounds Without Uniform Convergence
- Structure Preserving Cycle-GAN for Unsupervised Medical Image Domain Adaptation
- Neural networks for geospatial data
- Sharp-SSL: Selective high-dimensional axis-aligned random projections for semi-supervised learning
- UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining
- SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More
- Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling
- Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task
- Detection and Classification of Glioblastoma Brain Tumor
- Variational Relational Point Completion Network for Robust 3D Classification
- Fast Neural Scene Flow
- CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection
- Participatory Design of AI with Children: Reflections on IDC Design Challenge
- Electrical Impedance Tomography with Deep Calder'on Method
- M-ENIAC: A machine learning recreation of the first successful numerical weather forecasts
- METAM: Goal-Oriented Data Discovery
- Performance of GAN-based augmentation for deep learning COVID-19 image classification
- LLM-based Interaction for Content Generation: A Case Study on the Perception of Employees in an IT department
- Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation
- Revisiting k-NN for Fine-tuning Pre-trained Language Models
- Bayes Hilbert Spaces for Posterior Approximation
- Decoding Neural Activity to Assess Individual Latent State in Ecologically Valid Contexts
- DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables
- CodeKGC: Code Language Model for Generative Knowledge Graph Construction
- Neural Lumped Parameter Differential Equations with Application in Friction-Stir Processing
- Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
- Look ATME: The Discriminator Mean Entropy Needs Attention
- PaTeCon: A Pattern-Based Temporal Constraint Mining Method for Conflict Detection on Knowledge Graphs
- GUILGET: GUI Layout GEneration with Transformer
- Causal Flow-based Variational Auto-Encoder for Disentangled Causal Representation Learning
- A Biomedical Entity Extraction Pipeline for Oncology Health Records in Portuguese
- Joint Age-based Client Selection and Resource Allocation for Communication-Efficient Federated Learning over NOMA Networks
- Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logistics
- Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
- D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings
- A Comparison of Image Denoising Methods
- Incremental Image Labeling via Iterative Refinement
- Robustness of Visual Explanations to Common Data Augmentation
- MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
- In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
- Visual-LiDAR Odometry and Mapping with Monocular Scale Correction and Visual Bootstrapping
All 177
- Neural Architecture Search for Visual Anomaly Segmentation
- Fibroglandular Tissue Segmentation in Breast MRI using Vision Transformers -- A multi-institutional evaluation
- SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes
- Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMs
- PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering
- Generative modeling of living cells with SO(3)-equivariant implicit neural representations
- PG-VTON: A Novel Image-Based Virtual Try-On Method via Progressive Inference Paradigm
- From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation
- Audio-Driven Talking Face Generation with Diverse yet Realistic Facial Animations
- Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning
- POCE: Pose-Controllable Expression Editing
- Enhancing Textbooks with Visuals from the Web for Improved Learning
- SDFReg: Learning Signed Distance Functions for Point Cloud Registration
- ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
- Understand Data Preprocessing for Effective End-to-End Training of Deep Neural Networks
- Quantum Annealing for Single Image Super-Resolution
- Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
- Differentiable Genetic Programming for High-dimensional Symbolic Regression
- A Study of Neural Collapse Phenomenon: Grassmannian Frame, Symmetry and Generalization
- Computational and Exploratory Landscape Analysis of the GKLS Generator
- Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation
- Event Camera and LiDAR based Human Tracking for Adverse Lighting Conditions in Subterranean Environments
- An adaptive safety layer with hard constraints for safe reinforcement learning in multi-energy management systems
- Autonomous Systems: Autonomous Systems: Indoor Drone Navigation
- Tailoring Domain Adaptation for Machine Translation Quality Estimation
- Parameterized Neural Networks for Finance
- Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks
- NPS: A Framework for Accurate Program Sampling Using Graph Neural Network
- Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
- Romanization-based Large-scale Adaptation of Multilingual Language Models
- Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
- Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study
- Unveiling and unraveling aggregation and dispersion fallacies in group MCDM
- A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift
- Saliency-aware Stereoscopic Video Retargeting
- BadVFL: Backdoor Attacks in Vertical Federated Learning
- Feasible Policy Iteration for Safe Reinforcement Learning
- UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite
- GoferBot: A Visual Guided Human-Robot Collaborative Assembly System
- Sensor Fault Detection and Isolation in Autonomous Nonlinear Systems Using Neural Network-Based Observers
- Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation
- Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese
- TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models
- Motion-state Alignment for Video Semantic Segmentation
- Towards the Transferable Audio Adversarial Attack via Ensemble Methods
- SViTT: Temporal Learning of Sparse Video-Text Transformers
- Revisiting the Role of Similarity and Dissimilarity in Best Counter Argument Retrieval
- Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping
- AI Reliance and Decision Quality: Fundamentals, Interdependence, and the Effects of Interventions
- MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition
- Speaker Profiling in Multiparty Conversations
- Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization
- Large-scale Dynamic Network Representation via Tensor Ring Decomposition
- Deep Unrestricted Document Image Rectification
- A Systematic Literature Review of User Trust in AI-Enabled Systems: An HCI Perspective
- 3-Objective Pareto Optimization for Problems with Chance Constraints
- Cooperative Multi-Agent Reinforcement Learning for Inventory Management
- Masked Language Model Based Textual Adversarial Example Detection
- A Survey for Biomedical Text Summarization: From Pre-trained to Large Language Models
- Exoskeleton for the Mind: Exploring Strategies Against Misinformation with a Metacognitive Agent
- NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination
- AutoTaskFormer: Searching Vision Transformers for Multi-task Learning
- W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting
- Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints
- Estimating Joint Probability Distribution With Low-Rank Tensor Decomposition, Radon Transforms and Dictionaries
- Addressing Variable Dependency in GNN-based SAT Solving
- Human and AI Perceptual Differences in Image Classification Errors
- EfficientNet Algorithm for Classification of Different Types of Cancer
- Impossibility of Characterizing Distribution Learning -- a simple solution to a long-standing problem
- You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
- Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
- Learning Sim-to-Real Dense Object Descriptors for Robotic Manipulation
- LTC-SE: Expanding the Potential of Liquid Time-Constant Neural Networks for Scalable AI and Embedded Systems
- GlobalMind: Global Multi-head Interactive Self-attention Network for Hyperspectral Change Detection
- Learning Situation Hyper-Graphs for Video Question Answering
- Semi-supervised Learning of Pushforwards For Domain Translation & Adaptation
- An end-to-end, interactive Deep Learning based Annotation system for cursive and print English handwritten text