Papers
Thu 13 Jul 2023
173 papers
- Robotic Manipulation Datasets for Offline Compositional Reinforcement LearningOffline RL and imitation learning from data → Real-world robot offline RL
- Bootstrapping Vision-Language Learning with Decoupled Language Pre-trainingSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
- Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward ImprovementDiffusion models → Diffusion and flow policies for robotics
- Retrieval Augmented Generation using Engineering Design KnowledgeRetrieval-augmented generation → RAG pipeline design and evaluation
- Neuro-symbolic Empowered Denoising Diffusion Probabilistic Models for Real-time Anomaly Detection in Industry 4.0Diffusion models → Flow matching, time series and science
- In-context Autoencoder for Context Compression in a Large Language ModelEfficient LLM inference and serving → Prompt and context compression
- mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
- PC-Droid: Faster diffusion and improved quality for particle cloud generationDiffusion models → Flow matching, time series and science
- Leveraging Vision-Language Foundation Models for Fine-Grained Downstream TasksMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Privacy-Utility Trade-offs in Neural Networks for Medical Population Graphs: Insights from Differential Privacy and Graph StructureLLM safety and security → Membership inference attacks
- DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous VehicleEnd-to-end autonomous driving → End-to-end system architecture
- On the Effective Horizon of Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Improving Nonalcoholic Fatty Liver Disease Classification Performance With Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Body Fat Estimation from Surface Meshes using Graph Neural Networks
- EFL Students' Attitudes and Contradictions in a Machine-in-the-loop Activity System
- ChatGPT and Bard Responses to Polarizing Questions
- Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows
- Student Assessment in Cybersecurity Training Automated by Pattern Mining and Clustering
- Combining Vision and EMG-Based Hand Tracking for Extended Reality Musical Instruments
- Extended Graph Assessment Metrics for Graph Neural Networks
- Multi-view self-supervised learning for multivariate variable-channel time series
- Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing
- Sequential Monte Carlo Learning for Time Series Structure Discovery
- DenseMP: Unsupervised Dense Pre-training for Few-shot Medical Image Segmentation
- Guided Linear Upsampling
- Causal Influences over Social Learning Networks
- Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis
- Towards Ordinal Data Science
- Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
- Adapting an ASR Foundation Model for Spoken Language Assessment
- Learning to Select and Rank from Choice-Based Feedback: A Simple Nested Approach
- Unsupervised Learning of Distributional Properties can Supplement Human Labeling and Increase Active Learning Efficiency in Anomaly Detection
- National Origin Discrimination in Deep-learning-powered Automated Resume Screening
- CaRT: Certified Safety and Robust Tracking in Learning-based Motion Planning for Multi-Agent Systems
- Corticomorphic Hybrid CNN-SNN Architecture for EEG-based Low-footprint Low-latency Auditory Attention Detection
- Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise
- Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints
- PatchSorter: A High Throughput Deep Learning Digital Pathology Tool for Object Labeling
- Deep reinforcement learning for the dynamic vehicle dispatching problem: An event-based approach
- Real-time Percussive Technique Recognition and Embedding Learning for the Acoustic Guitar
- AutoHint: Automatic Prompt Optimization with Hint Generation
- Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks
- MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction
- Choice Models and Permutation Invariance: Demand Estimation in Differentiated Products Markets
- Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyond
- Probabilistic Constrained Reinforcement Learning with Formal Interpretability
- A Scenario-Based Functional Testing Approach to Improving DNN Performance
- Kernel t-distributed stochastic neighbor embedding
- An Analysis of Dialogue Repair in Virtual Voice Assistants
- Rician likelihood loss for quantitative MRI using self-supervised deep learning
- Can Blockchains Reliably Train Machine Learning Models?
- Controllable Emphasis with zero data for text-to-speech
- Vertex-based Networks to Accelerate Path Planning Algorithms
- Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling
- Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section
- MegaWika: Millions of reports and their sources across 50 diverse languages
- Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
- A metric learning approach for endoscopic kidney stone identification
- AnyStar: Domain randomized universal star-convex 3D instance segmentation
- GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer
- Bridging the Gap: Heterogeneous Face Recognition with Conditional Adaptive Instance Modulation
- Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima
- Data Augmentation for Machine Translation via Dependency Subtree Swapping
- Leveraging Factored Action Spaces for Off-Policy Evaluation
- Impact of Free-carrier Nonlinearities on Silicon Microring-based Reservoir Computing
- Electoral Agitation Data Set: The Use Case of the Polish Election
- Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks
- Data Augmentation for Mathematical Objects
- IR Design for Application-Specific Natural Language: A Case Study on Traffic Data
- Revisiting the DARPA Communicator Data using Conversation Analysis
- Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models
- A decision framework for selecting information-transfer strategies in population-based SHM
- Short Boolean Formulas as Explanations in Practice
- Machine Learning-Assisted Pattern Recognition Algorithms for Estimating Ultimate Tensile Strength in Fused Deposition Modeled Polylactic Acid Specimens
- Layer-wise Linear Mode Connectivity
- Is Task-Agnostic Explainable AI a Myth?
- Copy Is All You Need
- HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models
- Self-regulating Prompts: Foundational Model Adaptation without Forgetting
- Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
- On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
- Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
- Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
- DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding
- LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT
- Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
- Uncovering Unique Concept Vectors through Latent Space Decomposition
- Generating Benchmarks for Factuality Evaluation of Language Models
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
- Min-Max Optimization under Delays
- The complexity of non-stationary reinforcement learning
- Identifying Early Help Referrals For Local Authorities With Machine Learning And Bias Analysis
- Embodied Lifelong Learning for Task and Motion Planning
- DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering
- Effective Prompt Extraction from Language Models
- LVLane: Deep Learning for Lane Detection and Classification in Challenging Conditions
- Self-Supervised Learning for Interactive Perception of Surgical Thread for Autonomous Suture Tail-Shortening
- Personalization for BERT-based Discriminative Speech Recognition Rescoring
- A Novel Bayes' Theorem for Upper Probabilities
All 173
- A Causal Framework to Unify Common Domain Generalization Approaches
- TinyMetaFed: Efficient Federated Meta-Learning for TinyML
- Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics
- Negated Complementary Commonsense using Large Language Models
- Robotic surface exploration with vision and tactile sensing for cracks detection and characterisation
- Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks
- Layered controller synthesis for dynamic multi-agent systems
- Cramer Type Distances for Learning Gaussian Mixture Models by Gradient Descent
- Watch Where You Head: A View-biased Domain Gap in Gait Recognition and Unsupervised Adaptation
- Vehicle Dispatching and Routing of On-Demand Intercity Ride-Pooling Services: A Multi-Agent Hierarchical Reinforcement Learning Approach
- Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data
- MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting
- Multimodal Object Detection in Remote Sensing
- Breaking 3-Factor Approximation for Correlation Clustering in Polylogarithmic Rounds
- Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative
- Weakly supervised marine animal detection from remote sensing images using vector-quantized variational autoencoder
- Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models
- GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators
- To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?
- Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues
- S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
- Parmesan: mathematical concept extraction for education
- IntelliGraphs: Datasets for Benchmarking Knowledge Graph Generation
- Ageing Analysis of Embedded SRAM on a Large-Scale Testbed Using Machine Learning
- YOLIC: An Efficient Method for Object Localization and Classification on Edge Devices
- Aeolus Ocean -- A simulation environment for the autonomous COLREG-compliant navigation of Unmanned Surface Vehicles using Deep Reinforcement Learning and Maritime Object Detection
- Towards Ubiquitous Semantic Metaverse: Challenges, Approaches, and Opportunities
- Explainable Artificial Intelligence driven mask design for self-supervised seismic denoising
- DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification
- Transformer-based end-to-end classification of variable-length volumetric data
- A Comprehensive Analysis of Blockchain Applications for Securing Computer Vision Systems
- Multivariate Time Series characterization and forecasting of VoIP traffic in real mobile networks
- An Improved Uniform Convergence Bound with Fat-Shattering Dimension
- Data-Scarce Identification of Game Dynamics via Sum-of-Squares Optimization
- Frameless Graph Knowledge Distillation
- Image Transformation Sequence Retrieval with General Reinforcement Learning
- Automated Deception Detection from Videos: Using End-to-End Learning Based High-Level Features and Classification Approaches
- Quantum Autoencoders for Learning Quantum Channel Codes
- Online Distributed Learning with Quantized Finite-Time Coordination
- Learning IMM Filter Parameters from Measurements using Gradient Descent
- SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
- NLOS Dies Twice: Challenges and Solutions of V2X for Cooperative Perception
- Interpretable 2D Vision Models for 3D Medical Images
- MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
- Image Denoising and the Generative Accumulation of Photons
- Deep Neural Networks for Semiparametric Frailty Models via H-likelihood
- RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
- Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
- A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
- Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
- Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification
- Prescriptive Process Monitoring Under Resource Constraints: A Reinforcement Learning Approach
- Metal Oxide-based Gas Sensor Array for the VOCs Analysis in Complex Mixtures using Machine Learning
- Deep Network Approximation: Beyond ReLU to Diverse Activation Functions
- Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations
- Full-resolution Lung Nodule Segmentation from Chest X-ray Images using Residual Encoder-Decoder Networks
- Quantum Image Denoising: A Framework via Boltzmann Machines, QUBO, and Quantum Annealing
- Convolutional Neural Networks for Sentiment Analysis on Weibo Data: A Natural Language Processing Approach
- Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
- DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection
- Domain-adaptive Person Re-identification without Cross-camera Paired Samples
- Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study
- Optimised Least Squares Approach for Accurate Polygon and Ellipse Fitting
- Free-Form Composition Networks for Egocentric Action Recognition
- AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion
- Agreement Tracking for Multi-Issue Negotiation Dialogues
- Artificial Intelligence for Drug Discovery: Are We There Yet?
- Machine Learning practices and infrastructures
- Leveraging Contextual Counterfactuals Toward Belief Calibration
- WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces
- Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning
- On the ability of CNNs to extract color invariant intensity based features for image classification
- Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems