Papers
Wed 12 Jul 2023
171 papers
- Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research DirectionsEnd-to-end autonomous driving → End-to-end system architecture
- Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug EventsKnowledge distillation → Knowledge distillation for LLMs
- Budgeting Counterfactual for Offline RLOffline RL and imitation learning from data → Offline RL algorithms
- MMBench: Is Your Multi-modal Model an All-around Player?LLM reasoning → Multimodal reasoning +1
- Exposing the Fake: Effective Diffusion-Generated Images DetectionDiffusion models → Image generation, text-to-image and editing
- Diffusion Models for Multi-target Adversarial TrackingDiffusion models → Diffusion and flow policies for robotics
- Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location ReasoningLLM reasoning → Spatial and embodied reasoning +1
- SoK: Comparing Different Membership Inference Attacks with a Comprehensive BenchmarkLLM safety and security → Membership inference attacks
- VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street ViewLLM agents and tool use → Multimodal and embodied agents
- Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
- Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech RecognitionMixture-of-experts → Multimodal MoE models
- Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
- DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled RepresentationDiffusion models → Diffusion foundations and sampling
- Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning
- Detecting the Presence of COVID-19 Vaccination Hesitancy from South African Twitter Data Using Machine Learning
- Pathway: a fast and flexible unified stream data processing framework for analytical and Machine Learning applications
- Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
- Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering
- SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology
- SSVEP-Based BCI Wheelchair Control System
- Enhancing ECG Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification
- SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
- Embracing the chaos: analysis and diagnosis of numerical instability in variational flows
- ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
- FDAPT: Federated Domain-adaptive Pre-training for Language Models
- Data Augmentation in Training CNNs: Injecting Noise to Images
- CLAIMED -- the open source framework for building coarse-grained operators for accelerated discovery in science
- Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
- Misclassification in Automated Content Analysis Causes Bias in Regression. Can We Fix It? Yes We Can!
- Early Autism Diagnosis based on Path Signature and Siamese Unsupervised Feature Compressor
- Assessing the Ability of ChatGPT to Screen Articles for Systematic Reviews
- Efficiently-Verifiable Strong Uniquely Solvable Puzzles and Matrix Multiplication
- Discovering Image Usage Online: A Case Study With "Flatten the Curve''
- Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective
- Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms
- Efficient Convolution and Transformer-Based Network for Video Frame Interpolation
- On Collaboration in Distributed Parameter Estimation with Resource Constraints
- No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
- A Comprehensive Overview of Large Language Models
- Improved selective background Monte Carlo simulation at Belle II with graph attention networks and weighted events
- Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
- Robust scalable initialization for Bayesian variational inference with multi-modal Laplace approximations
- Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
- RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation
- The Acquisition of Semantic Relationships between words
- Testing Sparsity Assumptions in Bayesian Networks
- Designing Behavior Trees from Goal-Oriented LTLf Formulas
- Trainability, Expressivity and Interpretability in Gated Neural ODEs
- Temporal Label-Refinement for Weakly-Supervised Audio-Visual Event Localization
- Rethinking Answer Set Programming Templates
- Personalized Anomaly Detection in PPG Data using Representation Learning and Biometric Identification
- Spectral-Bias and Kernel-Task Alignment in Physically Informed Neural Networks
- T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation
- The Whole Pathological Slide Classification via Weakly Supervised Learning
- Sequential Experimental Design for X-Ray CT Using Deep Reinforcement Learning
- ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression
- Assessment of the suitability of degradation models for the planning of CCTV inspections of sewer pipes
- Denoising Simulated Low-Field MRI (70mT) using Denoising Autoencoders (DAE) and Cycle-Consistent Generative Adversarial Networks (Cycle-GAN)
- Neural Free-Viewpoint Relighting for Glossy Indirect Illumination
- Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
- Provably Faster Gradient Descent via Long Steps
- Deep Learning of Crystalline Defects from TEM images: A Solution for the Problem of "Never Enough Training Data"
- Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
- Facial Reenactment Through a Personalized Generator
- Locally Adaptive Federated Learning
- Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
- Towards a Certified Proof Checker for Deep Neural Network Verification
- Improved Real-time Image Smoothing with Weak Structures Preserved and High-contrast Details Removed
- Instruction Mining: Instruction Data Selection for Tuning Large Language Models
- Rational Neural Network Controllers
- Tackling Computational Heterogeneity in FL: A Few Theoretical Insights
- Stochastic Light Field Holography
- Physics-informed Machine Learning for Calibrating Macroscopic Traffic Flow Models
- On the hierarchical Bayesian modelling of frequency response functions
- UGCANet: A Unified Global Context-Aware Transformer-based Network with Feature Alignment for Endoscopic Image Analysis
- Machine learning and Topological data analysis identify unique features of human papillae in 3D scans
- Identifiability Guarantees for Causal Disentanglement from Soft Interventions
- Reconstructing Spatiotemporal Data with C-VAEs
- DSSE: a drone swarm search environment
- Multimodal Molecular Pretraining via Modality Blending
- On the Importance of Denoising when Learning to Compress Images
- Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches
- Testing different Log Bases For Vector Model Weighting Technique
- Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging
- SepVAE: a contrastive VAE to separate pathological patterns from healthy ones
- Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems
- CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
- Large Class Separation is not what you need for Relational Reasoning-based OOD Detection
- Smart Infrastructure: A Research Junction
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
- Auxiliary-Tasks Learning for Physics-Informed Neural Network-Based Partial Differential Equations Solving
- The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset
- Deep Generative Models for Physiological Signals: A Systematic Literature Review
- Reflective Hybrid Intelligence for Meaningful Human Control in Decision-Support Systems
- Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions
- NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services
- Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression
- SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
- Guided Bottom-Up Interactive Constraint Acquisition
- Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation
All 171
- Enhancing Portuguese Sign Language Animation with Dynamic Timing and Mouthing
- Recognizing student identification numbers from the matrix templates using a modified U-net architecture
- TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image
- Deep learning for dynamic graphs: models and benchmarks
- RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation
- Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks
- Online Laplace Model Selection Revisited
- Quantitative CLTs in Deep Neural Networks
- AICT: An Adaptive Image Compression Transformer
- Operational Support Estimator Networks
- Interpreting deep embeddings for disease progression clustering
- Function-Space Regularization for Deep Bayesian Classification
- Visualization for Multivariate Gaussian Anomaly Detection in Images
- A Study on the Appropriate size of the Mongolian general corpus
- Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
- A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
- Rhythm Modeling for Voice Conversion
- Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images
- AI-Generated Imagery: A New Era for the `Readymade'
- Pluggable Neural Machine Translation Models via Memory-augmented Adapters
- Learning from Exemplary Explanations
- balance -- a Python package for balancing biased data samples
- PolyLM: An Open Source Polyglot Large Language Model
- An Effective and Efficient Time-aware Entity Alignment Framework via Two-aspect Three-view Label Propagation
- What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation
- DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification
- Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera
- Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
- Digital tools in occupational health, brakes or levers for building multidisciplinary dynamics?
- A Comprehensive Review of Automated Data Annotation Techniques in Human Activity Recognition
- Transformers in Reinforcement Learning: A Survey
- Outlier detection in regression: conic quadratic formulations
- Contrastive Learning for Conversion Rate Prediction
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models
- GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation
- Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations
- Newell's theory based feature transformations for spatio-temporal traffic prediction
- Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
- A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models
- YOGA: Deep Object Detection in the Wild with Lightweight Feature Learning and Multiscale Attention
- Prototypical Contrastive Transfer Learning for Multimodal Language Understanding
- Automatically Reconciling the Trade-off between Prediction Accuracy and Earliness in Prescriptive Business Process Monitoring
- Sem-CS: Semantic CLIPStyler for Text-Based Image Style Transfer
- BiRP: Learning Robot Generalized Bimanual Coordination using Relative Parameterization Method on Human Demonstration
- A New Dataset and Comparative Study for Aphid Cluster Detection
- Filling time-series gaps using image techniques: Multidimensional context autoencoder approach for building energy data imputation
- Reading Radiology Imaging Like The Radiologist
- Unified Medical Image-Text-Label Contrastive Learning With Continuous Prompt
- SwiFT: Swin 4D fMRI Transformer
- FIS-ONE: Floor Identification System with One Label for Crowdsourced RF Signals
- Close-up View synthesis by Interpolating Optical Flow
- Grain and Grain Boundary Segmentation using Machine Learning with Real and Generated Datasets
- Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding
- Mini-Batch Optimization of Contrastive Loss
- Stability Guarantees for Feature Attributions with Multiplicative Smoothing
- Single Domain Generalization via Normalised Cross-correlation Based Convolutions
- Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
- Deep learning-based estimation of whole-body kinematics from multi-view images
- Deep Unrolling for Nonconvex Robust Principal Component Analysis
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views
- PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks
- FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
- Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation
- Efficient Task Offloading Algorithm for Digital Twin in Edge/Cloud Computing Environment
- tdCoxSNN: Time-Dependent Cox Survival Neural Network for Continuous-time Dynamic Prediction
- Multi-Object Tracking as Attention Mechanism
- OG: Equip vision occupancy with instance segmentation and visual grounding
- Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes
- FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems
- GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video