Papers
Mon 24 Apr 2023
195 papers
- Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion ModelLLM reasoning → Audio-language model reasoning +1
- TextMesh: Generation of Realistic 3D Meshes From Text PromptsDiffusion models → 3D, point cloud and scene generation
- Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Customized Load Profiles Synthesis for Electricity Customers Based on Conditional Diffusion ModelsDiffusion models → Flow matching, time series and science
- Improving Knowledge Distillation via Transferring Learning AbilityKnowledge distillation → General knowledge distillation methods
- Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- Function-Consistent Feature DistillationKnowledge distillation → General knowledge distillation methods
- Hierarchical Diffusion Autoencoders and Disentangled Image ManipulationDiffusion models → Diffusion foundations and sampling
- Your Identity is Your Behavior -- Continuous User Authentication based on Machine Learning and Touch Dynamics
- Context-enriched molecule representations improve few-shot drug discovery
- Time delay multi-feature correlation analysis to extract subtle dependencies from EEG signals
- Accurate Surface and Finite Temperature Bulk Properties of Lithium Metal at Large Scales using Machine Learning Interaction Potentials
- Adversarial Generative NMF for Single Channel Source Separation
- Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction
- Restoring Original Signal From Pile-up Signal using Deep Learning
- AI, write an essay for me: A large-scale comparison of human-written versus ChatGPT-generated essays
- Quantum Machine Learning Approach for the Prediction of Surface Roughness in Additive Manufactured Specimens
- ChatLLM Network: More brains, More intelligence
- Neural Implicit Shape Editing using Boundary Sensitivity
- Generating robust counterfactual explanations
- Topological properties and organizing principles of semantic networks
- Evolving Three Dimension (3D) Abstract Art: Fitting Concepts by Language
- AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design Anywhere
- Constraining Chaos: Enforcing dynamical invariants in the training of recurrent neural networks
- Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification
- Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection
- Evaluating Adversarial Robustness on Document Image Classification
- DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents
- Towards Realistic Generative 3D Face Models
- AGI: Artificial General Intelligence for Education
- On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
- Design optimization for high-performance computing using FPGA
- Vision-based Estimation of Fatigue and Engagement in Cognitive Training Sessions
- Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
- Robust, randomized preconditioning for kernel ridge regression
- A Study on Improving Realism of Synthetic Data for Machine Learning
- TensoIR: Tensorial Inverse Rendering
- Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout
- Unsupervised Style-based Explicit 3D Face Reconstruction from Single Image
- Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning
- Predicting Pulmonary Hypertension by Electrocardiograms Using Machine Learning
- Understanding and Predicting Human Label Variation in Natural Language Inference through Explanation
- Stochastic MPC for energy hubs using data driven demand forecasting
- Sparse Private LASSO Logistic Regression
- TIGTEC : Token Importance Guided TExt Counterfactuals
- Immunohistochemistry Biomarkers-Guided Image Search for Histopathology
- Composite Biomarker Image for Advanced Visualization in Histopathology
- Multi-Source to Multi-Target Decentralized Federated Domain Adaptation
- Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hulls
- End-to-End Lidar-Camera Self-Calibration for Autonomous Vehicles
- PEFT-Ref: A Modular Reference Architecture and Typology for Parameter-Efficient Finetuning Techniques
- AutoFocusFormer: Image Segmentation off the Grid
- Synthesizing Stable Reduced-Order Visuomotor Policies for Nonlinear Systems via Sums-of-Squares Optimization
- Semantic Tokenizer for Enhanced Natural Language Processing
- HDCC: A Hyperdimensional Computing compiler for classification on embedded systems and high-performance computing
- On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research
- Extreme Classification for Answer Type Prediction in Question Answering
- Pointersect: Neural Rendering with Cloud-Ray Intersection
- Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction
- Better Question-Answering Models on a Budget
- Analyzing categorical time series with the R package ctsfeatures
- USTEP: Structuration des logs en flux grace `a un arbre de recherche 'evolutif
- Parallel bootstrap-based on-policy deep reinforcement learning for continuous flow control applications
- Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]
- Virus2Vec: Viral Sequence Classification Using Machine Learning
- Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis
- Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection
- Distilling from Similar Tasks for Transfer Learning on a Budget
- ExCalibR: Expected Calibration of Recommendations
- Fully Sparse Fusion for 3D Object Detection
- Segment Anything in 3D with Radiance Fields
- Segment Anything in Medical Images
- A Survey on Multi-Resident Activity Recognition in Smart Environments
- AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
- Large-capacity and Flexible Video Steganography via Invertible Neural Network
- Explicit Correspondence Matching for Generalizable Neural Radiance Fields
- Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
- Synthpop++: A Hybrid Framework for Generating A Country-scale Synthetic Population
- HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video
- Stubborn: An Environment for Evaluating Stubbornness between Agents with Aligned Incentives
- AMR Parsing with Instruction Fine-tuned Pre-trained Language Models
- Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study
- Ordinal time series analysis with the R package otsfeatures
- Fuzzy clustering of ordinal time series based on two novel distances with economic applications
- WizardLM: Empowering large pre-trained language models to follow complex instructions
- Uni-QSAR: an Auto-ML Tool for Molecular Property Prediction
- Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation
- An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning
- Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network
- Topology-Aware Focal Loss for 3D Image Segmentation
- Impact-Oriented Contextual Scholar Profiling using Self-Citation Graphs
- More Communication Does Not Result in Smaller Generalization Error in Federated Learning
- A Cookbook of Self-Supervised Learning
- PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale
- Synthetic Datasets for Autonomous Driving: A Survey
- Pi-ML: A dimensional analysis-based machine learning parameterization of optical turbulence in the atmospheric surface layer
- USA-Net: Unified Semantic and Affordance Representations for Robot Memory
- Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection
- End-to-End Spatio-Temporal Action Localisation with Video Transformers
- Explainable AI Insights for Symbolic Computation: A case study on selecting the variable ordering for cylindrical algebraic decomposition
All 195
- Efficient Halftoning via Deep Reinforcement Learning
- Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning
- Exploring shared memory architectures for end-to-end gigapixel deep learning
- Combining Monte Carlo Tree Search and Heuristic Search for Weighted Vertex Coloring
- Reconstructing Turbulent Flows Using Physics-Aware Spatio-Temporal Dynamics and Test-Time Refinement
- Augmentation-based Domain Generalization for Semantic Segmentation
- FedPIDAvg: A PID controller inspired aggregation method for Federated Learning
- SQLi Detection with ML: A data-source perspective
- Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
- ComGAN: Toward GANs Exploiting Multiple Samples
- Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey
- Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning
- Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
- Renate: A Library for Real-World Continual Learning
- Improving Synthetically Generated Image Detection in Cross-Concept Settings
- VR Facial Animation for Immersive Telepresence Avatars
- MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
- Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
- GRIG: Few-Shot Generative Residual Image Inpainting
- D2NT: A High-Performing Depth-to-Normal Translator
- SocialDial: A Benchmark for Socially-Aware Dialogue Systems
- Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters
- ITER: Iterative Neural Repair for Multi-Location Patches
- Optimal Layout Synthesis for Quantum Circuits as Classical Planning (full version)
- Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications
- CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTracts
- Designing Optimal Personalized Incentive for Traffic Routing using BIG Hype algorithm
- Diabetic Foot Ulcer Grand Challenge 2022 Summary
- Hierarchical State Abstraction Based on Structural Information Principles
- MMC: Multi-Modal Colorization of Images using Textual Descriptions
- Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs
- Causal fault localisation in dataflow systems
- Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model
- MRSN: Multi-Relation Support Network for Video Action Detection
- gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction
- Causal Effect Estimation with Variational AutoEncoder and the Front Door Criterion
- Track Anything: Segment Anything Meets Videos
- ICDAR 2023 Competition on Reading the Seal Title
- 3rd Place Solution to Meta AI Video Similarity Challenge
- Towards Mode Balancing of Generative Models via Diversity Weights
- ThreatCrawl: A BERT-based Focused Crawler for the Cybersecurity Domain
- A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
- Estimation of sparse linear regression coefficients under L-subexponential covariates
- Benchmarking ChatGPT-4 on ACR Radiation Oncology In-Training (TXIT) Exam and Red Journal Gray Zone Cases: Potentials and Challenges for AI-Assisted Medical Education and Decision Making in Radiation Oncology
- UTSGAN: Unseen Transition Suss GAN for Transition-Aware Image-to-image Translation
- Spikingformer: A Key Foundation Model for Spiking Neural Networks
- Geometric Relational Embeddings: A Survey
- Constructing Tree-based Index for Efficient and Effective Dense Retrieval
- MoniLog: An Automated Log-Based Anomaly Detection System for Cloud Computing Infrastructures
- Is ChatGPT the Ultimate Programming Assistant -- How far is it?
- Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning
- Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
- Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator
- KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
- Generating Topic Pages for Scientific Concepts Using Scientific Publications
- Development of a Trust-Aware User Simulator for Statistical Proactive Dialog Modeling in Human-AI Teams
- Addressing distributional shifts in operations management: The case of order fulfillment in customized production
- Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization
- Transformer-based stereo-aware 3D object detection from binocular images
- Data-driven Knowledge Fusion for Deep Multi-instance Learning
- Unsupervised Machine Learning to Classify the Confinement of Waves in Periodic Superstructures
- Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting
- Recurrent neural network based parameter estimation of Hawkes model on high-frequency financial data
- The State of the Art in transformer fault diagnosis with artificial intelligence and Dissolved Gas Analysis: A Review of the Literature
- Underwater object classification combining SAS and transferred optical-to-SAS Imagery
- Incorporating Experts' Judgment into Machine Learning Models
- A Benchmark for Cycling Close Pass Detection from Video Streams
- Universal Domain Adaptation via Compressive Attention Matching
- Towards a Praxis for Intercultural Ethics in Explainable AI
- On the lifting and reconstruction of nonlinear systems with multiple invariant sets
- Fitness-for-Duty Classification using Temporal Sequences of Iris Periocular images
- Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
- Glocal Energy-based Learning for Few-Shot Open-Set Recognition
- Human intuition as a defense against attribute inference
- Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions
- Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
- Robust and Efficient Memory Network for Video Object Segmentation
- Local Energy Distribution Based Hyperparameter Determination for Stochastic Simulated Annealing
- Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
- Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning
- Shape from Shading for Robotic Manipulation
- Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
- Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving
- Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
- Multiplierless In-filter Computing for tinyML Platforms
- NoiseTrans: Point Cloud Denoising with Transformers
- PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis
- OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images
- FineEHR: Refine Clinical Note Representations to Improve Mortality Prediction
- Coevolution of Camouflage
- Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation
- Adaptive-saturated RNN: Remember more with less instability
- Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?
- B2Opt: Learning to Optimize Black-box Optimization with Little Budget
- Now You See Me: Robust approach to Partial Occlusions