Papers
Mon 25 Sep 2023
256 papers
- Training-free Linear Image Inverses via FlowsDiffusion models → Flow matching, time series and science
- Identifying the Risks of LM Agents with an LM-Emulated SandboxLLM agents and tool use → Agent threats, guardrails and governance
- Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming EducationLLM agents and tool use → Educational agents and math problem solving
- Aligning Large Multimodal Models with Factually Augmented RLHFMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
- Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain TranslationDiffusion models → Diffusion foundations and sampling
- LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language ModelsMixture-of-experts → MoE large language models
- Rethinking Internet Communication Through LLMs: How Close Are We?LLM reasoning → Reasoning benchmarks and evaluation
- MoDem-V2: Visuo-Motor World Models for Real-World Robot ManipulationWorld models → Embodied and robot world models
- Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Continual Driving Policy Optimization with Closed-Loop Individualized CurriculaEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Data Upcycling Knowledge Distillation for Image Super-ResolutionKnowledge distillation → General knowledge distillation methods
- Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial NetworksLLM safety and security → Vision-language and text-to-image safety
- Hierarchical Imitation Learning for Stochastic EnvironmentsOffline RL and imitation learning from data → Imitation learning methods
- SPOTS: Stable Placement of Objects with Reasoning in Semi-Autonomous Teleoperation SystemsLLM reasoning → Spatial and embodied reasoning
- DDTSE: Discriminative Diffusion Model for Target Speech ExtractionDiffusion models → Audio, speech and music
- Statistical Perspective of Top-K Sparse Softmax Gating Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
- Tuning Multi-mode Token-level Prompt Alignment across ModalitiesMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- AI and Democracy's Digital Identity Crisis
- The Cybersecurity Crisis of Artificial Intelligence: Unrestrained Adoption and Natural Language-Based Attacks
- Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping
- Can neural networks count digit frequency?
- A Novel Deep Learning Technique for Morphology Preserved Fetal ECG Extraction from Mother ECG using 1D-CycleGAN
- A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing
- Enhancing Healthcare with EOG: A Novel Approach to Sleep Stage Classification
- Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
- Multi-Task Learning For Reduced Popularity Bias In Multi-Territory Video Recommendations
- Benchmarking Local Robustness of High-Accuracy Binary Neural Networks for Enhanced Traffic Sign Recognition
- Physics-Informed Solution of The Stationary Fokker-Plank Equation for a Class of Nonlinear Dynamical Systems: An Evaluation Study
- Disinformation Detection: An Evolving Challenge in the Age of LLMs
- Understanding the Structure of QM7b and QM9 Quantum Mechanical Datasets Using Unsupervised Learning
- Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
- Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts
- Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew
- Integrating Higher-Order Dynamics and Roadway-Compliance into Constrained ILQR-based Trajectory Planning for Autonomous Vehicles
- Generative Escher Meshes
- Towards a statistical theory of data selection under weak supervision
- Disruption Detection for a Cognitive Digital Supply Chain Twin Using Hybrid Deep Learning
- Art or Artifice? Large Language Models and the False Promise of Creativity
- Tactile Estimation of Extrinsic Contact Patch for Stable Placement
- MEMO: Dataset and Methods for Robust Multimodal Retinal Image Registration with Large or Small Vessel Density Differences
- Algorithmic Collusion or Competition: the Role of Platforms' Recommender Systems
- Cluster-based Method for Eavesdropping Identification and Localization in Optical Links
- Effect of roundabout design on the behavior of road users: A case study of roundabouts with application of Unsupervised Machine Learning
- Dynamic Scene Graph Representation for Surgical Video
- Pixel-Grounded Prototypical Part Networks
- ChatGPT Performance on Standardized Testing Exam -- A Proposed Strategy for Learners
- Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernels
- Watch Your Language: Investigating Content Moderation with Large Language Models
- UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities
- Accurate and Interactive Visual-Inertial Sensor Calibration with Next-Best-View and Next-Best-Trajectory Suggestion
- Byzantine-Resilient Federated PCA and Low Rank Column-wise Sensing
- DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
- Zeroth-order Riemannian Averaging Stochastic Approximation Algorithms
- Uncertainty Aware Deep Learning for Particle Accelerators
- Assessment of a new GeoAI foundation model for flood inundation mapping
- Interaction-Aware Decision-Making for Autonomous Vehicles in Forced Merging Scenario Leveraging Social Psychology Factors
- Era Splitting: Invariant Learning for Decision Trees
- Classifying token frequencies using angular Minkowski p-distance
- Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
- AiAReSeg: Catheter Detection and Segmentation in Interventional Ultrasound using Transformers
- When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs
- Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond
- Unveiling the Potential of Deep Learning Models for Solar Flare Prediction in Near-Limb Regions
- LogGPT: Log Anomaly Detection via GPT
- Incorporating Ensemble and Transfer Learning For An End-To-End Auto-Colorized Image Detection Model
- Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unet
- Adapting Double Q-Learning for Continuous Reinforcement Learning
- FARSEC: A Reproducible Framework for Automatic Real-Time Vehicle Speed Estimation Using Traffic Cameras
- DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulation
- Online Active Learning For Sound Event Detection
- Skilog: A Smart Sensor System for Performance Analysis and Biofeedback in Ski Jumping
- Learning dislocation dynamics mobility laws from large-scale MD simulations
- Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery
- On the expressivity of embedding quantum kernels
- Provable advantages of kernel-based quantum learners and quantum preprocessing based on Grover's algorithm
- Joint Audio and Speech Understanding
- pLMFPPred: a novel approach for accurate prediction of functional peptides integrating embedding from pre-trained protein language model and imbalanced learning
- Physics of Language Models: Part 3.2, Knowledge Manipulation
- DECORAIT -- DECentralized Opt-in/out Registry for AI Training
- Date-Driven Approach for Identifying State of Hemodialysis Fistulas: Entropy-Complexity and Formal Concept Analysis
- Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion
- Predicting environment effects on breast cancer by implementing machine learning
- Guess & Sketch: Language Model Guided Transpilation
- Implicit Sensing in Traffic Optimization: Advanced Deep Reinforcement Learning Techniques
- Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction
- An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-oriented Systems
- Early Churn Prediction from Large Scale User-Product Interaction Time Series
- Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering
- Exploring Robot Morphology Spaces through Breadth-First Search and Random Query
- Sampling - Variational Auto Encoder - Ensemble: In the Quest of Explainable Artificial Intelligence
- Extreme Parkour with Legged Robots
- Chop & Learn: Recognizing and Generating Object-State Compositions
- 3D Indoor Instance Segmentation in an Open-World
- UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation
- Tasks Makyth Models: Machine Learning Assisted Surrogates for Tipping Points
- LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
- Noise-in, Bias-out: Balanced and Real-time MoCap Solving
- Innovative Digital Storytelling with AIGC: Exploration and Discussion of Recent Advances
All 256
- DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention
- Efficient Pauli channel estimation with logarithmic quantum memory
- Towards General-Purpose Text-Instruction-Guided Voice Conversion
- Small-scale proxies for large-scale Transformer training instabilities
- Lifelong Robot Learning with Human Assisted Language Planners
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
- Multiple Different Black Box Explanations for Image Classifiers
- A post-selection algorithm for improving dynamic ensemble selection methods
- DeepMesh: Mesh-based Cardiac Motion Tracking using Deep Learning
- Overview of Class Activation Maps for Visualization Explainability
- Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation
- Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
- NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields
- On the Non-Associativity of Analog Computations
- Tiled Multiplane Images for Practical 3D Photography
- CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
- Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation
- SINCERE: Supervised Information Noise-Contrastive Estimation REvisited
- Perception-and-Energy-aware Motion Planning for UAV using Learning-based Model under Heteroscedastic Uncertainty
- Unsupervised correspondence with combined geometric learning and imaging for radiotherapy applications
- Identity-preserving Editing of Multiple Facial Attributes by Learning Global Edit Directions and Local Adjustments
- Industrial Application of 6D Pose Estimation for Robotic Manipulation in Automotive Internal Logistics
- OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding
- A Weighted Prognostic Covariate Adjustment Method for Efficient and Powerful Treatment Effect Inferences in Randomized Controlled Trials
- Prediction Model For Wordle Game Results With High Robustness
- Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning
- Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation
- Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation
- Learning to Abstain From Uninformative Data
- Urdu Poetry Generated by Using Deep Learning Techniques
- Mixed variable structural optimization using mixed variable system Monte Carlo tree search formulation
- Accelerating Machine Learning Algorithms with Adaptive Sampling
- MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation
- Autonomous Vehicles an overview on system, cyber security, risks, issues, and a way forward
- QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds
- Framework based on complex networks to model and mine patient pathways
- Automatic Animation of Hair Blowing in Still Portrait Photos
- Detecting and Grounding Multi-Modal Media Manipulation and Beyond
- (Predictable) Performance Bias in Unsupervised Anomaly Detection
- Learning Restricted Boltzmann Machines with greedy quantum search
- Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
- Federated Learning Under Restricted User Availability
- Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation
- Towards End-User Development for IoT: A Case Study on Semantic Parsing of Cooking Recipes for Programming Kitchen Devices
- LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch
- Designing and evaluating an online reinforcement learning agent for physical exercise recommendations in N-of-1 trials
- Extragradient Type Methods for Riemannian Variational Inequality Problems
- SPIRT: A Fault-Tolerant and Reliable Peer-to-Peer Serverless ML Training Architecture
- Examining Temporal Bias in Abusive Language Detection
- Exploring the Impact of Serverless Computing on Peer To Peer Training Machine Learning
- IEBins: Iterative Elastic Bins for Monocular Depth Estimation
- Masked Image Residual Learning for Scaling Deeper Vision Transformers
- One-Class Classification for Intrusion Detection on Vehicular Networks
- On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
- Driving behavior-guided battery health monitoring for electric vehicles using machine learning
- SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
- MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks
- Small Objects Matters in Weakly-supervised Semantic Segmentation
- HyperTrack: Neural Combinatorics for High Energy Physics
- Semi-Abstract Value-Based Argumentation Framework
- Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech
- Affective Game Computing: A Survey
- Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning
- On the Benefit of Optimal Transport for Curriculum Reinforcement Learning
- Convolutional autoencoder-based multimodal one-class classification
- BiSinger: Bilingual Singing Voice Synthesis
- REPA: Client Clustering without Training and Data Labels for Improved Federated Learning in Non-IID Settings
- Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challenges
- Analysis and Detection of Pathological Voice using Glottal Source Features
- ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
- Neural Network Parameter-optimization of Gaussian pmDAGs
- BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
- AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation
- FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
- Weakly Supervised Semantic Segmentation by Knowledge Graph Inference
- Revisiting LARS for Large Batch Training Generalization of Neural Networks
- Single Image Test-Time Adaptation for Segmentation
- Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience
- An automatic selection of optimal recurrent neural network architecture for processes dynamics modelling purposes
- DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
- Diffeomorphic Transformations for Time Series Analysis: An Efficient Approach to Nonlinear Warping
- TomOpt: Differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography
- Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time
- LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression
- Variational Inference for Scalable 3D Object-centric Learning
- Multiple evolutionary pressures shape identical consonant avoidance in the world's languages
- Linked shrinkage to improve estimation of interaction effects in regression models
- Identification of Mixtures of Discrete Product Distributions in Near-Optimal Sample and Time Complexity
- A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
- Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
- Better Generalization of White Matter Tract Segmentation to Arbitrary Datasets with Scaled Residual Bootstrap
- Morphological Computing as Logic Underlying Cognition in Human, Animal, and Intelligent Machine
- Diverse Semantic Image Editing with Style Codes
- Audio classification with Dilated Convolution with Learnable Spacings
- May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability
- Connecting Speech Encoder and Large Language Model for ASR
- Egocentric RGB+Depth Action Recognition in Industry-Like Settings
- Newton Method-based Subspace Support Vector Data Description
- Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design
- In-Domain GAN Inversion for Faithful Reconstruction and Editability
- Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets
- VidChapters-7M: Video Chapters at Scale
- Local and Global Trend Bayesian Exponential Smoothing Models
- Characterising User Transfer Amid Industrial Resource Variation: A Bayesian Nonparametric Approach
- Provable Training for Graph Contrastive Learning
- Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
- A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution
- The Time Traveler's Guide to Semantic Web Research: Analyzing Fictitious Research Themes in the ESWC "Next 20 Years" Track
- Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall
- Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey
- SAMN: A Sample Attention Memory Network Combining SVM and NN in One Architecture
- Pseudo Label Selection is a Decision Problem
- Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges
- Recursive Counterfactual Deconfounding for Object Recognition
- Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds
- Matrix Factorization in Tropical and Mixed Tropical-Linear Algebras
- A comparison of controller architectures and learning mechanisms for arbitrary robot morphologies
- Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization
- Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts
- Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environments
- Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
- Graph Representation Learning Towards Patents Network Analysis
- Can Class-Priors Help Single-Positive Multi-Label Learning?
- TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning
- Estimating Treatment Effects Under Heterogeneous Interference
- Skip-Connected Neural Networks with Layout Graphs for Floor Plan Auto-Generation
- Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
- Attention and Pooling based Sigmoid Colon Segmentation in 3D CT images
- PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
- On Calibration of Modern Quantized Efficient Neural Networks
- SuPerPM: A Surgical Perception Framework Based on Deep Point Matching Learned from Physical Constrained Simulation Data
- Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning
- Adversarial Attacks on Video Object Segmentation with Hard Region Discovery
- DISeR: Designing Imaging Systems with Reinforcement Learning
- Traj-LO: In Defense of LiDAR-Only Odometry Using an Effective Continuous-Time Trajectory
- On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors
- Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction
- Penalized Principal Component Analysis Using Smoothing
- Backorder Prediction in Inventory Management: Classification Techniques and Cost Considerations
- IBVC: Interpolation-driven B-frame Video Compression
- Prior Bilinear Based Models for Knowledge Graph Completion
- Dual Feature Augmentation Network for Generalized Zero-shot Learning
- NSOTree: Neural Survival Oblique Tree
- PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition
- MMA-Net: Multiple Morphology-Aware Network for Automated Cobb Angle Measurement
- DVI-SLAM: A Dual Visual Inertial SLAM Network
- Boundary-Aware Proposal Generation Method for Temporal Action Localization
- Forecasting large collections of time series: feature-based methods
- Privacy-preserving Linear Computations in Spiking Neural P Systems
- Projected Randomized Smoothing for Certified Adversarial Robustness
- ReMasker: Imputing Tabular Data with Masked Autoencoding
- Can LLM-Generated Misinformation Be Detected?
- Distribution-Free Statistical Dispersion Control for Societal Applications
- On the Computational Benefit of Multimodal Learning
- Explainable Machine Learning for ICU Readmission Prediction