Papers
Tue 26 Sep 2023
228 papers
- V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication IntegrationEnd-to-end autonomous driving → Cooperative and V2X driving
- Learning Using Generated Privileged Information by Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
- Ragas: Automated Evaluation of Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
- DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion ModelsDiffusion models → Video generation
- Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingLLM reasoning → Reinforcement learning for reasoning
- Large Language Model Alignment: A SurveyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- MoCaE: Mixture of Calibrated Experts Significantly Improves Object DetectionMixture-of-experts → Vision mixture-of-experts
- Integration of Large Language Models within Cognitive Architectures for Autonomous RobotsLLM reasoning → Spatial and embodied reasoning
- FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image EditingDiffusion models → Image generation, text-to-image and editing
- Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model EvaluationDiffusion models → Image generation, text-to-image and editing
- Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker VerificationKnowledge distillation → Speech and audio distillation
- A Structured Prediction Approach for Robot Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- On quantifying and improving realism of images generated with diffusionDiffusion models → Image generation, text-to-image and editing
- Text-image guided Diffusion Model for generating Deepfake celebrity interactionsDiffusion models → Image generation, text-to-image and editing
- ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth EstimationKnowledge distillation → Detection and dense prediction distillation
- Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image EnhancementDiffusion models → Inverse problems and image restoration
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineKnowledge distillation → Detection and dense prediction distillation
- Efficient Post-training Quantization with FP8 FormatsDiffusion models → Diffusion foundations and sampling
- Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression
- MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation
- Fixing the problems of deep neural networks will require better training data and learning algorithms
- With ChatGPT, do we have to rewrite our learning objectives -- CASE study in Cybersecurity
- FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation
- Hebbian learning inspired estimation of the linear regression parameters from queries
- Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI
- Ego-perspective enhanced fitness training experience of AR Try to Move game
- Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition
- Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems
- Investigation of factors regarding the effects of COVID-19 pandemic on college students' depression by quantum annealer
- Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks
- GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes
- Telescope: An Automated Hybrid Forecasting Approach on a Level-Playing Field
- Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project
- Identifying factors associated with fast visual field progression in patients with ocular hypertension based on unsupervised machine learning
- ChatGPT & Mechanical Engineering: Examining performance on the FE Mechanical Engineering and Undergraduate Exams
- How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
- Automated Detection of Persistent Inflammatory Biomarkers in Post-COVID-19 Patients Using Machine Learning Techniques
- ANNCRIPS: Artificial Neural Networks for Cancer Research In Prediction & Survival
- Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
- Targeting relative risk heterogeneity with causal forests
- DeepROCK: Error-controlled interaction detection in deep neural networks
- Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning
- Conversion of single-energy computed tomography to parametric maps of dual-energy computed tomography using convolutional neural network
- M33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding
- MAPTree: Beating "Optimal" Decision Trees with Bayesian Decision Trees
- The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents
- STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience
- Beyond Log-Concavity: Theory and Algorithm for Sum-Log-Concave Optimization
- Multiple Case Physics-Informed Neural Network for Biomedical Tube Flows
- Maximum diffusion reinforcement learning
- Scaling Representation Learning from Ubiquitous ECG with State-Space Models
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
- Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
- A Physics Enhanced Residual Learning (PERL) Framework for Vehicle Trajectory Prediction
- Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models
- Boosting High Resolution Image Classification with Scaling-up Transformers
- A Topological Machine Learning Pipeline for Classification
- Efficient Low-rank Backpropagation for Vision Transformer Adaptation
- Memory-Efficient Continual Learning Object Segmentation for Long Video
- DECO: Dense Estimation of 3D Human-Scene Contact In The Wild
- ObVi-SLAM: Long-Term Object-Visual SLAM
- SLIQ: Quantum Image Similarity Networks on Noisy Quantum Computers
- STARC: A General Framework For Quantifying Differences Between Reward Functions
- Method and Validation for Optimal Lineup Creation for Daily Fantasy Football Using Machine Learning and Linear Programming
- VPA: Fully Test-Time Visual Prompt Adaptation
- SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets
- Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks
- APIS: A paired CT-MRI dataset for ischemic stroke segmentation challenge
- PlotMap: Automated Layout Design for Building Game Worlds
- User Experience Design Professionals' Perceptions of Generative Artificial Intelligence
- Cross-Validation for Training and Testing Co-occurrence Network Inference Algorithms
- Collaborative Watermarking for Adversarial Speech Synthesis
- Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition
- A Comparative Study of Filters and Deep Learning Models to predict Diabetic Retinopathy
- Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcasting
- CLRmatchNet: Enhancing Curved Lane Detection with Deep Matching Process
- ICML 2023 Topological Deep Learning Challenge : Design and Results
- Monitoring Machine Learning Models: Online Detection of Relevant Deviations
- Zero-Shot Reinforcement Learning from Low Quality Data
- Robust Stance Detection: Understanding Public Perceptions in Social Media
- Revealing the Power of Masked Autoencoders in Traffic Forecasting
- 3D Reconstruction with Generalizable Neural Fields using Scene Priors
- A Review on AI Algorithms for Energy Management in E-Mobility Services
- PINF: Continuous Normalizing Flows for Physics-Constrained Deep Learning
- Deep Generative Methods for Producing Forecast Trajectories in Power Systems
- Contrastive Continual Multi-view Clustering with Filtered Structural Fusion
- From Asset Flow to Status, Action and Intention Discovery: Early Malice Detection in Cryptocurrency
- Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies
- Generating Visual Scenes from Touch
- InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
- SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
- Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow
- Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
- Case Study: Ensemble Decision-Based Annotation of Unconstrained Real Estate Images
- Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs
- Identifying Simulation Model Through Alternative Techniques for a Medical Device Assembly Process
- VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
- Single Biological Neurons as Temporally Precise Spatio-Temporal Pattern Recognizers
All 228
- RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models
- Video-adverb retrieval with compositional adverb-action embeddings
- The Surveillance AI Pipeline
- RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation
- On Excess Risk Convergence Rates of Neural Network Classifiers
- Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
- QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers
- When Prolog meets generative models: a new approach for managing knowledge and planning in robotic applications
- Class Incremental Learning via Likelihood Ratio Based Task Prediction
- Can-SAVE: Deploying Low-Cost and Population-Scale Cancer Screening via Survival Analysis Variables and EHR
- HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning
- SOFARI: High-Dimensional Manifold-Based Inference
- Nuclear Pleomorphism in Canine Cutaneous Mast Cell Tumors: Comparison of Reproducibility and Prognostic Relevance between Estimates, Manual Morphometry and Algorithmic Morphometry
- Synthia's Melody: A Benchmark Framework for Unsupervised Domain Adaptation in Audio
- IFT: Image Fusion Transformer for Ghost-free High Dynamic Range Imaging
- Unidirectional brain-computer interface: Artificial neural network encoding natural images to fMRI response in the visual cortex
- Question-Answering Approach to Evaluating Legal Summaries
- Updated Corpora and Benchmarks for Long-Form Speech Recognition
- Automating question generation from educational text
- Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Features
- An Ensemble Model for Distorted Images in Real Scenarios
- IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network
- Measurement Models For Sailboats Price vs. Features And Regional Areas
- Robust Sequential DeepFake Detection
- Tempo Adaptation in Non-stationary Reinforcement Learning
- Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks
- Improving Unsupervised Visual Program Inference with Code Rewriting Families
- Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
- A novel approach for holographic 3D content generation without depth map
- Interactively Learning Social Media Representations Improves News Source Factuality Detection
- GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction
- Context-Aware Generative Models for Prediction of Aircraft Ground Tracks
- Addressing preferred orientation in single-particle cryo-EM through AI-generated auxiliary particles
- Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher
- Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
- Learning Generative Models for Climbing Aircraft from Radar Data
- Parallel Multi-Objective Hyperparameter Optimization with Uniform Normalization and Bounded Objectives
- Addressing Data Misalignment in Image-LiDAR Fusion on Point Cloud Segmentation
- A Democratic Platform for Engaging with Disabled Community in Generative AI Development
- PHRIT: Parametric Hand Representation with Implicit Template
- Robustness of the Random Language Model
- Face Cartoonisation For Various Poses Using StyleGAN
- Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
- Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning
- FDLS: A Deep Learning Approach to Production Quality, Controllable, and Retargetable Facial Performances
- Verifiable Learned Behaviors via Motion Primitive Composition: Applications to Scooping of Granular Media
- Nearest Neighbor Guidance for Out-of-Distribution Detection
- Locality-preserving Directions for Interpreting the Latent Space of Satellite Image GANs
- Credit Card Fraud Detection with Subspace Learning-based One-Class Classification
- Explainable Sustainability for AI in the Arts
- Directional Texture Editing for 3D Models
- Cross-Dataset-Robust Method for Blind Real-World Image Quality Assessment
- Unsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone
- Cluster Exploration using Informative Manifold Projections
- Supersonic: Learning to Generate Source Code Optimizations in C/C++
- Learning Multimodal Attention for Manipulating Deformable Objects with Changing States
- Generalization of pixel-wise phase estimation by CNN and improvement of phase-unwrapping by MRF optimization for one-shot 3D scan
- Segmentation-Free Streaming Machine Translation
- OS-net: Orbitally Stable Neural Networks
- Three-dimensional Tracking of a Large Number of High Dynamic Objects from Multiple Views using Current Statistical Model
- Discrepancy Matters: Learning from Inconsistent Decoder Features for Consistent Semi-supervised Medical Image Segmentation
- A Comparative Study of Population-Graph Construction Methods and Graph Neural Networks for Brain Age Regression
- ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios
- Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning
- Evaluating Soccer Match Prediction Models: A Deep Learning Approach and Feature Optimization for Gradient-Boosted Trees
- 3D printed realistic finger vein phantoms
- Fine-tuning and aligning question answering models for complex information extraction tasks
- 3D Density-Gradient based Edge Detection on Neural Radiance Fields (NeRFs) for Geometric Reconstruction
- Forgetting-aware Linear Bias for Attentive Knowledge Tracing
- Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data
- Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
- Frugal Satellite Image Change Detection with Deep-Net Inversion
- Transferring climate change physical knowledge
- Towards Data-efficient Customer Intent Recognition with Prompt-based Learning Paradigm
- Markov Chain Mirror Descent On Data Federation
- BLIP-Adapter: Parameter-Efficient Transfer Learning for Mobile Screenshot Captioning
- Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
- KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation
- Multi-Label Feature Selection Using Adaptive and Transformed Relevance
- InvKA: Gait Recognition via Invertible Koopman Autoencoder
- ConPET: Continual Parameter-Efficient Tuning for Large Language Models
- Program Repair with Minimal Edits Using CodeT5
- Diffusion-based Holistic Texture Rectification and Synthesis
- Age Minimization in Massive IoT via UAV Swarm: A Multi-agent Reinforcement Learning Approach
- Image Denoising via Style Disentanglement
- Advanced Volleyball Stats for All Levels: Automatic Setting Tactic Detection and Classification with a Single Camera
- SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion
- Volumetric Semantically Consistent 3D Panoptic Mapping
- Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models
- Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization
- PLMM: Personal Large Language Models on Mobile Devices
- Optimizing delegation between human and AI collaborative agents
- QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
- Explaining Deep Face Algorithms through Visualization: A Survey
- Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer
- Structure Invariant Transformation for better Adversarial Transferability
- On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks
- DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch
- A Simple Text to Video Model via Transformer
- Are Human-generated Demonstrations Necessary for In-context Learning?
- XGV-BERT: Leveraging Contextualized Language Model and Graph Neural Network for Efficient Software Vulnerability Detection
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
- Leveraging Herpangina Data to Enhance Hospital-level Prediction of Hand-Foot-and-Mouth Disease Admissions Using UPTST
- ALEX: Towards Effective Graph Transfer Learning with Noisy Labels
- DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks
- ZiCo-BC: A Bias Corrected Zero-Shot NAS for Vision Tasks
- Learning NEAT Emergent Behaviors in Robot Swarms
- Transformer-based classification of user queries for medical consultancy with respect to expert specialization
- CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration
- Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
- Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis
- Free Discontinuity Regression: With an Application to the Economic Effects of Internet Shutdowns
- Text-to-Image Generation for Abstract Concepts
- Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach
- Towards A Unified Utilitarian Ethics Framework for Healthcare Artificial Intelligence
- NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space
- Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents
- Reparameterized Variational Rejection Sampling
- Unsupervised Graph Deep Learning Reveals Emergent Flood Risk Profile of Urban Areas
- Neuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method
- Progressive Text-to-3D Generation for Automatic 3D Prototyping
- Decoding trust: A reinforcement learning perspective
- Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
- Applications of Sequential Learning for Medical Image Classification
- Distortion Resilience for Goal-Oriented Semantic Communication
- Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
- DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space
- CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss