Papers
Fri 11 Aug 2023
163 papers
- Learning Deductive Reasoning from Synthetic Corpus based on Formal LogicLLM reasoning → Reasoning benchmarks and evaluation +1
- Taming Self-Training for Open-Vocabulary Object DetectionSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
- White-box Membership Inference Attacks against Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
- Detecting and Preventing Hallucinations in Large Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
- ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Mirror Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation ModalsLLM reasoning → Prompting and chain-of-thought reasoning
- Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic FeaturesKnowledge distillation → Multimodal distillation
- DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Learning Control Policies for Variable Objectives from Offline DataOffline RL and imitation learning from data → Offline RL algorithms
- Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance FlowDiffusion models → 3D, point cloud and scene generation
- Experts Weights Averaging: A New General Training Scheme for Vision TransformersMixture-of-experts → Vision mixture-of-experts
- Illumination and Shadows in Head Rotation: experiments with Denoising Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Diverse Data Augmentation with Diffusions for Effective Test-time Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
- Attention, not scale, drives human-AI alignment in multimodal language predictionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Masked-Attention Diffusion Guidance for Spatially Controlling Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- Controlling Character Motions without Observable Driving SourceEnd-to-end autonomous driving → Generative simulation for driving
- BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Parametric Leaky Tanh: A New Hybrid Activation Function for Deep Learning
- Inappropriate Benefits and Identification of ChatGPT Misuse in Programming Tests: A Controlled Experiment
- FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare
- Monitoring of Urban Changes with multi-modal Sentinel 1 and 2 Data in Mariupol, Ukraine, in 2022/23
- Deep learning-based flow disaggregation for short-term hydropower plant operations
- Causally Linking Health Application Data and Personal Information Management Tools
- AI-Assisted Investigation of On-Chain Parameters: Risky Cryptocurrencies and Price Factors
- Evaluating Picture Description Speech for Dementia Detection using Image-text Alignment
- A Hierarchical Descriptor Framework for On-the-Fly Anatomical Location Matching between Longitudinal Studies
- An Encoder-Decoder Approach for Packing Circles
- M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
- Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review
- Dialogue Possibilities between a Human Supervisor and UAM Air Traffic Management: Route Alteration
- A Brain-Computer Interface Augmented Reality Framework with Auto-Adaptive SSVEP Recognition
- Learning Bayesian Networks with Heterogeneous Agronomic Data Sets via Mixed-Effect Models and Hierarchical Clustering
- R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild
- Dynamic Planning with a LLM
- U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds
- Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion
- DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System
- CATS v2: Hybrid encoders for robust medical segmentation
- UAMM: Price-oracle based Automated Market Maker
- Large Language Models and Knowledge Graphs: Opportunities and Challenges
- Wireless Federated k-Means Clustering with Non-coherent Over-the-Air Computation
- Topic-Level Bayesian Surprise and Serendipity for Recommender Systems
- Large Language Models to Identify Social Determinants of Health in Electronic Health Records
- Learning Distributions via Monte-Carlo Marginalization
- Surrogate Model for Geological CO2 Storage and Its Use in Hierarchical MCMC History Matching
- Size Lowerbounds for Deep Operator Networks
- Combining feature aggregation and geometric similarity for re-identification of patterned animals
- Deep Learning-Based Open Source Toolkit for Eosinophil Detection in Pediatric Eosinophilic Esophagitis
- Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology
- Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss
- Predicting Resilience with Neural Networks
- Towards Packaging Unit Detection for Automated Palletizing Tasks
- Discovering Local Binary Pattern Equation for Foreground Object Removal in Videos
- A New Approach to Overcoming Zero Trade in Gravity Models to Avoid Indefinite Values in Linear Logarithmic Equations and Parameter Verification Using Machine Learning
- Classification of All Blood Cell Images using ML and DL Models
- Defensive Perception: Estimation and Monitoring of Neural Network Performance under Deployment
- Classification of White Blood Cells Using Machine and Deep Learning Models: A Systematic Review
- Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT
- Target Detection on Hyperspectral Images Using MCMC and VI Trained Bayesian Neural Networks
- The divergence time of protein structures modelled by Markov matrices and its relation to the divergence of sequences
- Foundation Model is Efficient Multimodal Multitask Model Selector
- Enhancing Network Management Using Code Generated by Large Language Models
- ChatGPT-based Investment Portfolio Selection
- Self-Alignment with Instruction Backtranslation
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
- Private Distribution Learning with Public Data: The View from Sample Compression
- KETM:A Knowledge-Enhanced Text Matching method
- MaxFloodCast: Ensemble Machine Learning Model for Predicting Peak Inundation Depth And Decoding Influencing Features
- Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms
- Nonlinear Permuted Granger Causality
- Continual Face Forgery Detection via Historical Distribution Preserving
- Change Point Detection with Conceptors
- A Large Language Model Enhanced Conversational Recommender System
- Safety in Traffic Management Systems: A Comprehensive Survey
- Towards a Causal Probabilistic Framework for Prediction, Action-Selection & Explanations for Robot Block-Stacking Tasks
- Exploring Predicate Visual Context in Detecting Human-Object Interactions
- Weakly Supervised Text Classification on Free Text Comments in Patient-Reported Outcome Measures
- DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
- Software Doping Analysis for Human Oversight
- Assessing Guest Nationality Composition from Hotel Reviews
- Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook
- Task Conditioned BERT for Joint Intent Detection and Slot-filling
- Rethinking the Localization in Weakly Supervised Object Localization
- Phased Deep Spatio-temporal Learning for Highway Traffic Volume Prediction
- Gaussian Process Regression for Maximum Entropy Distribution
- Semihierarchical Reconstruction and Weak-area Revisiting for Robotic Visual Seafloor Mapping
- Identification of the Relevance of Comments in Codes Using Bag of Words and Transformer Based Models
- CompTLL-UNet: Compressed Domain Text-Line Localization in Challenging Handwritten Documents using Deep Feature Learning from JPEG Coefficients
- Application of Artificial Neural Networks for Investigation of Pressure Filtration Performance, a Zinc Leaching Filter Cake Moisture Modeling
- A Game-Theoretic Framework for Joint Forecasting and Planning
- PDE Discovery for Soft Sensors Using Coupled Physics-Informed Neural Network with Akaike's Information Criterion
- Uncertainty Quantification for Image-based Traffic Prediction across Cities
- Improving Joint Speech-Text Representations Without Alignment
- Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
- Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models
- Hawkes Processes with Delayed Granger Causality
- Composable Function-preserving Expansions for Transformer Architectures
- Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation
- Automated Construction of Time-Space Diagrams for Traffic Analysis Using Street-View Video Sequence
All 163
- RIGID: Recurrent GAN Inversion and Editing of Real Face Videos
- Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes
- Reinforcement Logic Rule Learning for Temporal Point Processes
- Toward a Better Understanding of Loss Functions for Collaborative Filtering
- An Autoethnographic Exploration of XAI in Algorithmic Composition
- Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters
- Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization
- Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling
- Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space
- Out-of-Distribution Detection for Monocular Depth Estimation
- Safeguarding Learning-based Control for Smart Energy Systems with Sampling Specifications
- A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation
- Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction
- Computer-Aided Cytology Diagnosis in Animals: CNN-Based Image Quality Assessment for Accurate Disease Classification
- Hardware Accelerators in Autonomous Driving
- Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
- Towards Instance-adaptive Inference for Federated Learning
- Learning to Guide Human Experts via Personalized Large Language Models
- Deep Context Interest Network for Click-Through Rate Prediction
- Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?
- Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation
- Scale-Preserving Automatic Concept Extraction (SPACE)
- Optimizing transformer-based machine translation model for single GPU training: a hyperparameter ablation study
- Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
- Large Language Models for Telecom: Forthcoming Impact on the Industry
- ViGT: Proposal-free Video Grounding with Learnable Token in Transformer
- Does AI for science need another ImageNet Or totally different benchmarks? A case study of machine learning force fields
- Deep Task-specific Bottom Representation Network for Multi-Task Recommendation
- Audio is all in one: speech-driven gesture synthetics using WavLM pre-trained model
- Image-based Geolocalization by Ground-to-2.5D Map Matching
- Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
- MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection
- Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance
- TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
- Contrastive Explanations of Centralized Multi-agent Optimization Solutions
- Face Encryption via Frequency-Restricted Identity-Agnostic Attacks
- CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation
- Zero-shot Text-driven Physically Interpretable Face Editing
- Tweet Sentiment Extraction using Viterbi Algorithm with Transfer Learning
- Focused Specific Objects NeRF
- Learning nonparametric DAGs with incremental information via high-order HSIC
- YOLOrtho -- A Unified Framework for Teeth Enumeration and Dental Disease Detection
- Decentralised Governance-Driven Architecture for Designing Foundation Model based Systems: Exploring the Role of Blockchain in Responsible AI
- Compositional Learning in Transformer-Based Human-Object Interaction Detection
- Learned Point Cloud Compression for Classification
- Node Embedding for Homophilous Graphs with ARGEW: Augmentation of Random walks by Graph Edge Weights
- Uncertainty-Aware Cross-Modal Transfer Network for Sketch-Based 3D Shape Retrieval
- FoodSAM: Any Food Segmentation
- A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions
- LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain of Teach Prompts
- Generalizing Event-Based Motion Deblurring in Real-World Scenarios
- INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
- CaPhy: Capturing Physical Properties for Animatable Human Avatars
- BATINet: Background-Aware Text to Image Synthesis and Manipulation Network
- Semantics2Hands: Transferring Hand Motion Semantics between Avatars
- Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking
- On the equivalence of Occam algorithms
- Comparing the quality of neural network uncertainty estimates for classification problems
- Semantic-embedded Similarity Prototype for Scene Recognition
- Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding
- DF2: Distribution-Free Decision-Focused Learning
- PIPPA: A Partially Synthetic Conversational Dataset
- Empirical Bayes Estimation with Side Information: A Nonparametric Integrative Tweedie Approach