Papers
Tue 29 Aug 2023
211 papers
- Pure Exploration under Mediators' FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style TransferDiffusion models → Image generation, text-to-image and editing
- When Do Program-of-Thoughts Work for Reasoning?LLM reasoning → Reasoning for agents, planning and code
- Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?LLM reasoning → Reasoning benchmarks and evaluation
- AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
- Elucidating the Exposure Bias in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial ExpressionsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Evaluation and Analysis of Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- SpikeBERT: A Language Spikformer Learned from BERT with Knowledge DistillationKnowledge distillation → Distillation for spiking neural networks
- Large Language Models on the Chessboard: A Study on ChatGPT's Formal Language Comprehension and Complex Reasoning SkillsLLM reasoning → Reasoning for agents, planning and code
- DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight DetectionDiffusion models → Video generation
- DiffBIR: Towards Blind Image Restoration with Generative Diffusion PriorDiffusion models → Inverse problems and image restoration
- SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory BudgetMixture-of-experts → MoE large language models
- C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion ModelDiffusion models → Audio, speech and music
- Read-only Prompt Optimization for Vision-Language Few-shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Analysis of Learned Features and Framework for Potato Disease Detection
- Wordification: A New Way of Teaching English Spelling Patterns
- Explaining Vision and Language through Graphs of Events in Space and Time
- Radiology-Llama2: Best-in-Class Large Language Model for Radiology
- Improving the State of the Art for Training Human-AI Teams: Technical Report #3 -- Analysis of Testbed Alternatives
- Improving the State of the Art for Training Human-AI Teams: Technical Report #2 -- Results of Researcher Knowledge Elicitation Survey
- Improving the State of the Art for Training Human-AI Teams: Technical Report #1 -- Results of Subject-Matter Expert Knowledge Elicitation Survey
- Extracting Mathematical Concepts with Large Language Models
- Modified Lagrangian Formulation of Gear Tooth Crack Analysis using Combined Approach of Variable Mode Decomposition (VMD) and Time Synchronous Averaging (TSA)
- Multimodal Foundation Models For Echocardiogram Interpretation
- Bridging Distribution Learning and Image Clustering in High-dimensional Space
- CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation
- Deep Reinforcement Learning Based Framework for Mobile Energy Disseminator Dispatching to Charge On-the-Road Electric Vehicles
- Ensuring User-side Fairness in Dynamic Recommender Systems
- A General Recipe for Automated Machine Learning in Practice
- AskIt: Unified Programming Interface for Programming with Large Language Models
- Gap-Free Clustering: Sensitivity and Robustness of SDP
- Identifying Constitutive Parameters for Complex Hyperelastic Materials using Physics-Informed Neural Networks
- Hyperbolic Convolutional Neural Networks
- Detection of Mild Cognitive Impairment Using Facial Features in Video Conversations
- Intelligent System for Assessing University Student Personality Development and Career Readiness
- RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images
- Everything Perturbed All at Once: Enabling Differentiable Graph Attacks
- Mixed Variational Flows for Discrete Variables
- InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning
- Benchmarks for Detecting Measurement Tampering
- An Experimental Comparison of Partitioning Strategies for Distributed Graph Neural Network Training
- Learning the greatest common divisor: explaining transformer predictions
- Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning
- Parametric quantile autoregressive conditional duration models with application to intraday value-at-risk
- Over-Squashing in Graph Neural Networks: A Comprehensive survey
- Learning Sequential Information in Task-based fMRI for Synthetic Data Augmentation
- WeatherBench 2: A benchmark for the next generation of data-driven global weather models
- Glocal Explanations of Expected Goal Models in Soccer
- A Pseudo-Boolean Polynomials Approach for Image Edge Detection
- Dimensionality Reduction Using pseudo-Boolean polynomials For Cluster Analysis
- Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning
- Efficient Ray Sampling for Radiance Fields Reconstruction
- DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction
- Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis
- International Governance of Civilian AI: A Jurisdictional Certification Approach
- Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings
- Shatter and Gather: Learning Referring Image Segmentation with Text Supervision
- unORANIC: Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features
- On the Steganographic Capacity of Selected Learning Models
- Classification robustness to common optical aberrations
- 3D Adversarial Augmentations for Robust Out-of-Domain Predictions
- An Adaptive Tangent Feature Perspective of Neural Networks
- A General-Purpose Self-Supervised Model for Computational Pathology
- Learning Modulated Transformation in GANs
- Policy composition in reinforcement learning via multi-objective policy optimization
- Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Prediction
- Input margins can predict generalization too
- A Comparative Study of Loss Functions: Traffic Predictions in Regular and Congestion Scenarios
- Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection
- Canonical Factors for Hybrid Neural Fields
- From SMOTE to Mixup for Deep Imbalanced Classification
- Pseudo-Boolean Polynomials Approach To Edge Detection And Image Segmentation
- Vulgar Remarks Detection in Chittagonian Dialect of Bangla
- Combining predictive distributions of electricity prices: Does minimizing the CRPS lead to optimal decisions in day-ahead bidding?
- Random feature approximation for general spectral methods
- Complementing Onboard Sensors with Satellite Map: A New Perspective for HD Map Construction
- Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability
- WrappingNet: Mesh Autoencoder via Deep Sphere Deformation
- Probabilistic solar flare forecasting using historical magnetogram data
- Robust Long-Tailed Learning via Label-Aware Bounded CVaR
- Color Aesthetics: Fuzzy based User-driven Method for Harmony and Preference Prediction
- The CausalBench challenge: A machine learning contest for gene network inference from single-cell perturbation data
- Decentralized Multi-agent Reinforcement Learning based State-of-Charge Balancing Strategy for Distributed Energy Storage System
- Bayesian Integration of Information Using Top-Down Modulated WTA Networks
- Shape-Margin Knowledge Augmented Network for Thyroid Nodule Segmentation and Diagnosis
- On the Robustness of Object Detection Models on Aerial Images
- Multi-Response Heteroscedastic Gaussian Process Models and Their Inference
- RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
- Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation
- Heterogeneous Multi-Task Gaussian Cox Processes
- Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
- Ego-Motion Estimation and Dynamic Motion Separation from 3D Point Clouds for Accumulating Data and Improving 3D Object Detection
- Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection
- Historical patterns of rice farming explain modern-day language use in China and Japan more than modernization and urbanization
- Lie-Poisson Neural Networks (LPNets): Data-Based Computing of Hamiltonian Systems with Symmetries
- Enhancing Mobile Face Anti-Spoofing: A Robust Framework for Diverse Attack Types under Screen Flash
- IndGIC: Supervised Action Recognition under Low Illumination
- Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundary
- AI Framework for Early Diagnosis of Coronary Artery Disease: An Integration of Borderline SMOTE, Autoencoders and Convolutional Neural Networks Approach
All 211
- The Responsible Development of Automated Student Feedback with Generative AI
- Enhancing Robot Learning through Learned Human-Attention Feature Maps
- Federated Neuro-Symbolic Learning
- Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsing
- 3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking
- Spatio-temporal MLP-graph network for 3D human pose estimation
- On-Device Learning with Binary Neural Networks
- MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection
- TaskLAMA: Probing the Complex Task Understanding of Language Models
- KGConv, a Conversational Corpus grounded in Wikidata
- A Hybrid Membership Latent Distance Model for Unsigned and Signed Integer Weighted Networks
- Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata
- ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques
- Structural Node Embeddings with Homomorphism Counts
- ADFA: Attention-augmented Differentiable top-k Feature Adaptation for Unsupervised Medical Anomaly Detection
- Cross-Modal Retrieval Meets Inference:Improving Zero-Shot Classification with Cross-Modal Retrieval
- AutoDroid: LLM-powered Task Automation in Android
- NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
- Enhancing OCR Performance through Post-OCR Models: Adopting Glyph Embedding for Improved Correction
- Let There Be Sound: Reconstructing High Quality Speech from Silent Videos
- The Relative Gaussian Mechanism and its Application to Private Gradient Descent
- A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation
- Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation
- Reliability Gaps Between Groups in COMPAS Dataset
- Natural language to SQL in low-code platforms
- Assessing Cyclostationary Malware Detection via Feature Selection and Classification
- Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysis
- PronounFlow: A Hybrid Approach for Calibrating Pronouns in Sentences
- Classification-Aware Neural Topic Model Combined With Interpretable Analysis -- For Conflict Classification
- Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering
- Providing Previously Unseen Users Fair Recommendations Using Variational Autoencoders
- CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation
- From DDMs to DNNs: Using process data and models of decision-making to improve human-AI interactions
- Evaluating Explanation Methods for Multivariate Time Series Classification
- On-the-Fly Guidance Training for Medical Image Registration
- Shared Lexical Items as Triggers of Code Switching
- Benchmarking the Generation of Fact Checking Explanations
- Where Would I Go Next? Large Language Models as Human Mobility Predictors
- Ensemble of Counterfactual Explainers
- Enhancing Psychological Counseling with Large Language Model: A Multifaceted Decision-Support System for Non-Professionals
- LTLf Best-Effort Synthesis in Nondeterministic Planning Domains
- LTLf Synthesis Under Environment Specifications for Reachability and Safety Properties
- Small Area Estimation with Random Forests and the LASSO
- Symbolic LTLf Best-Effort Synthesis
- Is visual explanation with Grad-CAM more reliable for deeper neural networks? a case study with automatic pneumothorax diagnosis
- A lightweight 3D dense facial landmark estimation model from position map data
- Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning
- Ontologies in Digital Twins: A Systematic Literature Review
- ABS-SGD: A Delayed Synchronous Stochastic Gradient Descent Algorithm with Adaptive Batch Size for Heterogeneous GPU Clusters
- On the improvement of model-predictive controllers
- The Anatomy of Conspirators: Unveiling Traits using a Comprehensive Twitter Dataset
- Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
- A Multimodal Visual Encoding Model Aided by Introducing Verbal Semantic Information
- Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images
- Abdominal Multi-Organ Segmentation Based on Feature Pyramid Network and Spatial Recurrent Neural Network
- CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs
- Biquality Learning: a Framework to Design Algorithms Dealing with Closed-Set Distribution Shifts
- AI-Based Facial Emotion Recognition Solutions for Education: A Study of Teacher-User and Other Categories
- Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein Simulators
- Stochastic Graph Bandit Learning with Side-Observations
- Probabilistic Dataset Reconstruction from Interpretable Models
- Sequential annotations for naturally-occurring HRI: first insights
- How Faithful are Self-Explainable GNNs?
- Group-Conditional Conformal Prediction via Quantile Regression Calibration for Crop and Weed Classification
- Can We Rely on AI?
- Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?
- Using deep learning for an automatic detection and classification of the vascular bifurcations along the Circle of Willis
- Learning to Upsample by Learning to Sample
- Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery
- LAMBO: Large AI Model Empowered Edge Intelligence
- Exploring Model Transferability through the Lens of Potential Energy
- Advancing Adversarial Robustness Through Adversarial Logit Update
- MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
- A Comprehensive Augmentation Framework for Anomaly Detection
- Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification
- AIoT-Based Drum Transcription Robot using Convolutional Neural Networks
- OEBench: Investigating Open Environment Challenges in Real-World Relational Data Streams
- A Consumer-tier based Visual-Brain Machine Interface for Augmented Reality Glasses Interactions
- Taxonomic Loss for Morphological Glossing of Low-Resource Languages
- Adapting Text-based Dialogue State Tracker for Spoken Dialogues
- iBARLE: imBalance-Aware Room Layout Estimation
- Pose-Free Neural Radiance Fields via Implicit Pose Regularization
- Large language models converge toward human-like concept organization
- R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
- Is it an i or an l: Test-time Adaptation of Text Line Recognition Models
- Improving Neural Ranking Models with Traditional IR Methods
- Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
- Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs
- Pyramid diffractive optical networks for unidirectional image magnification and demagnification
- TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification
- Directional Optimism for Safe Linear Bandits
- Few-Shot Object Detection via Synthetic Features with Optimal Transport
- PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
- Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints
- Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation
- WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification
- ICARUS: An Android-Based Unmanned Aerial Vehicle (UAV) Search and Rescue Eye in the Sky
- Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence
- Inferences on Mixing Probabilities and Ranking in Mixed-Membership Models
- Constructive Incremental Learning for Fault Diagnosis of Rolling Bearings with Ensemble Domain Adaptation
- Sub-universal variational circuits for combinatorial optimization problems
- Vision Grid Transformer for Document Layout Analysis
- Efficient labeling of solar flux evolution videos by a deep learning model
- LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks
- Distributed multi-agent target search and tracking with Gaussian process and reinforcement learning
- Uncovering the Hidden Cost of Model Compression
- CEFHRI: A Communication Efficient Federated Learning Framework for Recognizing Industrial Human-Robot Interaction
- Streaming Compression of Scientific Data via weak-SINDy
- Robust Open-Set Spoken Language Identification and the CU MultiLang Dataset
- Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
- Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation