Papers
Mon 15 May 2023
234 papers
- Interactive Fashion Content Generation Using LLMs and Latent Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Denoising Diffusion Models for Plug-and-Play Image RestorationDiffusion models → Inverse problems and image restoration
- Motion Question Answering via Modular Motion ProgramsLLM reasoning → Spatial and embodied reasoning
- Common Diffusion Noise Schedules and Sample Steps are FlawedDiffusion models → Diffusion foundations and sampling
- Laughing Matters: Introducing Laughing-Face Generation using Diffusion ModelsDiffusion models → Audio, speech and music
- Make-A-Protagonist: Generic Video Editing with An Ensemble of ExpertsDiffusion models → Video generation
- Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsKnowledge distillation → Detection and dense prediction distillation
- A Reproducible Extraction of Training Images from Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Improved baselines for vision-language pre-trainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- TESS: Text-to-Text Self-Conditioned Simplex DiffusionDiffusion models → Discrete and text diffusion
- Large Language Model Guided Tree-of-ThoughtLLM reasoning → Test-time compute and efficient thinking
- Risk stratification of malignant melanoma using neural networks
- Biomarker Discovery with Quantum Neural Networks: A Case-study in CTLA4-Activation Pathways
- Certification Labels for Trustworthy AI: Insights From an Empirical Mixed-Method Study
- Integrating Generative Artificial Intelligence in Intelligent Vehicle Systems
- Semantic Composition in Visually Grounded Language Models
- A Hybrid Semantic-Geometric Approach for Clutter-Resistant Floorplan Generation from Building Point Clouds
- Towards personalised music-therapy; a neurocomputational modelling perspective
- ChatGPT and the Labor Market: Unraveling the Effect of AI Discussions on Students' Earnings Expectations
- Neural information coding for efficient spike-based image denoising
- Critical Appraisal of Artificial Intelligence-Mediated Communication
- NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs
- The Effectiveness of a Dynamic Loss Function in Neural Network Based Automated Essay Scoring
- Emotion Recognition based on Psychological Components in Guided Narratives for Emotion Regulation
- Memorization for Good: Encryption with Autoregressive Language Models
- Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
- Evaluation Strategy of Time-series Anomaly Detection with Decay Function
- A Whisper transformer for audio captioning trained with synthetic captions and transfer learning
- OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
- Data Bias Management
- Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets
- FiMReSt: Finite Mixture of Multivariate Regulated Skew-t Kernels -- A Flexible Probabilistic Model for Multi-Clustered Data with Asymmetrically-Scattered Non-Gaussian Kernels
- An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions
- SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
- Capturing Humans' Mental Models of AI: An Item Response Theory Approach
- Bounded KRnet and its applications to density estimation and approximation
- SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification
- Learning Linear Embeddings for Non-Linear Network Dynamics with Koopman Message Passing
- Private Training Set Inspection in MLaaS
- Self-Supervised Pretraining on Paired Sequences of fMRI Data for Transfer Learning to Brain Decoding Tasks
- Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls
- Convex optimization over a probability simplex
- Scalable and Robust Tensor Ring Decomposition for Large-scale Data
- Adaptive Federated Pruning in Hierarchical Wireless Networks
- What Matters in Reinforcement Learning for Tractography
- Algorithmic Censoring in Dynamic Learning Systems
- AI in the Loop -- Functionalizing Fold Performance Disagreement to Monitor Automated Medical Image Segmentation Pipelines
- SKI to go Faster: Accelerating Toeplitz Neural Networks via Asymmetric Kernels
- Soft Prompt Decoding for Multilingual Dense Retrieval
- It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance
- DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applications
- Gaussian Process Port-Hamiltonian Systems: Bayesian Learning with Physics Prior
- The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn)
- Physics-enhanced Gaussian Process Variational Autoencoder
- Survey of Malware Analysis through Control Flow Graph using Machine Learning
- The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting
- LoViT: Long Video Transformer for Surgical Phase Recognition
- Federated Learning over Harmonized Data Silos
- Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and Feedback
- An assessment of measuring local levels of homelessness through proxy social media signals
- Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation
- A Causal Inference Framework for Leveraging External Controls in Hybrid Trials
- Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface
- One Forward is Enough for Neural Network Training via Likelihood Ratio Method
- Causal Analysis for Robust Interpretability of Neural Networks
- Image Matching by Bare Homography
- DopUS-Net: Quality-Aware Robotic Ultrasound Imaging based on Doppler Signal
- MIMEx: Intrinsic Rewards from Masked Input Modeling
- AF2-Mutation: Adversarial Sequence Mutations against AlphaFold2 on Protein Tertiary Structure Prediction
- Differential Convolutional Fuzzy Time Series Forecasting
- New methods for new data? An overview and illustration of quantitative inductive methods for HRM research
- Covariate-distance Weighted Regression (CWR): A Case Study for Estimation of House Prices
- Building Energy Efficiency through Advanced Regression Models and Metaheuristic Techniques for Sustainable Management
- CQE: A Comprehensive Quantity Extractor
- Python Tool for Visualizing Variability of Pareto Fronts over Multiple Runs
- MV-Map: Offboard HD-Map Generation with Multi-view Consistency
- Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs
- Small Models are Valuable Plug-ins for Large Language Models
- Privacy Auditing with One (1) Training Run
- Large Language Models are Zero-Shot Rankers for Recommender Systems
- RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
- Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
- A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes
- Attacking Perceptual Similarity Metrics
- PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India
- Learning Better Contrastive View from Radiologist's Gaze
- Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement
- Dragon-Alpha&cu32: A Java-based Tensor Computing Framework With its High-Performance CUDA Library
- Sentence Level Curriculum Learning for Improved Neural Conversational Models
- Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
- AutoRecon: Automated 3D Object Discovery and Reconstruction
- Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
- GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training
- Smoothness and monotonicity constraints for neural networks using ICEnet
- Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text
- Measuring Cross-Lingual Transferability of Multilingual Transformers on Sentence Classification
- Predictive Models from Quantum Computer Benchmarks
- Fair Information Spread on Social Networks with Community Structure
- Comparing Variation in Tokenizer Outputs Using a Series of Problematic and Challenging Biomedical Sentences
- TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation
All 234
- Question-Answering System Extracts Information on Injection Drug Use from Clinical Notes
- Transactional Python for Durable Machine Learning: Vision, Challenges, and Feasibility
- DA-LSTM: A Dynamic Drift-Adaptive Learning Framework for Interval Load Forecasting with LSTM Networks
- Physics Informed Token Transformer for Solving Partial Differential Equations
- Neural Oscillators are Universal
- A Matter of Annotation: An Empirical Study on In Situ and Self-Recall Activity Annotations from Wearable Sensors
- Fast and Attributed Change Detection on Dynamic Graphs with Density of States
- Automating privacy decisions -- where to draw the line?
- Integrating Uncertainty into Neural Network-based Speech Enhancement
- Refining Amortized Posterior Approximations using Gradient-Based Summary Statistics
- Knowledge Rumination for Pre-trained Language Models
- Learning More Discriminative Local Descriptors for Few-shot Learning
- M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
- Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks
- sustain.AI: a Recommender System to analyze Sustainability Reports
- Back Translation for Speech-to-text Translation Without Transcripts
- Understanding and Bridging the Modality Gap for Speech Translation
- Schema-adaptable Knowledge Graph Construction
- Recyclable Tuning for Continual Pre-training
- Continual Multimodal Knowledge Graph Construction
- Accelerated Algorithms for Nonlinear Matrix Decomposition with the ReLU function
- CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
- Natural Language Decomposition and Interpretation of Complex Utterances
- An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations
- aUToLights: A Robust Multi-Camera Traffic Light Detection and Tracking System
- MADDM: Multi-Advisor Dynamic Binary Decision-Making by Maximizing the Utility
- Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
- Towards Automated COVID-19 Presence and Severity Classification
- On the connections between optimization algorithms, Lyapunov functions, and differential equations: theory and insights
- Meta-models for transfer learning in source localisation
- Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering
- Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings
- Topological Interpretability for Deep-Learning
- Double-Weighting for Covariate Shift Adaptation
- AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning
- Text2Gender: A Deep Learning Architecture for Analysis of Blogger's Age and Gender
- A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs
- Non-Separable Multi-Dimensional Network Flows for Visual Computing
- Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models
- Mastering the exploration-exploitation trade-off in Bayesian Optimization
- GeNAS: Neural Architecture Search with Better Generalization
- Evaluating Splitting Approaches in the Context of Student Dropout Prediction
- Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application
- DarkBERT: A Language Model for the Dark Side of the Internet
- Improving Customer Experience in Call Centers with Intelligent Customer-Agent Pairing
- NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
- Toward Moir'e-Free and Detail-Preserving Demosaicking
- Fast Inference of Tree Ensembles on ARM Devices
- A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
- Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
- NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
- Designing Discontinuities
- Distilling Knowledge for Short-to-Long Term Trajectory Prediction
- Curvature-Aware Training for Coordinate Networks
- Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation
- Towards Visual Saliency Explanations of Face Verification
- Quantum Neural Network for Quantum Neural Computing
- SRRM: Semantic Region Relation Model for Indoor Scene Recognition
- Kernel-based Joint Independence Tests for Multivariate Stationary and Non-stationary Time Series
- Measuring Consistency in Text-based Financial Forecasting Models
- Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs
- Beqi: Revitalize the Senegalese Wolof Language with a Robust Spelling Corrector
- Generative Adversarial Networks for Spatio-Spectral Compression of Hyperspectral Images
- SAT-Based PAC Learning of Description Logic Concepts
- Fast Traversability Estimation for Wild Visual Navigation
- Component-aware anomaly detection framework for adjustable and logical industrial visual inspection
- A Knowledge Graph Perspective on Supply Chain Resilience
- FLARE: Detection and Mitigation of Concept Drift for Federated Learning based IoT Deployments
- A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization
- MeeQA: Natural Questions in Meeting Transcripts
- Label Smoothing is Robustification against Model Misspecification
- Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks
- Creative Data Generation: A Review Focusing on Text and Poetry
- Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
- Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages
- Task-Oriented Communication Design at Scale
- A Crosslingual Investigation of Conceptualization in 1335 Languages
- Shared and Private Information Learning in Multimodal Sentiment Analysis with Deep Modal Alignment and Self-supervised Multi-Task Learning
- Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives
- Convergence Analysis of Mean Shift
- Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation
- Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
- MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation
- Document Understanding Dataset and Evaluation (DUDE)
- Tracking Progress in Multi-Agent Path Finding
- Exploiting Frequency Spectrum of Adversarial Images for General Robustness
- EMBRACE: Evaluation and Modifications for Boosting RACE
- Legal Extractive Summarization of U.S. Court Opinions
- Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
- Online Sequence Clustering Algorithm for Video Trajectory Analysis
- Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasing
- What's the Meaning of Superhuman Performance in Today's NLU?
- Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward
- SB-VQA: A Stack-Based Video Quality Assessment Framework for Video Enhancement
- Theoretical Analysis of Inductive Biases in Deep Convolutional Networks
- MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation
- Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study
- Edit As You Wish: Video Caption Editing with Multi-grained User Control
- PLIP: Language-Image Pre-training for Person Representation Learning
- The Impact of Incumbent/Opposition Status and Ideological Similitude on Emotions in Political Manifestos
- Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
- Text Classification via Large Language Models
- Hierarchical Aligned Multimodal Learning for NER on Tweet Posts
- SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation
- Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration
- CLRerNet: Improving Confidence of Lane Detection with LaneIoU
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
- Quadratic Functional Encryption for Secure Training in Vertical Federated Learning
- Fast and Efficient Matching Algorithm with Deadline Instances
- Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension
- Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension
- KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering
- Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation
- Finite Expression Methods for Discovering Physical Laws from Data
- Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology
- Neural Boltzmann Machines
- Inverse Rendering of Translucent Objects using Physical and Neural Renderers
- FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning
- Screentone-Aware Manga Super-Resolution Using DeepLearning
- C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
- Model Checking Strategies from Synthesis Over Finite Traces
- CMSG Cross-Media Semantic-Graph Feature Matching Algorithm for Autonomous Vehicle Relocalization
- SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction
- Deep-Unfolding for Next-Generation Transceivers
- t-RAIN: Robust generalization under weather-aliasing label shift attacks
- "Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion
- Symbol tuning improves in-context learning in language models
- Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild
- CLImage: Human-Annotated Datasets for Complementary-Label Learning
- Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
- SWAN: A Generic Framework for Auditing Textual Conversational Systems
- A Language Model of Java Methods with Train/Test Deduplication
- Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
- From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models