Papers
Wed 21 Jun 2023
191 papers
- OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text DocumentsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Understanding Social Reasoning in Language Models with Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like BiasesLLM reasoning → Reasoning benchmarks and evaluation
- SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Semi-Implicit Denoising Diffusion Models (SIDDMs)Diffusion models → Diffusion foundations and sampling
- VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolutionMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
- DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D GenerationDiffusion models → 3D, point cloud and scene generation
- One-shot Imitation Learning via Interaction WarpingOffline RL and imitation learning from data → Robot manipulation imitation learning
- Diffusion Posterior Sampling for Informed Single-Channel DereverberationDiffusion models → Audio, speech and music
- Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge ResourceEfficient LLM inference and serving → Early exit and edge inference
- OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and DialogueMultimodal LLMs / vision-language models → Medical vision-language models
- DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic ImagesDiffusion models → Inverse problems and image restoration
- HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading ComprehensionLLM reasoning → Knowledge- and tool-augmented reasoning
- Ambigram Generation by A Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- TauPETGen: Text-Conditional Tau PET Image Synthesis Based on Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
- FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair
- Subgraph Stationary Hardware-Software Inference Co-Design
- ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
- Testing of Detection Tools for AI-Generated Text
- Utilizing Natural Language Processing for Automated Assessment of Classroom Discussion
- Towards Enriched Controllability for Educational Question Generation
- Evaluating the overall sensitivity of saliency-based explanation methods
- Estimating the Value of Evidence-Based Decision Making
- GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks
- Key Frame Extraction with Attention Based Deep Neural Networks
- A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision
- Resources and Evaluations for Multi-Distribution Dense Information Retrieval
- Constant Memory Attention Block
- A Hierarchical Approach to exploiting Multiple Datasets from TalkBank
- State-wise Constrained Policy Optimization
- Rapid building damage assessment workflow: An implementation for the 2023 Rolling Fork, Mississippi tornado event
- ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews
- Hierarchical Neural Simulation-Based Inference Over Event Ensembles
- Adversarial Training with Generated Data in High-Dimensional Regression: An Asymptotic Study
- Morphological Inflection with Phonological Features
- NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning
- An efficient and straightforward online quantization method for a data stream through remove-birth updating
- Uniqueness of Iris Pattern Based on AR Model
- Local 3D Editing via 3D Distillation of CLIP Knowledge
- Neural Spectro-polarimetric Fields
- Exploring the Role of Audio in Video Captioning
- Improving Long-Horizon Imitation Through Instruction Prediction
- On Evaluation of Document Classification using RVL-CDIP
- Finite-time Lyapunov exponents of deep neural networks
- DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching
- Neural Multigrid Memory For Computational Fluid Dynamics
- Memory-Query Tradeoffs for Randomized Convex Optimization
- Structured Learning in Time-dependent Cox Models
- LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network
- FFCV: Accelerating Training by Removing Data Bottlenecks
- Comparative Analysis of Segment Anything Model and U-Net for Breast Tumor Detection in Ultrasound and Mammography Images
- Joint Prompt Optimization of Stacked LLMs using Variational Inference
- Investigating Poor Performance Regions of Black Boxes: LIME-based Exploration in Sepsis Detection
- Empirical Risk Minimization with Shuffled SGD: A Primal-Dual Perspective and Improved Bounds
- Density Uncertainty Layers for Reliable Uncertainty Estimation
- Verifying Global Neural Network Specifications using Hyperproperties
- Misinformation as Information Pollution
- Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
- Precision psychiatry: predicting predictability
- On-orbit model training for satellite imagery with label proportions
- Deep Dynamic Epidemiological Modelling for COVID-19 Forecasting in Multi-level Districts
- Pushing the Limits of Machine Design: Automated CPU Design with AI
- Learning Conditional Instrumental Variable Representation for Causal Effect Estimation
- Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase
- LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
- Addressing Discontinuous Root-Finding for Subsequent Differentiability in Machine Learning, Inverse Problems, and Control
- Timely Asynchronous Hierarchical Federated Learning: Age of Convergence
- Multi-Task Consistency for Active Learning
- Improving Software Requirements Prioritization through the Lens of Constraint Solving
- Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling
- mathbfmathbbEFWI: Multi-parameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
- Probing the limit of hydrologic predictability with the Transformer network
- Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
- On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation
- Geometric Algorithms for k-NN Poisoning
- M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks
- Optimistic Active Exploration of Dynamical Systems
- PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning
- Attention Hybrid Variational Net for Accelerated MRI Reconstruction
- Sigma-point Kalman Filter with Nonlinear Unknown Input Estimation via Optimization and Data-driven Approach for Dynamic Systems
- Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
- An efficient, provably optimal algorithm for the 0-1 loss linear classification problem
- Geometric Pooling: maintaining more useful information
- ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
- Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image Representation
- Iterated Piecewise Affine (IPA) Approximation for Language Modeling
- Introspective Action Advising for Interpretable Transfer Learning
- Medical ministrations through web scraping
- Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
- StarVQA+: Co-training Space-Time Attention for Video Quality Assessment
- Resilient Sparse Array Radar with the Aid of Deep Learning
- Online Resource Allocation with Convex-set Machine-Learned Advice
- SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings
- Wildfire Detection Via Transfer Learning: A Survey
- From structure mining to unsupervised exploration of atomic octahedral networks
- A Finite Expression Method for Solving High-Dimensional Committor Problems
- Combining multi-spectral data with statistical and deep-learning models for improved exoplanet detection in direct imaging at high contrast
- Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation
- Solving and Generating NPR Sunday Puzzles with Large Language Models
All 191
- GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
- Knowledge-based Multimodal Music Similarity
- Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
- Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
- Inter-Instance Similarity Modeling for Contrastive Learning
- Concurrent ischemic lesion age estimation and segmentation of CT brain using a Transformer-based network
- Predicting protein variants with equivariant graph neural networks
- Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
- Lumbar spine segmentation in MR images: a dataset and a public benchmark
- Automated Machine Learning for Remaining Useful Life Predictions
- More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity
- Limits for Learning with Language Models
- MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates
- Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI
- Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes
- Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks
- Split Learning in 6G Edge Networks
- Quantifying lottery tickets under label noise: accuracy, calibration, and complexity
- Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation
- Facial Expression Re-targeting from a Single Character
- Feature Interactions Reveal Linguistic Structure in Language Models
- Mixture Encoder for Joint Speech Separation and Recognition
- Post-hoc Selection of Pareto-Optimal Solutions in Search and Recommendation
- Adversarial Attacks Neutralization via Data Set Randomization
- Fast Segment Anything
- Joint Dense-Point Representation for Contour-Aware Graph Segmentation
- DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
- Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario
- Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification
- Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals
- Synaptic metaplasticity with multi-level memristive devices
- Spatial Heterophily Aware Graph Neural Networks
- Machine Learning Based Compensation for Inconsistencies in Knitted Force Sensors
- Explaining human body responses in random vibration: Effect of motion direction, sitting posture, and anthropometry
- Lightweight wood panel defect detection method incorporating attention mechanism and feature fusion network
- A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking
- ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining
- Mass-Producing Failures of Multimodal Systems with Language Models
- Efficient ResNets: Residual Network Design
- MSW-Transformer: Multi-Scale Shifted Windows Transformer Networks for 12-Lead ECG Classification
- Understanding human mobility patterns in Chicago: an analysis of taxi data using clustering techniques
- Edge Devices Inference Performance Comparison
- Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
- Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints
- An Efficient Virtual Data Generation Method for Reducing Communication in Federated Learning
- What Constitutes Good Contrastive Learning in Time-Series Forecasting?
- FLGo: A Fully Customizable Federated Learning Platform
- Accelerating Multiframe Blind Deconvolution via Deep Learning
- Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers
- NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN
- Task-Robust Pre-Training for Worst-Case Downstream Adaptation
- Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions
- EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
- Beyond Learned Metadata-based Raw Image Reconstruction
- Chili Pepper Disease Diagnosis via Image Reconstruction Using GrabCut and Generative Adversarial Serial Autoencoder
- A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging
- Analyzing Font Style Usage and Contextual Factors in Real Images
- Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
- Residual-Based Error Corrector Operator to Enhance Accuracy and Reliability of Neural Operator Surrogates of Nonlinear Variational Boundary-Value Problems
- Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes
- Sample Attackability in Natural Language Adversarial Attacks
- Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
- Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection
- Quantifying Node-based Core Resilience
- Distributed Random Reshuffling Methods with Improved Convergence
- Self-Tuning Self-Supervised Image Anomaly Detection
- Comparative analysis of various web crawler algorithms
- Continual Learners are Incremental Model Generalizers
- Visual-Aware Text-to-Speech
- A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing
- 3HAN: A Deep Neural Network for Fake News Detection
- Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection
- Learning Homogenization for Elliptic Operators
- An Overview of Catastrophic AI Risks
- Generalizable Metric Network for Cross-domain Person Re-identification
- Physics-constrained Attack against Convolution-based Human Motion Prediction
- Training Transformers with 4-bit Integers
- Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity
- Evaluation of Popular XAI Applied to Clinical Prediction Models: Can They be Trusted?
- Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture
- Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI
- Interactive Molecular Discovery with Natural Language
- Universal adversarial perturbations for multiple classification tasks with quantum classifiers
- AdCraft: An Advanced Reinforcement Learning Benchmark Environment for Search Engine Marketing Optimization
- RSMT: Real-time Stylized Motion Transition for Characters
- Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning
- Sampling Individually-Fair Rankings that are Always Group Fair
- Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features
- TADIL: Task-Agnostic Domain-Incremental Learning through Task-ID Inference using Transformer Nearest-Centroid Embeddings
- On the Optimal Bounds for Noisy Computing
- Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity