Papers
Sun 6 Aug 2023
86 papers
- Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiesLLM reasoning → Test-time compute and efficient thinking
- Photorealistic and Identity-Preserving Image-Based Emotion Manipulation with Latent Diffusion ModelsDiffusion models → Audio, speech and music
- Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
- SAPIEN: Affective Virtual Agents Powered by Large Language ModelsLLM agents and tool use → Social simulation and multi-agent debate
- Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D RepresentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Comparative Analysis of Epileptic Seizure Prediction: Exploring Diverse Pre-Processing Techniques and Machine Learning Models
- A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems
- Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
- Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables
- Why Linguistics Will Thrive in the 21st Century: A Reply to Piantadosi (2023)
- Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
- Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
- The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning
- Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits
- Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series
- Communication-Free Distributed GNN Training with Vertex Cut
- Microvasculature Segmentation in Human BioMolecular Atlas Program (HuBMAP)
- Source-free Domain Adaptive Human Pose Estimation
- Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
- Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities
- Understanding Biometric Entropy and Iris Capacity: Avoiding Identity Collisions on National Scales
- A Lightweight Method for Modeling Confidence in Recommendations with Learned Beta Distributions
- VN-Solver: Vision-based Neural Solver for Combinatorial Optimization over Graphs
- Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection
- Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
- Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing
- Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
- Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration
- Detection of Anomalies in Multivariate Time Series Using Ensemble Techniques
- Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
- FireFly A Synthetic Dataset for Ember Detection in Wildfire
- CGBA: Curvature-aware Geometric Black-box Attack
- Precise Benchmarking of Explainable AI Attribution Methods
- AI-GOMS: Large AI-Driven Global Ocean Modeling System
- "We care": Improving Code Mixed Speech Emotion Recognition in Customer-Care Conversations
- Towards socially-competent and culturally-adaptive artificial agents Expressive order, interactional disruptions and recovery strategies
- Self-Directed Linear Classification
- Unfolded proximal neural networks for robust image Gaussian denoising
- Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation
- Iterative Magnitude Pruning as a Renormalisation Group: A Study in The Context of The Lottery Ticket Hypothesis
- "Kurosawa": A Script Writer's Assistant
- NNVISR: Bring Neural Network Video Interpolation and Super Resolution into Video Processing Framework
- PromptSum: Parameter-Efficient Controllable Abstractive Summarization
- SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation
- Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data
- Improving Domain-Specific Retrieval by NLI Fine-Tuning
- Learning-Rate-Free Learning: Dissecting D-Adaptation and Probabilistic Line Search
- LARCH: Large Language Model-based Automatic Readme Creation with Heuristics
- System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator
- Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
- Gradient Coding with Iterative Block Leverage Score Sampling
- Control-aware echo state networks (Ca-ESN) for the suppression of extreme events
- ECT: Fine-grained Edge Detection with Learned Cause Tokens
- Visualization of Extremely Sparse Contingency Table by Taxicab Correspondence Analysis: A Case Study of Textual Data
- Study for Performance of MobileNetV1 and MobileNetV2 Based on Breast Cancer
- M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition
- InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild
- TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment
- Language-based Photo Color Adjustment for Graphic Designs
- TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties
- Multi-scale Alternated Attention Transformer for Generalized Stereo Matching
- Prototypes-oriented Transductive Few-shot Learning with Conditional Transport
- Machine learning methods for the search for L&T brown dwarfs in the data of modern sky surveys
- 3D-EX : A Unified Dataset of Definitions and Dictionary Examples
- Learning Fine-Grained Features for Pixel-wise Video Correspondences
- Machine Learning for Infectious Disease Risk Prediction: A Survey
- Serverless Federated AUPRC Optimization for Multi-Party Collaborative Imbalanced Data Mining
- FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information
- Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement
- Pre-Trained Large Language Models for Industrial Control
- Causal Disentanglement Hidden Markov Model for Fault Diagnosis
- Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation
- All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation
- Recurrent Spike-based Image Restoration under General Illumination
- Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesis
- High-Resolution Vision Transformers for Pixel-Level Identification of Structural Components and Damage
- MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation
- Deep Polar Codes
- Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
- Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet
- StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning
- Novel Class Discovery for Long-tailed Recognition
- Introducing Feature Attention Module on Convolutional Neural Network for Diabetic Retinopathy Detection
- Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection
- Spanish Pre-trained BERT Model and Evaluation Data