Papers
Sat 27 Jul 2024
86 papers
- AgentPeerTalk: Empowering Students through Agentic-AI-Driven Discernment of Bullying and Joking in Peer Interactions in SchoolsLLM agents and tool use → Educational agents and math problem solving
- Inverse Problems with Diffusion Models: A MAP Estimation PerspectiveDiffusion models → Inverse problems and image restoration
- GP-VLS: A general-purpose vision language model for surgeryMultimodal LLMs / vision-language models → Medical vision-language models
- Large Language Models for Human-like Autonomous Driving: A SurveyEnd-to-end autonomous driving → Large language models for driving
- Mamba? Catch The Hype Or Rethink What Really Helps for Image RegistrationState-space sequence models (S4, Mamba) → Vision Mamba backbones
- Mamba-UIE: Enhancing Underwater Images with Physical Model ConstraintState-space sequence models (S4, Mamba) → Mamba for image restoration
- Radio Frequency Signal based Human Silhouette Segmentation: A Sequential Diffusion ApproachDiffusion models → Medical imaging and segmentation
- Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-AttentionsDiffusion models → Video generation
- On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMsMechanistic interpretability → Knowledge and representations inside LLMs
- LLaVA-Read: Enhancing Reading Ability of Multimodal Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- On the benefits of pixel-based hierarchical policies for task generalizationDeep reinforcement learning methods → Deep RL algorithms and representations
- Using deep learning to enhance electronic service quality: Application to real estate websites
- Graph Residual based Method for Molecular Property Prediction
- LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
- Optimization of Energy Consumption Forecasting in Puno using Parallel Computing and ARIMA Models: An Innovative Approach to Big Data Processing
- LawLLM: Law Large Language Model for the US Legal System
- From pixels to planning: scale-free active inference
- Formalization of Dialogue in the Decision Support System of Dr. Watson Type
- AccessShare: Co-designing Data Access and Sharing with Blind People
- Predicting T-Cell Receptor Specificity
- Polynomial Regression as a Task for Understanding In-context Learning Through Finetuning and Alignment
- Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
- Parameter-Efficient Fine-Tuning via Circular Convolution
- Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification on the DAIC-WOZ
- Semantic Communication Enhanced by Knowledge Graph Representation Learning
- A Semi-supervised Fake News Detection using Sentiment Encoding and LSTM with Self-Attention
- Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
- Polyp segmentation in colonoscopy images using DeepLabV3++
- Accounting for plasticity: An extension of inelastic Constitutive Artificial Neural Networks
- Investigating Critical Period Effects in Language Acquisition through Neural Language Models
- Deep Learning Based Crime Prediction Models: Experiments and Analysis
- MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo
- WindsorML: High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics
- AResNet-ViT: A Hybrid CNN-Transformer Network for Benign and Malignant Breast Nodule Classification in Ultrasound Images
- Can Modifying Data Address Graph Domain Adaptation?
- Ensembling convolutional neural networks for human skin segmentation
- Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector
- Symmetrical Joint Learning Support-query Prototypes for Few-shot Segmentation
- IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity Alignment
- CoLiDR: Concept Learning using Aggregated Disentangled Representations
- The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints
- Multi-Modal CLIP-Informed Protein Editing
- Rethinking Attention Module Design for Point Cloud Analysis
- Bayesian meta learning for trustworthy uncertainty quantification
- On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps
- Optimizing Synthetic Data for Enhanced Pancreatic Tumor Segmentation
- A self-supervised and adversarial approach to hyperspectral demosaicking and RGB reconstruction in surgical imaging
- Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network
- A Bayesian Approach Toward Robust Multidimensional Ellipsoid-Specific Fitting
- Interactive Learning in Computer Science Education Supported by a Discord Chatbot
- Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation
- Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications
- Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction
- Comprehensive Survey of Complex-Valued Neural Networks: Insights into Backpropagation and Activation Functions
- Stochastic Parrots or ICU Experts? Large Language Models in Critical Care Medicine: A Scoping Review
- Nonlinear spectral analysis extracts harmonics from land-atmosphere fluxes
- Approximate learning of parsimonious Bayesian context trees
- Ordered Momentum for Asynchronous SGD
- Alleviating Over-Smoothing via Aggregation over Compact Manifolds
- Magic3DSketch: Create Colorful 3D Models From Sketch-Based 3D Modeling Guided by Text and Language-Image Pre-Training
- EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
- Towards the Terminator Economy: Assessing Job Exposure to AI through LLMs
- Clean-Label Physical Backdoor Attacks with Data Distillation
- Long Range Switching Time Series Prediction via State Space Model
- A simulation study of cluster search algorithms in data set generated by Gaussian mixture models
- Towards the Dynamics of a DNN Learning Symbolic Interactions
- Why Misinformation is Created? Detecting them by Integrating Intent Features
- A collaborative ensemble construction method for federated random forest
- Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
- Efficiently improving key weather variables forecasting by performing the guided iterative prediction in latent space
- Channel Boosted CNN-Transformer-based Multi-Level and Multi-Scale Nuclei Segmentation
- Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery
- Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks
- Data Processing Techniques for Modern Multimodal Models
- Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection
- Reducing Spurious Correlation for Federated Domain Generalization
- FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts
- Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
- Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification
- Decomposing heterogeneous dynamical systems with graph neural networks
- Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble
- Debiased Graph Poisoning Attack via Contrastive Surrogate Objective
- RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry
- A Survey of Malware Detection Using Deep Learning
- Few-Shot Medical Image Segmentation with Large Kernel Attention
- Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration