Papers
Sat 26 Aug 2023
93 papers
- Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight TuningKnowledge distillation → Knowledge distillation for LLMs
- LMSanitator: Defending Prompt-Tuning Against Task-Agnostic BackdoorsLLM safety and security → Backdoor and data poisoning attacks
- Unsupervised Domain Adaptation via Domain-Adaptive DiffusionDiffusion models → Diffusion foundations and sampling
- The DiffuseStyleGesture+ entry to the GENEA Challenge 2023Diffusion models → Audio, speech and music
- Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMsDiffusion models → Video generation
- Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic ContentLLM safety and security → Jailbreaking
- DiffI2I: Efficient Diffusion Model for Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
- Autonomous Underwater Robotic System for Aquaculture Applications
- FAM: fast adaptive federated meta-learning
- Gaze-Informed Vision Transformers: Predicting Driving Decisions Under Uncertainty
- Multivariate time series classification with dual attention network
- Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
- Sparse Models for Machine Learning
- Differentiable Weight Masks for Domain Transfer
- Prior-guided Source-free Domain Adaptation for Human Pose Estimation
- Deep learning assisted robust detection techniques for a chipless RFID sensor tag
- A small vocabulary database of ultrasound image sequences of vocal tract dynamics
- A transport approach to sequential simulation-based inference
- Transfer Learning for Microstructure Segmentation with CS-UNet: A Hybrid Algorithm with Transformer and CNN Encoders
- Exploring Large Language Models for Knowledge Graph Completion
- A Wide Evaluation of ChatGPT on Affective Computing Tasks
- Exploring Human Crowd Patterns and Categorization in Video Footage for Enhanced Security and Surveillance using Computer Vision and Machine Learning
- A Two-Dimensional Deep Network for RF-based Drone Detection and Identification Towards Secure Coverage Extension
- Disjoint Pose and Shape for 3D Face Reconstruction
- Semi-Supervised Semantic Segmentation via Marginal Contextual Information
- Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
- FwdLLM: Efficient FedLLM using Forward Gradient
- Towards Real Time Egocentric Segment Captioning for The Blind and Visually Impaired in RGB-D Theatre Images
- Drug Interaction Vectors Neural Network: DrIVeNN
- Neural Implicit Morphing of Face Images
- ReFuSeg: Regularized Multi-Modal Fusion for Precise Brain Tumour Segmentation
- Applications of machine Learning to improve the efficiency and range of microbial biosynthesis: a review of state-of-art techniques
- Class Binarization to NeuroEvolution for Multiclass Classification
- Vision-Based Human Pose Estimation via Deep Learning: A Survey
- Graph Edit Distance Learning via Different Attention
- Brain-like representational straightening of natural movies in robust feedforward neural networks
- Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds
- Late Stopping: Avoiding Confidently Learning from Mislabeled Examples
- Bias in Unsupervised Anomaly Detection in Brain MRI
- Joint Gaze-Location and Gaze-Object Detection
- Beyond One-to-One: Rethinking the Referring Image Segmentation
- Effectively Heterogeneous Federated Learning: A Pairing and Split Learning Based Approach
- Solving Math Word Problem with Problem Type Classification
- Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Kolmogorov n-width Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel
- Price-Discrimination Game for Distributed Resource Management in Federated Learning
- Class-constrained t-SNE: Combining Data Features and Class Probabilities
- Deep Learning for Structure-Preserving Universal Stable Koopman-Inspired Embeddings for Nonlinear Canonical Hamiltonian Dynamics
- Evaluating Deep Learning Assisted Automated Aquaculture Net Pens Inspection Using ROV
- HoloPOCUS: Portable Mixed-Reality 3D Ultrasound Tracking, Reconstruction and Overlay
- A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
- Guaranteed Stable Quadratic Models and their applications in SINDy and Operator Inference
- Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning-Optimized Double-Ring Resonator
- Homological Convolutional Neural Networks
- Arbitrary Distributions Mapping via SyMOT-Flow: A Flow-based Approach Integrating Maximum Mean Discrepancy and Optimal Transport
- Point-Query Quadtree for Crowd Counting, Localization, and More
- Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery
- DM-VTON: Distilled Mobile Real-time Virtual Try-On
- DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series
- VIDES: Virtual Interior Design via Natural Language and Visual Guidance
- SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection
- Out-of-distribution detection using normalizing flows on the data manifold
- Handwritten image augmentation
- FFPN: Fourier Feature Pyramid Network for Ultrasound Image Segmentation
- ORES: Open-vocabulary Responsible Visual Synthesis
- Generalized Lightness Adaptation with Channel Selective Normalization
- Planning with Logical Graph-based Language Model for Instruction Generation
- Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation
- Large-scale gradient-based training of Mixtures of Factor Analyzers
- Self-Supervised Scalable Deep Compressed Sensing
- EditSum: A Retrieve-and-Edit Framework for Source Code Summarization
- Central Similarity Multi-View Hashing for Multimedia Retrieval
- Boosting Residual Networks with Group Knowledge
- Bengali Document Layout Analysis with Detectron2
- Unified Single-Stage Transformer Network for Efficient RGB-T Tracking
- How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context
- SamDSK: Combining Segment Anything Model with Domain-Specific Knowledge for Semi-Supervised Learning in Medical Image Segmentation
- i-Align: an interpretable knowledge graph alignment model
- ZC3: Zero-Shot Cross-Language Code Clone Detection
- Learning Efficient Representations for Image-Based Patent Retrieval
- PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation
- Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion
- On Philomatics and Psychomatics for Combining Philosophy and Psychology with Mathematics
- A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music
- MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree
- Learning variational autoencoders via MCMC speed measures
- Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models
- Dynamic Mode Decomposition for data-driven analysis and reduced-order modelling of ExB plasmas: II. dynamics forecasting
- Dynamic Mode Decomposition for data-driven analysis and reduced-order modelling of ExB plasmas: I. Extraction of spatiotemporally coherent patterns
- ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning
- Time-to-Pattern: Information-Theoretic Unsupervised Learning for Scalable Time Series Summarization
- A Computational Evaluation Framework for Singable Lyric Translation
- Uncovering Promises and Challenges of Federated Learning to Detect Cardiovascular Diseases: A Scoping Literature Review