Papers
Sun 7 May 2023
90 papers
- Pick your Poison: Undetectability versus Robustness in Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
- A Variational Perspective on Solving Inverse Problems with Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought PromptingLLM reasoning → Prompting and chain-of-thought reasoning
- Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningDiffusion models → Robustness, privacy and adversarial aspects +1
- X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign LanguagesSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
- Multi-agent Continual Coordination via Progressive Task Contextualization
- Robust Multi-agent Communication via Multi-view Message Certification
- Perception, performance, and detectability of conversational artificial intelligence across 32 university courses
- Optimizing National Security Strategies through LLM-Driven Artificial Intelligence Integration
- Model-Contrastive Federated Domain Adaptation
- Extracting Blockchain Concepts from Text
- Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup
- K-SpecPart: Supervised embedding algorithms and cut overlay for improved hypergraph partitioning
- Interpretable multimodal sentiment analysis based on textual modality descriptions by using large-scale language models
- Leveraging Synthetic Targets for Machine Translation
- Neurosymbolic Artificial Intelligence (NSAI) based Algorithm for predicting the Impact Strength of Additive Manufactured Polylactic Acid (PLA) Specimens
- CIT-EmotionNet: CNN Interactive Transformer Network for EEG Emotion Recognition
- Localization of Ultra-dense Emitters with Neural Networks
- Efficient pattern-based anomaly detection in a network of multivariate devices
- Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models
- HybridNet: Dual-Branch Fusion of Geometrical and Topological Views for VLSI Congestion Prediction
- Generative Pretrained Autoregressive Transformer Graph Neural Network applied to the Analysis and Discovery of Novel Proteins
- Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
- Disentangled Multi-Fidelity Deep Bayesian Active Learning
- Inferring Local Structure from Pairwise Correlations
- Data Efficient Training with Imbalanced Label Sample Distribution for Fashion Detection
- Spatiotemporally Consistent HDR Indoor Lighting Estimation
- LatinCy: Synthetic Trained Pipelines for Latin NLP
- A Generalized Framework for Predictive Clustering and Optimization
- Truncating Trajectories in Monte Carlo Reinforcement Learning
- ParlayANN: Scalable and Deterministic Parallel Graph-Based Approximate Nearest Neighbor Search Algorithms
- Quantifying Consistency and Information Loss for Causal Abstraction Learning
- Stanford MLab at SemEval-2023 Task 10: Exploring GloVe- and Transformer-Based Methods for the Explainable Detection of Online Sexism
- Interpreting Training Aspects of Deep-Learned Error-Correcting Codes
- Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
- Empowering Language Model with Guided Knowledge Fusion for Biomedical Document Re-ranking
- Fast parameter estimation of Generalized Extreme Value distribution using Neural Networks
- Classification Tree Pruning Under Covariate Shift
- Living in a Material World: Learning Material Properties from Full-Waveform Flash Lidar Data for Semantic Segmentation
- Segmentation of the veterinary cytological images for fast neoplastic tumors diagnosis
- FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering
- Neural Voting Field for Camera-Space 3D Hand Pose Estimation
- Lightweight Convolution Transformer for Cross-patient Seizure Detection in Multi-channel EEG Signals
- Unified Demonstration Retriever for In-Context Learning
- A Framework for Characterizing Novel Environment Transformations in General Environments
- The Human-or-Machine Matter: Turing-Inspired Reflections on an Everyday Issue
- Poses as Queries: Image-to-LiDAR Map Localization with Transformers
- HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction
- HashCC: Lightweight Method to Improve the Quality of the Camera-less NeRF Scene Generation
- PELE scores: Pelvic X-ray Landmark Detection by Pelvis Extraction and Enhancement
- Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion
- Learning from synthetic data generated with GRADE
- Analysing Multiscale Clusterings with Persistent Homology
- Boosting Distributed Machine Learning Training Through Loss-tolerant Transmission Protocol
- AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
- RSC-VAE: Recoding Semantic Consistency Based VAE for One-Class Novelty Detection
- Dual Residual Attention Network for Image Denoising
- MS-NeRF: Multi-Space Neural Radiance Fields
- Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization
- An Investigation on Word Embedding Offset Clustering as Relationship Classification
- Estimation of control area in badminton doubles with pose information from top and back view drone videos
- Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
- Instance-Variant Loss with Gaussian RBF Kernel for 3D Cross-modal Retriveal
- Opening the TAR Black Box: Developing an Interpretable System for eDiscovery Using the Fuzzy ARTMAP Neural Network
- RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration
- CatFLW: Cat Facial Landmarks in the Wild Dataset
- Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification
- Design, Implementation and Evaluation of an External Pose-Tracking System for Underwater Cameras
- LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
- Visual Causal Scene Refinement for Video Question Answering
- Influence of Swarm Intelligence in Data Clustering Mechanisms
- PiML Toolbox for Interpretable Machine Learning Model Development and Diagnostics
- Robust Image Ordinal Regression with Controllable Image Generation
- Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network
- RATs-NAS: Redirection of Adjacent Trails on GCN for Neural Architecture Search
- Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving
- Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning
- MrTF: Model Refinery for Transductive Federated Learning
- Cross-Modal Retrieval for Motion and Text via DropTriple Loss
- Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization
- OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese
- Shall We Trust All Relational Tuples by Open Information Extraction? A Study on Speculation Detection
- Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
- MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents
- YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification
- UIT-OpenViIC: A Novel Benchmark for Evaluating Image Captioning in Vietnamese
- Camera-Based HRV Prediction for Remote Learning Environments
- SynthMix: Mixing up Aligned Synthesis for Medical Cross-Modality Domain Adaptation
- Score: A Rule Engine for the Scone Knowledge Base System
- Context-Aware Chart Element Detection