Papers
Wed 3 May 2023
198 papers
- Lift Yourself Up: Retrieval-augmented Text Generation with Self MemoryRetrieval-augmented generation → RAG pipeline design and evaluation
- Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
- Defending against Insertion-based Textual Backdoor Attacks via AttributionLLM safety and security → Backdoor and data poisoning attacks
- Visual Chain of Thought: Bridging Logical Gaps with Multimodal InfillingsLLM reasoning → Multimodal reasoning
- Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data RegimeMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex TextLLM reasoning → Multimodal reasoning +1
- Transforming Visual Scene Graphs to Image CaptionsMixture-of-experts → Multimodal MoE models
- Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic CapacityMixture-of-experts → MoE large language models
- Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual LearningLLM reasoning → Reasoning benchmarks and evaluation
- Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight FactorizationKnowledge distillation → Distillation for spiking neural networks
- A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target TrainingKnowledge distillation → Knowledge distillation for LLMs
- Improving Contrastive Learning of Sentence Embeddings from AI FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Robust Multi-bit Natural Language Watermarking through Invariant FeaturesLLM safety and security → Watermarking generated content and models
- SCOTT: Self-Consistent Chain-of-Thought DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
- Multimodal Data Augmentation for Image Captioning using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Importance of equivariant and invariant symmetries for fluid flow modeling
- Judgments of research co-created by generative AI: experimental evidence
- The Beauty or the Beast: Which Aspect of Synthetic Medical Images Deserves Our Focus?
- Codesign of Edge Intelligence and Automated Guided Vehicle Control
- Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systems
- Optimization- and AI-based approaches to academic quality quantification for transparent academic recruitment: part 1-model development
- A Cross-Frequency Protective Emblem: Protective Options for Medical Units and Wounded Soldiers in the Context of (fully) Autonomous Warfare
- DELTA: Dynamic Embedding Learning with Truncated Conscious Attention for CTR Prediction
- Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems
- ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs
- CiteCaseLAW: Citation Worthiness Detection in Caselaw for Legal Assistive Writing
- Explore the difficulty of words and its influential attributes based on the Wordle game
- Training Natural Language Processing Models on Encrypted Text for Enhanced Privacy
- New Adversarial Image Detection Based on Sentiment Analysis
- Towards Invertible Semantic-Preserving Embeddings of Logical Formulae
- Plug-and-Play Multilingual Few-shot Spoken Words Recognition
- FastAMI -- a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics
- Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
- Maximizing Submodular Functions for Recommendation in the Presence of Biases
- Local Optima Correlation Assisted Adaptive Operator Selection
- Shap-E: Generating Conditional 3D Implicit Functions
- Tensorizing flows: a tool for variational inference
- Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge
- Quantifying the Dissimilarity of Texts
- Streaming PCA for Markovian Data
- Bayesian Safety Validation for Failure Probability Estimation of Black-Box Systems
- Tackling Universal Properties of Minimal Trap Spaces of Boolean Networks
- Reward Teaching for Federated Multi-armed Bandits
- Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs
- evaluating bert and parsbert for analyzing persian advertisement data
- Backdoor Learning on Sequence to Sequence Models
- PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer
- GAMIVAL: Video Quality Prediction on Mobile Cloud Gaming Content
- Normalizing flows for lattice gauge theory in arbitrary space-time dimension
- Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathology
- Learning-based Relational Object Matching Across Views
- Widespread Increases in Future Wildfire Risk to Global Forest Carbon Offset Projects Revealed by Explainable AI
- Can Feature Engineering Help Quantum Machine Learning for Malware Detection?
- Approximating CKY with Transformers
- SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning
- On the Security Risks of Knowledge Graph Reasoning
- Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations
- Discovering Communication Pattern Shifts in Large-Scale Labeled Networks using Encoder Embedding and Vertex Dynamics
- MaskSearch: Querying Image Masks at Scale
- A Novel Plagiarism Detection Approach Combining BERT-based Word Embedding, Attention-based LSTMs and an Improved Differential Evolution Algorithm
- Efficient estimation of weighted cumulative treatment effects by double/debiased machine learning
- Metric Tools for Sensitivity Analysis with Applications to Neural Networks
- PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives
- Entity Tracking in Language Models
- Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?
- Using Language Models on Low-end Hardware
- Structures of Neural Network Effective Theories
- Robot Goes Fishing: Rapid, High-Resolution Biological Hotspot Mapping in Coral Reefs with Vision-Guided Autonomous Underwater Vehicles
- Cultivated Wildness: Technodiversity and Wildness in Machines
- The Future of Artificial Intelligence (AI) and Machine Learning (ML) in Landscape Design: A Case Study in Coastal Virginia, USA
- Cybernetic Environment: A Historical Reflection on System, Design, and Machine Intelligence
- Sex Detection in the Early Stage of Fertilized Chicken Eggs via Image Recognition
- Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition
- Entity-Based Evaluation of Political Bias in Automatic Summarization
- Wavelet Coherence Of Total Solar Irradiance and Atlantic Climate
- AG3D: Learning to Generate 3D Avatars from 2D Image Collections
- Real-Time Radiance Fields for Single-Image Portrait View Synthesis
- CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
- Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Taste
- Calibrated Explanations: with Uncertainty Information and Counterfactuals
- New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
- Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
- Evaluating the Efficacy of Length-Controllable Machine Translation
- Dynamic Sparse Training with Structured Sparsity
- DynamicStereo: Consistent Dynamic Depth from Stereo Videos
- Iranian License Plate Recognition Using a Reliable Deep Learning Approach
- Evaluating BERT-based Scientific Relation Classifiers for Scholarly Knowledge Graph Construction on Digital Library Collections
- Distributed Leader Follower Formation Control of Mobile Robots based on Bioinspired Neural Dynamics and Adaptive Sliding Innovation Filter
- Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models
- M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis
- Multi-dimensional Signal Recovery using Low-rank Deconvolution
- End-to-end Training and Decoding for Pivot-based Cascaded Translation Model
- Standardized Benchmark Dataset for Localized Exposure to a Realistic Source at 10-90 GHz
- Contextual Reasoning for Scene Generation (Technical Report)
- An Adaptive Algorithm for Learning with Unknown Distribution Drift
- Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems
- Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally
- The Benefits of Label-Description Training for Zero-Shot Text Classification
- AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking
- Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference
All 198
- WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models
- LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
- Learnability with Time-Sharing Computational Resource Concerns
- Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
- DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents
- Inverse Global Illumination using a Neural Radiometric Prior
- Rethinking Graph Lottery Tickets: Graph Sparsity Matters
- CLUSTSEG: Clustering for Universal Segmentation
- A Statistical Exploration of Text Partition Into Constituents: The Case of the Priestly Source in the Books of Genesis and Exodus
- Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
- Explaining Language Models' Predictions with High-Impact Concepts
- Shotgun crystal structure prediction using machine-learned formation energies
- Zero-Shot Listwise Document Reranking with a Large Language Model
- Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
- Semi-Supervised Segmentation of Functional Tissue Units at the Cellular Level
- ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training
- GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
- A Curriculum View of Robust Loss Functions
- Why Oatmeal is Cheap: Kolmogorov Complexity and Procedural Generation
- System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning
- Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Network
- Pay More Attention to Relation Exploration for Knowledge Base Question Answering
- Asymmetric quantum decision-making
- Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning
- GPT-RE: In-context Learning for Relation Extraction using Large Language Models
- Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries
- ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering
- What makes a good pause? Investigating the turn-holding effects of fillers
- Single Image Deraining via Feature-based Deep Convolutional Neural Network
- Removing Human Bottlenecks in Bird Classification Using Camera Trap Images and Deep Learning
- Efficient Online Decision Tree Learning with Active Feature Acquisition
- Efficient CNN-based Super Resolution Algorithms for mmWave Mobile Radar Imaging
- Understanding cirrus clouds using explainable machine learning
- Revisiting the Encoding of Satellite Image Time Series
- A Systematic Study on Object Recognition Using Millimeter-wave Radar
- Considerations for Ethical Speech Recognition Datasets
- An Ontology Design Pattern for Role-Dependent Names
- A Vision Transformer Approach for Efficient Near-Field Irregular SAR Super-Resolution
- Efficient 3-D Near-Field MIMO-SAR Imaging for Irregular Scanning Geometries
- Attention Based Feature Fusion For Multi-Agent Collaborative Perception
- Human Machine Co-adaption Interface via Cooperation Markov Decision Process System
- Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
- Low-complexity subspace-descent over symmetric positive definite manifold
- Improved Static Hand Gesture Classification on Deep Convolutional Neural Networks using Novel Sterile Training Technique
- Response-conditioned Turn-taking Prediction
- SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
- Gym-preCICE: Reinforcement Learning Environments for Active Flow Control
- Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classification
- Near-Field MIMO-ISAR Millimeter-Wave Imaging
- Natural language processing on customer note data
- Neural Network Training and Non-Differentiable Objective Functions
- A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning
- Deep Learning-Based Multiband Signal Fusion for 3-D SAR Super-Resolution
- A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
- fairml: A Statistician's Take on Fair Machine Learning Modelling
- Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving
- Extraction of volumetric indices from echocardiography: which deep learning solution for clinical use?
- Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
- A Survey on Dataset Distillation: Approaches, Applications and Future Directions
- District-scale surface temperatures generated from high-resolution longitudinal thermal infrared images
- DPSeq: A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers using Sequencer Architecture
- Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech Research
- NorQuAD: Norwegian Question Answering Dataset
- SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method
- Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization
- Experimental Design for Any p-Norm
- Exploring the Protein Sequence Space with Global Generative Models
- Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
- Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs
- Can Large Language Models Be an Alternative to Human Evaluations?
- Illicit item detection in X-ray images for security applications
- An Exploration of Conditioning Methods in Graph Neural Networks
- Fully Automatic Neural Network Reduction for Formal Verification
- Visual Transformation Telling
- DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
- Generative Meta-Learning for Zero-Shot Relation Triplet Extraction
- Causal Interventions-based Few-Shot Named Entity Recognition
- MolKD: Distilling Cross-Modal Knowledge in Chemical Reactions for Molecular Property Prediction
- Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
- Localization using Multi-Focal Spatial Attention for Masked Face Recognition
- Few-shot Event Detection: An Empirical Study and a Unified View
- Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities
- VSRQ: Quantitative Assessment Method for Safety Risk of Vehicle Intelligent Connected System
- Fairness in AI Systems: Mitigating gender bias from language-vision models
- Evolving Dictionary Representation for Few-shot Class-incremental Learning
- Class adaptive threshold and negative class guided noisy annotation robust Facial Expression Recognition
- A Lightweight CNN-Transformer Model for Learning Traveling Salesman Problems
- Causality-aware Concept Extraction based on Knowledge-guided Prompting
- Morphological Classification of Galaxies Using SpinalNet
- Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models
- Unsupervised Improvement of Audio-Text Cross-Modal Representations
- GPTutor: a ChatGPT-powered programming tool for code explanation
- Towards Imperceptible Document Manipulations against Neural Ranking Models
- Bio-Inspired Simple Neural Network for Low-Light Image Restoration: A Minimalist Approach
- Inferential Moments of Uncertain Multivariable Systems
- LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation
- AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation
- Autonomous search of real-life environments combining dynamical system-based path planning and unsupervised learning