Papers
Tue 1 Aug 2023
182 papers
- Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfittingLLM safety and security → Machine unlearning
- BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel OptimizationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
- LISA: Reasoning Segmentation via Large Language ModelLLM reasoning → Multimodal reasoning +1
- FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated LearningLLM safety and security → Federated unlearning and poisoning
- NormKD: Normalized Logits for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical EducationRetrieval-augmented generation → Medical and biomedical RAG
- SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step ReasoningLLM reasoning → Test-time compute and efficient thinking
- DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture +1
- MetaGPT: Meta Programming for A Multi-Agent Collaborative FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
- Diffusion Model for Camouflaged Object DetectionDiffusion models → Image generation, text-to-image and editing
- Online Prototype Learning for Online Continual LearningKnowledge distillation → Distillation for continual learning
- LGViT: Dynamic Early Exiting for Accelerating Vision TransformerEfficient LLM inference and serving → Token pruning and merging for ViTs
- Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive BiasLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Advancing Beyond Identification: Multi-bit Watermark for Large Language ModelsLLM safety and security → Watermarking generated content and models
- Through their eyes: multi-subject Brain Decoding with simple alignment techniques
- Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks
- Covid-19 Public Sentiment Analysis for Indian Tweets Classification
- Revolutionizing Wireless Networks with Federated Learning: A Comprehensive Review
- MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers
- Proceedings Modalities in substructural logics: Applications at the interfaces of logic, language and computation
- Fair Models in Credit: Intersectional Discrimination and the Amplification of Inequity
- Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting
- Aspect based sentimental analysis for travellers' reviews
- Collaborative filtering to capture AI user's preferences as norms
- Towards More Human-like AI Communication: A Review of Emergent Communication Research
- CoSMo: A constructor specification language for Abstract Wikipedia's content selection process
- ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP
- qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation
- Learning to Generate Training Datasets for Robust Semantic Segmentation
- Exploring the Role of Explainability in AI-Assisted Embryo Selection
- Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning
- Choir Transformer: Generating Polyphonic Music with Relative Attention on Transformer
- Gated Driver Attention Predictor
- Accessibility and Inclusiveness of New Information and Communication Technologies for Disabled Users and Content Creators in the Metaverse
- MRQ:Support Multiple Quantization Schemes through Model Re-Quantization
- ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworks
- Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects
- Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
- DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems
- Beneficent Intelligence: A Capability Approach to Modeling Benefit, Assistance, and Associated Moral Failures through AI Systems
- PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems
- Active Inference in String Diagrams: A Categorical Account of Predictive Processing and Free Energy
- Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes
- Differential Privacy for Adaptive Weight Aggregation in Federated Tumor Segmentation
- A Comprehensive Study of Groundbreaking Machine Learning Research: Analyzing highly cited and impactful publications across six decades
- Training on Foveated Images Improves Robustness to Adversarial Attacks
- CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters
- Deep Learning Approaches in Pavement Distress Identification: A Review
- An Exact Kernel Equivalence for Finite Classification Models
- Designing a Communication Bridge between Communities: Participatory Design for a Question-Answering AI Agent
- Addressing Uncertainty in Imbalanced Histopathology Image Classification of HER2 Breast Cancer: An interpretable Ensemble Approach with Threshold Filtered Single Instance Evaluation (SIE)
- GRDD: A Dataset for Greek Dialectal NLP
- Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction
- An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning
- Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity Recognition
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
- High-Fidelity Eye Animatable Neural Radiance Fields for Human Face
- DYMOND: DYnamic MOtif-NoDes Network Generative Model
- Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrieval
- Decomposition Ascribed Synergistic Learning for Unified Image Restoration
- The Bias Amplification Paradox in Text-to-Image Generation
- A Knowledge-Oriented Approach to Enhance Integration and Communicability in the Polkadot Ecosystem
- Mapping Computer Science Research: Trends, Influences, and Predictions
- Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment
- ELFNet: Evidential Local-global Fusion for Stereo Matching
- Adaptive Semantic Consistency for Cross-domain Few-shot Classification
- Latent-Shift: Gradient of Entropy Helps Neural Codecs
- Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example
- Beam Detection Based on Machine Learning Algorithms
- AnyLoc: Towards Universal Visual Place Recognition
- Learning from Hypervectors: A Survey on Hypervector Encoding
- CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
- Applicability of scaling laws to vision encoding models
- Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
- Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
- Dependency Structure Search Bayesian Optimization for Decision Making Models
- Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes
- JIANG: Chinese Open Foundation Language Model
- NeRT: Implicit Neural Representations for General Unsupervised Turbulence Mitigation
- Explainable Cost-Sensitive Deep Neural Networks for Brain Tumor Detection from Brain MRI Images considering Data Imbalance
- Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers
- MonoNext: A 3D Monocular Object Detection with ConvNext
- Visibility Enhancement for Low-light Hazy Scenarios
- Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
- Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel
- PVG: Progressive Vision Graph for Vision Recognition
- Reinforcement Learning-based Non-Autoregressive Solver for Traveling Salesman Problems
- Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms
- Copula for Instance-wise Feature Selection and Ranking
- Detecting Cloud Presence in Satellite Images Using the RGB-based CLIP Vision-Language Model
- Predicting Early Dropouts of an Active and Healthy Ageing App
- PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Maps
- Graph Embedding Dynamic Feature-based Supervised Contrastive Learning of Transient Stability for Changing Power Grid Topologies
- Graph Contrastive Learning with Generative Adversarial Network
- A Novel Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction
- Variational Label-Correlation Enhancement for Congestion Prediction
- Unimodal Intermediate Training for Multimodal Meme Sentiment Classification
- Visual attention information can be traced on cortical response but not on the retina: evidence from electrophysiological mouse data using natural images as stimuli
- Transfer-Ensemble Learning based Deep Convolutional Neural Networks for Diabetic Retinopathy Classification
- SurveyLM: A platform to explore emerging value perspectives in augmented language models' behaviors
All 182
- Markerless human pose estimation for biomedical applications: a survey
- Relational Contrastive Learning for Scene Text Recognition
- Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
- Explainable Graph Spectral Clustering of Text Documents
- An L2-Normalized Spatial Attention Network For Accurate And Fast Classification Of Brain Tumors In 2D T1-Weighted CE-MRI Images
- DINO-CXR: A self supervised method based on vision transformer for chest X-ray classification
- Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
- A Deep Learning Approach for Virtual Contrast Enhancement in Contrast Enhanced Spectral Mammography
- Mirror Natural Evolution Strategies
- A Satellite Imagery Dataset for Long-Term Sustainable Development in United States Cities
- Center Contrastive Loss for Metric Learning
- DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes
- ViT2EEG: Leveraging Hybrid Pretrained Vision Transformers for EEG Data
- A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models
- Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification
- Structural Embeddings of Tools for Large Language Models
- FLatten Transformer: Vision Transformer using Focused Linear Attention
- Patch-wise Auto-Encoder for Visual Anomaly Detection
- Multiscale Feature Learning Using Co-Tuplet Loss for Offline Handwritten Signature Verification
- Generative adversarial networks with physical sound field priors
- Discourse-Aware Text Simplification: From Complex Sentences to Linked Propositions
- Space Debris: Are Deep Learning-based Image Enhancements part of the Solution?
- Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
- Metrics to Quantify Global Consistency in Synthetic Medical Images
- VideoPro: A Visual Analytics Approach for Interactive Video Programming
- ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
- Tackling Hallucinations in Neural Chart Summarization
- On the Generation of a Synthetic Event-Based Vision Dataset for Navigation and Landing
- A Survey of Time Series Anomaly Detection Methods in the AIOps Domain
- Counterfactual Graph Transformer for Traffic Flow Prediction
- Artificial-Intelligence-Based Triple Phase Shift Modulation for Dual Active Bridge Converter with Minimized Current Stress
- Artificial-Intelligence-Based Hybrid Extended Phase Shift Modulation for the Dual Active Bridge Converter with Full ZVS Range and Optimal Efficiency
- Shape Completion with Prediction of Uncertain Regions
- Deep Image Harmonization with Learnable Augmentation
- Fountain -- an intelligent contextual assistant combining knowledge representation and language models for manufacturing risk identification
- Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation
- Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
- Learning Green's Function Efficiently Using Low-Rank Approximations
- Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
- Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
- Monitoring Algorithmic Fairness under Partial Observations
- Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning
- Threshold-aware Learning to Generate Feasible Solutions for Mixed Integer Programs
- Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis
- LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack
- Pixel to policy: DQN Encoders for within & cross-game reinforcement learning
- Zero-Shot Learning by Harnessing Adversarial Samples
- Doubly Robust Instance-Reweighted Adversarial Training
- GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
- Domain Adaptation based on Human Feedback for Enhancing Generative Model Denoising Abilities
- Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
- Making the V in Text-VQA Matter
- Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images
- A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
- Predictive Modeling through Hyper-Bayesian Optimization
- CLAMS: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clustering
- ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddings
- Data Collaboration Analysis applied to Compound Datasets and the Introduction of Projection data to Non-IID settings
- Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
- Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction
- Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
- Benchmarking Ultra-High-Definition Image Reflection Removal
- Multimodal Multi-loss Fusion Network for Sentiment Analysis
- Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation
- The Algonauts Project 2023 Challenge: UARK-UAlbany Team Solution
- Improving Pixel-based MIM by Reducing Wasted Modeling Capability
- AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy
- Best-Subset Selection in Generalized Linear Models: A Fast and Consistent Algorithm via Splicing Technique
- Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review
- EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learning
- The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models
- Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation
- Partitioned Saliency Ranking with Dense Pyramid Transformers
- Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks
- Using Scene and Semantic Features for Multi-modal Emotion Recognition
- Experiments on Generative AI-Powered Parametric Modeling and BIM for Architectural Design
- Boundary Difference Over Union Loss For Medical Image Segmentation
- Multi-goal Audio-visual Navigation using Sound Direction Map
- Deep Reinforcement Learning-Based Battery Conditioning Hierarchical V2G Coordination for Multi-Stakeholder Benefits
- The Impact of Loss Functions and Scene Representations for 3D/2D Registration on Single-view Fluoroscopic X-ray Pose Estimation
- Scene Separation & Data Selection: Temporal Segmentation Algorithm for Real-Time Video Stream Analysis
- Synthetic Skull CT Generation with Generative Adversarial Networks to Train Deep Learning Models for Clinical Transcranial Ultrasound