Papers
Wed 10 May 2023
208 papers
- Analyzing Bias in Diffusion-based Face Generation ModelsDiffusion models → Image generation, text-to-image and editing
- Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and TaxonomyLLM safety and security → Machine unlearning
- RECKONING: Reasoning through Dynamic Knowledge EncodingLLM reasoning → Reasoning benchmarks and evaluation
- Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal PerceptionMixture-of-experts → Multimodal MoE models
- SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake DetectionLLM safety and security → Watermarking generated content and models
- Explainable Knowledge Distillation for On-device Chest X-Ray ClassificationKnowledge distillation → Distillation for medical imaging
- Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Multi-Prompt with Depth Partitioned Cross-Modal LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- A proof of convergence of inverse reinforcement learning for multi-objective optimizationOffline RL and imitation learning from data → Inverse reinforcement learning
- Relightify: Relightable 3D Faces from a Single Image via Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge BaseLLM reasoning → Reasoning benchmarks and evaluation
- iEdit: Localised Text-guided Image Editing with Weak SupervisionDiffusion models → Image generation, text-to-image and editing
- Fast Distributed Inference Serving for Large Language ModelsEfficient LLM inference and serving → Serving systems and request scheduling
- Text-guided High-definition Consistency Texture ModelDiffusion models → 3D, point cloud and scene generation
- Diffusion-based Signal Refiner for Speech Enhancement and SeparationDiffusion models → Audio, speech and music
- Beyond Negativity: Re-Analysis and Follow-Up Experiments on Hope Speech Detection
- GPT Models Meet Robotic Applications: Co-Speech Gesturing Chat System
- What We Know So Far: Artificial Intelligence in African Healthcare
- Benchmarking large language models for biomedical natural language processing applications and recommendations
- Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces
- Talking with Machines: A Comprehensive Survey of Emergent Dialogue Systems
- Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design
- Novel deep learning methods for 3D flow field segmentation and classification
- Enriching language models with graph-based context information to better understand textual data
- ORKG-Leaderboards: A Systematic Workflow for Mining Leaderboards as a Knowledge Graph
- Bits of Grass: Does GPT already know how to write like Whitman?
- SPSQL: Step-by-step Parsing Based Framework for Text-to-SQL Generation
- Appliance Detection Using Very Low-Frequency Smart Meter Time Series
- BIOT: Cross-data Biosignal Learning in the Wild
- Multiverse at the Edge: Interacting Real World and Digital Twins for Wireless Beamforming
- Davinci the Dualist: the mind-body divide in large language models and in human learners
- Supplementing Gradient-Based Reinforcement Learning with Simple Evolutionary Ideas
- Shhh! The Logic of Clandestine Operations
- Quran Recitation Recognition using End-to-End Deep Learning
- An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-Markov Decision Processes
- Humans are Still Better than ChatGPT: Case of the IEEEXtreme Competition
- Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing
- Multimodal Contextualized Plan Prediction for Embodied Task Completion
- Towards L-System Captioning for Tree Reconstruction
- ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks
- SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
- Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
- Securing Distributed SGD against Gradient Leakage Threats
- ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps
- Perpetual Humanoid Control for Real-time Simulated Avatars
- Autonomous GIS: the next-generation AI-powered GIS
- What Students Can Learn About Artificial Intelligence -- Recommendations for K-12 Computing Education
- Continual Facial Expression Recognition: A Benchmark
- Dynamic Graph Representation Learning for Depression Screening with Transformer
- Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
- Data, Trees, and Forests -- Decision Tree Learning in K-12 Education
- Self-Supervised Video Representation Learning via Latent Time Navigation
- Multi-Robot Coordination and Layout Design for Automated Warehousing
- Phase transitions in the mini-batch size for sparse and dense two-layer neural networks
- Word Grounded Graph Convolutional Network
- A Generalizable Physics-informed Learning Framework for Risk Probability Estimation
- HoneyIoT: Adaptive High-Interaction Honeypot for IoT Devices Through Reinforcement Learning
- Mispronunciation Detection of Basic Quranic Recitation Rules using Deep Learning
- Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization
- Bot or Human? Detecting ChatGPT Imposters with A Single Question
- An Empirical Study on the Robustness of the Segment Anything Model (SAM)
- A Method to Automate the Discharge Summary Hospital Course for Neurology Patients
- Accelerating Batch Active Learning Using Continual Learning Techniques
- Combo of Thinking and Observing for Outside-Knowledge VQA
- LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM
- Towards Scalable Adaptive Learning with Graph Neural Networks and Reinforcement Learning
- ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion
- Local Region-to-Region Mapping-based Approach to Classify Articulated Objects
- Text-To-Concept (and Back) via Cross-Model Alignment
- HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
- Discovery of Optimal Quantum Error Correcting Codes via Reinforcement Learning
- Efficient Training of Multi-task Neural Solver for Combinatorial Optimization
- HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
- VideoChat: Chat-Centric Video Understanding
- Reconstructing Animatable Categories from Videos
- Supervised learning with probabilistic morphisms and kernel mean embeddings
- CosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulators
- Orthogonal Transforms in Neural Networks Amount to Effective Regularization
- Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs
- K-UniMorph: Korean Universal Morphology and its Feature Schema
- Korean Named Entity Recognition Based on Language-Specific Features
- Similarity of Neural Network Models: A Survey of Functional and Representational Measures
- NervePool: A Simplicial Pooling Layer
- Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks
- Automatic Evaluation of Attribution by Large Language Models
- Analysis of Adversarial Image Manipulations
- Self-Supervised Instance Segmentation by Grasping
- Evaluating Embedding APIs for Information Retrieval
- Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)
- Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions
- Extracting Diagnosis Pathways from Electronic Health Records Using Deep Reinforcement Learning
- CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation
- Joint Metrics Matter: A Better Standard for Trajectory Forecasting
- Learning Video-Conditioned Policies for Unseen Manipulation Tasks
- A Multi-modal Garden Dataset and Hybrid 3D Dense Reconstruction Framework Based on Panoramic Stereo Images for a Trimming Robot
- Context-Aware Document Simplification
- Embedded Feature Similarity Optimization with Specific Parameter Initialization for 2D/3D Medical Image Registration
- Deep Reinforcement Learning Based Resource Allocation for Cloud Native Wireless Network
- Rethinking the Value of Labels for Instance-Dependent Label Noise Learning
- Radious: Unveiling the Enigma of Dental Radiology with BEIT Adaptor and Mask2Former in Semantic Segmentation
All 208
- Penalized deep neural networks estimator with general loss functions under weak dependence
- DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
- Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
- Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
- Multiclass MRI Brain Tumor Segmentation using 3D Attention-based U-Net
- Learning in a Single Domain for Non-Stationary Multi-Texture Synthesis
- Computationally Efficient and Statistically Optimal Robust High-Dimensional Linear Regression
- A Multi-modal Approach to Single-modal Visual Place Classification
- Sequence-Agnostic Multi-Object Navigation
- Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID
- Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery
- Feature Expansion for Graph Neural Networks
- Active Semantic Localization with Graph Neural Embedding
- CrudeBERT: Applying Economic Theory towards fine-tuning Transformer-based Sentiment Analysis Models to the Crude Oil Market
- A Neural Emulator for Uncertainty Estimation of Fire Propagation
- When ChatGPT for Computer Vision Will Come? From 2D to 3D
- Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era
- FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment
- Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach
- NeRF2: Neural Radio-Frequency Radiance Fields
- VTPNet for 3D deep learning on point cloud
- Few-shot Action Recognition via Intra- and Inter-Video Information Maximization
- The Compositional Structure of Bayesian Inference
- Pavlok-Nudge: A Feedback Mechanism for Atomic Behaviour Modification with Snoring Usecase
- XMI-ICU: Explainable Machine Learning Model for Pseudo-Dynamic Prediction of Mortality in the ICU for Heart Attack Patients
- Few-shot Link Prediction on N-ary Facts
- Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
- PAI at SemEval-2023 Task 2: A Universal System for Named Entity Recognition with External Entity Information
- XTab: Cross-table Pretraining for Tabular Transformers
- Building Interoperable Electronic Health Records as Purpose-Driven Knowledge Graphs
- A Glimpse in ChatGPT Capabilities and its impact for AI research
- FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature
- Best Arm Identification in Bandits with Limited Precision Sampling
- Towards Effective Visual Representations for Partial-Label Learning
- iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?
- Enhancing Quantum Support Vector Machines through Variational Kernel Training
- Visual Tuning
- Compressing Neural Networks Using Tensor Networks with Exponentially Fewer Variational Parameters
- A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
- Post-training Model Quantization Using GANs for Synthetic Data Generation
- Correlation visualization under missing values: a comparison between imputation and direct parameter estimation methods
- Autonomous Stabilization of Retinal Videos for Streamlining Assessment of Spontaneous Venous Pulsations
- Blockwise Principal Component Analysis for monotone missing data imputation and dimensionality reduction
- FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume
- Uncertainty in GNN Learning Evaluations: The Importance of a Consistent Benchmark for Community Detection
- Brain Tumor Detection using Swin Transformers
- A Survey on the Robustness of Computer Vision Models against Common Corruptions
- Safe motion planning with environment uncertainty
- InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation
- Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations
- MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
- DMNR: Unsupervised De-noising of Point Clouds Corrupted by Airborne Particles
- Structural Hawkes Processes for Learning Causal Structure from Discrete-Time Event Sequences
- Uncertainty-Aware Semi-Supervised Learning for Prostate MRI Zonal Segmentation
- Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models
- Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
- Pearson-Matthews correlation coefficients for binary and multinary classification and hypothesis testing
- Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
- FusionBooster: A Unified Image Fusion Boosting Paradigm
- Investigating Forgetting in Pre-Trained Representations Through Continual Learning
- Graph Neural Networks and 3-Dimensional Topology
- Interpretable Multimodal Misinformation Detection with Logic Reasoning
- Fair principal component analysis (PCA): minorization-maximization algorithms for Fair PCA, Fair Robust PCA and Fair Sparse PCA
- Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation
- Multi-Path Transformer is Better: A Case Study on Neural Machine Translation
- Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer
- Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment
- V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
- Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering
- Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference
- WikiSQE: A Large-Scale Dataset for Sentence Quality Estimation in Wikipedia
- Deep Learning for Predicting Progression of Patellofemoral Osteoarthritis Based on Lateral Knee Radiographs, Demographic Data and Symptomatic Assessments
- Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification
- A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer
- Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
- Multi-stage Progressive Reasoning for Dunhuang Murals Inpainting
- DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
- Mobile Image Restoration via Prior Quantization
- Mixture of personality improved Spiking actor network for efficient multi-agent cooperation
- A Black-Box Attack on Code Models via Representation Nearest Neighbor Search
- CUTS+: High-dimensional Causal Discovery from Irregular Time-series
- Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
- Weakly-supervised ROI extraction method based on contrastive learning for remote sensing images
- Computational Optics for Mobile Terminals in Mass Production
- Level-line Guided Edge Drawing for Robust Line Segment Detection
- Deep Partial Multi-Label Learning with Graph Disambiguation
- Address Matching Based On Hierarchical Information
- Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
- Medical supervised masked autoencoders: Crafting a better masking strategy and efficient fine-tuning schedule for medical image classification
- Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation
- Optical Aberration Correction in Postprocessing using Imaging Simulation
- Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks
- V=arta: A Large-Scale Headline-Generation Dataset for Indic Languages
- Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation
- Sketching the Future (STF): Applying Conditional Control Techniques to Text-to-Video Models
- MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks
- D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point Searching and Learnable Feature Fusion
- A Self-Training Framework Based on Multi-Scale Attention Fusion for Weakly Supervised Semantic Segmentation
- Achieving Diversity in Counterfactual Explanations: a Review and Discussion
- Low-Light Image Enhancement via Structure Modeling and Guidance
- Generative Steganographic Flow
- Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation
- Unsupervised Dense Retrieval Training with Web Anchors
- Causal Information Splitting: Engineering Proxy Features for Robustness to Distribution Shifts
- A Normal Map-Based Proximal Stochastic Gradient Method: Convergence and Identification Properties
- Inclusive FinTech Lending via Contrastive Learning and Domain Adaptation
- Context-dependent communication under environmental constraints
- Best-Effort Adaptation