Papers
Thu 17 Aug 2023
194 papers
- Multimodal Analysis Of Google Bard And GPT-Vision: Experiments In Visual ReasoningLLM reasoning → Multimodal reasoning +1
- Evaluating the Instruction-Following Robustness of Large Language Models to Prompt InjectionLLM safety and security → Prompt injection and agent security
- MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
- Regularizing Adversarial Imitation Learning Using Causal InvarianceOffline RL and imitation learning from data → Imitation learning methods
- Edit Temporal-Consistent Videos with Image Diffusion ModelDiffusion models → Video generation
- FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo EmbeddingsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Reinforced Self-Training (ReST) for Language ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +2
- Watch Your Steps: Local Image and Scene Editing by Text InstructionsDiffusion models → Image generation, text-to-image and editing
- Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective ApproachKnowledge distillation → Speech and audio distillation
- CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code GenerationLLM reasoning → Reasoning for agents, planning and code
- Discrete Prompt Compression with Reinforcement LearningEfficient LLM inference and serving → Prompt and context compression
- Learning A Coarse-to-Fine Diffusion Transformer for Image RestorationDiffusion models → Inverse problems and image restoration
- Probabilistic Results on the Architecture of Mathematical Reasoning Aligned by Cognitive AlternationLLM reasoning → Mathematical reasoning
- Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service
- General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing
- Automatic Cadastral Boundary Detection of Very High Resolution Images Using Mask R-CNN
- AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery
- Education in the age of Generative AI: Context and Recent Developments
- Approaches to Generative Artificial Intelligence, A Social Justice Perspective
- Artificial Intelligence for Web 3.0: A Comprehensive Survey
- KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases
- Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
- Neurological Prognostication of Post-Cardiac-Arrest Coma Patients Using EEG Data: A Dynamic Survival Analysis Framework with Competing Risks
- Synergistic Signal Denoising for Multimodal Time Series of Structure Vibration
- Building Emotional Support Chatbots in the Era of LLMs
- BERT4CTR: An Efficient Framework to Combine Pre-trained Language Model with Non-textual Features for CTR Prediction
- Online Transition-Based Feature Generation for Anomaly Detection in Concurrent Data Streams
- Bayesian polynomial neural networks and polynomial neural ordinary differential equations
- A Novel Loss Function Utilizing Wasserstein Distance to Reduce Subject-Dependent Noise for Generalizable Models in Affective Computing
- Sensor Fusion by Spatial Encoding for Autonomous Driving
- ChatGPT-HealthPrompt. Harnessing the Power of XAI in Prompt-Based Healthcare Decision Support using ChatGPT
- The Utility of the Virtual Imaging Trials Methodology for Objective Characterization of AI Systems and Training Data
- Learning representations by forward-propagating errors
- Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank
- Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital Health
- MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modeling
- Knowledge-inspired Subdomain Adaptation for Cross-Domain Knowledge Transfer
- GPU Accelerated Color Correction and Frame Warping for Real-time Video Stitching
- A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings
- TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning
- Polynomial Bounds for Learning Noisy Optical Physical Unclonable Functions and Connections to Learning With Errors
- Half-Hop: A graph upsampling approach for slowing down message passing
- A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug Reports
- Distributed Extra-gradient with Optimal Complexity and Communication Guarantees
- Is Argument Structure of Learner Chinese Understandable: A Corpus-Based Analysis
- RatGPT: Turning online LLMs into Proxies for Malware Attacks
- How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
- Diversifying AI: Towards Creative Chess with AlphaZero
- Forensic Data Analytics for Anomaly Detection in Evolving Networks
- FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning
- ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse
- Characterizing Information Seeking Events in Health-Related Social Discourse
- Accurate machine learning force fields via experimental and simulation data fusion
- Semi-sparsity Priors for Image Structure Analysis and Extraction
- The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
- Semantic Consistency for Assuring Reliability of Large Language Models
- EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
- Linearity of Relation Decoding in Transformer Language Models
- RTB Formulation Using Point Process
- ICAR: Image-based Complementary Auto Reasoning
- MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models
- Multi-fidelity Fourier Neural Operator for Fast Modeling of Large-Scale Geological Carbon Storage
- JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer
- Spectral information criterion for automatic elbow detection
- Hyperbolic Face Anti-Spoofing
- Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
- Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks
- ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection
- Identity-Aware Semi-Supervised Learning for Comic Character Re-Identification
- Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries
- Modeling Edge Features with Deep Bayesian Graph Networks
- Embracing assay heterogeneity with neural processes for markedly improved bioactivity predictions
- MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices
- Over-the-Air Computation Aided Federated Learning with the Aggregation of Normalized Gradient
- Pedestrian Environment Model for Automated Driving
- Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling
- Fast Decision Support for Air Traffic Management at Urban Air Mobility Vertiports using Graph Learning
- mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning
- Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning
- Enhancing API Documentation through BERTopic Modeling and Summarization
- Contrasting Linguistic Patterns in Human and LLM-Generated News Text
- Uplift Modeling: from Causal Inference to Personalization
- Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
- Fostering User Engagement in the Critical Reflection of Arguments
- Don't lose the message while paraphrasing: A study on content preserving style transfer
- Refining a Deep Learning-based Formant Tracker using Linear Prediction Methods
- Kernel-Based Tests for Likelihood-Free Hypothesis Testing
- Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features
- A Mathematical Characterization of Minimally Sufficient Robot Brains
- SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
- MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins
- Synthesizing Physically Plausible Human Motions in 3D Scenes
- Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks
- LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation
- SR-GAN for SR-gamma: super resolution of photon calorimeter images at collider experiments
- Reinforcement Learning for Battery Management in Dairy Farming
- ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval
- Multi-field Visualisation via Trait-induced Merge Trees
- Deep-seeded Clustering for Emotion Recognition from Wearable Physiological Sensors
- Towards Lightweight Data Integration using Multi-workflow Provenance and Data Observability
All 194
- DealMVC: Dual Contrastive Calibration for Multi-view Clustering
- An Extended Convergence Result for Behaviour Tree Controllers
- Semantic Information for Object Detection
- Neural oscillators for generalization of physics-informed machine learning
- Evaluation of really good grammatical error correction
- Quantifying the biomimicry gap in biohybrid robot-fish pairs
- Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models
- Eosinophils Instance Object Segmentation on Whole Slide Imaging Using Multi-label Circle Representation
- End-to-End Beam Retrieval for Multi-Hop Question Answering
- CONVERT:Contrastive Graph Clustering with Reliable Augmentation
- A Dual-Perspective Approach to Evaluating Feature Attribution Methods
- Predicting Crop Yield With Machine Learning: An Extensive Analysis Of Input Modalities And Models On a Field and sub-field Level
- Interpretable Graph Neural Networks for Tabular Data
- Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?
- Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
- Automatic Signboard Recognition in Low Quality Night Images
- Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces
- Estimating fire Duration using regression methods
- SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection
- On Data Imbalance in Molecular Property Prediction with Pre-training
- Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
- A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
- Frequency Perception Network for Camouflaged Object Detection
- IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making
- Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection
- Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing
- Development of a Knowledge Graph Embeddings Model for Pain
- Optimal Resource Allocation for U-Shaped Parallel Split Learning
- Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
- Dual Gauss-Newton Directions for Deep Learning
- Event-Guided Procedure Planning from Instructional Videos with Text Supervision
- SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations
- Text-Only Training for Visual Storytelling
- Enhancing Convergence Speed with Feature-Enforcing Physics-Informed Neural Networks: Utilizing Boundary Conditions as Prior Knowledge for Faster Convergence
- Towards Semi-supervised Learning with Non-random Missing Labels
- Spatially and Spectrally Consistent Deep Functional Maps
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
- D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
- MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimation
- Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
- Language-enhanced RNR-Map: Querying Renderable Neural Radiance Field maps with natural language
- Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays
- Learning the hub graphical Lasso model with the structured sparsity via an efficient algorithm
- A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation
- Machine Learning-Assisted Discovery of Flow Reactor Designs
- CMB: A Comprehensive Medical Benchmark in Chinese
- ICoNIK: Generating Respiratory-Resolved Abdominal MR Reconstructions Using Neural Implicit Representations in k-Space
- Lifted Algorithms for Symmetric Weighted First-Order Model Sampling
- Factuality Detection using Machine Translation -- a Use Case for German Clinical Text
- Controlling Federated Learning for Covertness
- Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction
- Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
- MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
- End-to-end Alternating Optimization for Real-World Blind Super Resolution
- A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction
- Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
- Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit
- Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
- Deep Ear Biometrics for Gender Classification
- Chinese Spelling Correction as Rephrasing Language Model
- Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces
- Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
- Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks
- APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service
- Exploring Demonstration Ensembling for In-context Learning
- Environment Diversification with Multi-head Neural Network for Invariant Learning
- Large Language Models at Work in China's Labor Market
- Learning to In-paint: Domain Adaptive Shape Completion for 3D Organ Segmentation
- Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
- URL: Combating Label Noise for Lung Nodule Malignancy Grading
- Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
- Explainable AI for tool wear prediction in turning
- XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Driving
- Efficient Commercial Bank Customer Credit Risk Assessment Based on LightGBM and Feature Engineering
- Fine-grained Text and Image Guided Point Cloud Completion with CLIP Model
- BOTT: Box Only Transformer Tracker for 3D Object Tracking
- An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
- PMET: Precise Model Editing in a Transformer
- MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction
- Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction
- ReProHRL: Towards Multi-Goal Navigation in the Real World using Hierarchical Agents
- On the Effectiveness of Log Representation for Log-based Anomaly Detection
- Recursive Detection and Analysis of Nanoparticles in Scanning Electron Microscopy Images
- Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification
- Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing
- Long-Range Grouping Transformer for Multi-View 3D Reconstruction
- Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression
- RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar
- EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices
- V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints
- Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition
- Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks
- Consciousness in Artificial Intelligence: Insights from the Science of Consciousness