Papers
Wed 19 Oct 2022
236 papers
- Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image SynthesisLLM safety and security → Federated unlearning and poisoning
- Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Scaling Laws for Reward Model OveroptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial QueriesLLM safety and security → Membership inference attacks
- Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image ModelsDiffusion models → Image generation, text-to-image and editing
- ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly DetectionKnowledge distillation → Detection and dense prediction distillation
- Robust Offline Reinforcement Learning with Gradient Penalty and Constraint RelaxationOffline RL and imitation learning from data → Offline RL algorithms
- Dense but Efficient VideoQA for Intricate Compositional ReasoningLLM reasoning → Multimodal reasoning
- On the Adversarial Robustness of Mixture of ExpertsMixture-of-experts → Vision mixture-of-experts
- An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries
- Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendation
- LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation
- Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
- Keyword Targeting Optimization in Sponsored Search Advertising: Combining Selection and Matching
- Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation
- Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Trading
- Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks
- Multi-Granularity Cross-Modality Representation Learning for Named Entity Recognition on Social Media
- Commonsense Knowledge from Scene Graphs for Textual Environments
- Motion correction in MRI using deep learning and a novel hybrid loss function
- An Experimental Study of Dimension Reduction Methods on Machine Learning Algorithms with Applications to Psychometrics
- A Dimension-Augmented Physics-Informed Neural Network (DaPINN) with High Level Accuracy and Efficiency
- lo-fi: distributed fine-tuning without communication
- RT-MOT: Confidence-Aware Real-Time Scheduling Framework for Multi-Object Tracking Tasks
- Computer-Aided Cancer Diagnosis via Machine Learning and Deep Learning: A comparative review
- Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
- Neural Co-Processors for Restoring Brain Function: Results from a Cortical Model of Grasping
- Hierarchical Deep Learning with Generative Adversarial Network for Automatic Cardiac Diagnosis from ECG Signals
- The Effectiveness of Social Media Engagement Strategy on Disaster Fundraising
- Image Semantic Relation Generation
- Structure-based drug design with geometric deep learning
- OCR-VQGAN: Taming Text-within-Image Generation
- Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey
- Knowledge-Enhanced Relation Extraction Dataset
- Hierarchical classification at multiple operating points
- Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge
- DOT-VAE: Disentangling One Factor at a Time
- Prophet Attention: Predicting Attention with Future Attention for Image Captioning
- Palm up: Playing in the Latent Manifold for Unsupervised Pretraining
- A baseline revisited: Pushing the limits of multi-segment models for context-aware translation
- Machine and Deep Learning Methods with Manual and Automatic Labelling for News Classification in Bangla Language
- r-Adaptive Deep Learning Method for Solving Partial Differential Equations
- Learning Preferences for Interactive Autonomy
- Window-Based Distribution Shift Detection for Deep Neural Networks
- DEEP2: Deep Learning Powered De-scattering with Excitation Patterning
- Mitigating spectral bias for the multiscale operator learning
- Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning
- G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR
- Exiting the Simulation: The Road to Robust and Resilient Autonomous Vehicles at Scale
- An Optimization-Based Supervised Learning Algorithm for PXRD Phase Fraction Estimation
- Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
- Cluster and Aggregate: Face Recognition with Large Probe Set
- QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
- Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions
- Dictionary Learning for the Almost-Linear Sparsity Regime
- BELIEF in Dependence: Leveraging Atomic Linearity in Data Bits for Rethinking Generalized Linear Models
- Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
- MMRNet: Improving Reliability for Multimodal Object Detection and Segmentation for Bin Picking via Multimodal Redundancy
- How Hate Speech Varies by Target Identity: A Computational Analysis
- A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
- On Learning Fairness and Accuracy on Multiple Subgroups
- Scene Text Recognition with Semantics
- Grounded Video Situation Recognition
- Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data
- VTC: Improving Video-Text Retrieval with User Comments
- A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition
- Self-Supervised Representation Learning for CAD
- Graph Regularized Probabilistic Matrix Factorization for Drug-Drug Interactions Prediction
- Self-learning locally-optimal hypertuning using maximum entropy, and comparison of machine learning approaches for estimating fatigue life in composite materials
- Topology Optimization via Machine Learning and Deep Learning: A Review
- TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
- Learning to Discover and Detect Objects
- Anomaly Detection Requires Better Representations
- Multi-view Tracking Using Weakly Supervised Human Motion Prediction
- LaMAR: Benchmarking Localization and Mapping for Augmented Reality
- "Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
- Anytime-valid off-policy inference for contextual bandits
- When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
- On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
- On Representing Mixed-Integer Linear Programs by Graph Neural Networks
- GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
- Two-level Data Augmentation for Calibrated Multi-view Detection
- Transformers Learn Shortcuts to Automata
- A Flexible Approach for Normal Approximation of Geometric and Topological Statistics
- A kernel Stein test of goodness of fit for sequential models
- RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations
- OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping
- TabLLM: Few-shot Classification of Tabular Data with Large Language Models
- UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
- Whole Page Unbiased Learning to Rank
- CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
- Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation
- Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction
- AUC-based Selective Classification
- Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking
- Robustness of Demonstration-based Learning Under Limited Data Scenario
- Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages
- Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
- Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information
- Language Models Understand Us, Poorly
All 236
- Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP
- Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
- Arabic Word-level Readability Visualization for Assisted Text Simplification
- Attaining Class-level Forgetting in Pretrained Model using Few Samples
- Weakly Supervised Learning for Analyzing Political Campaigns on Facebook
- N-Best Hypotheses Reranking for Text-To-SQL Systems
- Binary Orthogonal Non-negative Matrix Factorization
- Fantomas: Understanding Face Anonymization Reversibility
- Robust Regression with Highly Corrupted Data via Physics Informed Neural Networks
- Towards Accurate Subgraph Similarity Computation via Neural Graph Pruning
- Comparative analysis of deep learning approaches for AgNOR-stained cytology samples interpretation
- Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control
- Irregularly-Sampled Time Series Modeling with Spline Networks
- HAVANA: Hard negAtiVe sAmples aware self-supervised coNtrastive leArning for Airborne laser scanning point clouds semantic segmentation
- Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics
- A Unified View of Masked Image Modeling
- Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification
- Extending Graph Transformers with Quantum Computed Aggregation
- DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models
- Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels
- NGEP: A Graph-based Event Planning Framework for Story Generation
- Self-supervised Graph Masking Pre-training for Graph-to-Text Generation
- DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
- DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
- Active Learning for Imbalanced Civil Infrastructure Data
- CEntRE: A paragraph-level Chinese dataset for Relation Extraction among Enterprises
- Margin Optimal Classification Trees
- Geometric Deep Learning for the Assessment of Thrombosis Risk in the Left Atrial Appendage
- Hierarchical Multi-Interest Co-Network For Coarse-Grained Ranking
- Improved lung segmentation based on U-Net architecture and morphological operations
- Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing
- PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting
- The phase unwrapping of under-sampled interferograms using radial basis function neural networks
- Online LiDAR-Camera Extrinsic Parameters Self-checking
- Stability of Entropic Wasserstein Barycenters and application to random geometric graphs
- Deep-based quality assessment of medical images through domain adaptation
- Adversarial De-confounding in Individualised Treatment Effects Estimation
- Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing
- Graph sampling for node embedding
- A Segment-Wise Gaussian Process-Based Ground Segmentation With Local Smoothness Estimation
- The Future of Consumer Edge-AI Computing
- Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors
- Spectroscopic data de-noising via training-set-free deep learning method
- Visual SLAM: What are the Current Trends and What to Expect?
- A Robust Pedestrian Detection Approach for Autonomous Vehicles
- Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective
- Estimating the Contamination Factor's Distribution in Unsupervised Anomaly Detection
- Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
- Learning Transferable Adversarial Robust Representations via Multi-view Consistency
- Effective Targeted Attacks for Adversarial Self-Supervised Learning
- RLM-Tracking: Online Multi-Pedestrian Tracking Supported by Relative Location Mapping
- Video super-resolution for single-photon LIDAR
- FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping
- Bayesian Emulation for Computer Models with Multiple Partial Discontinuities
- On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
- Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering
- Estimating the coverage in 3d reconstructions of the colon from colonoscopy videos
- Group Fairness in Prediction-Based Decision Making: From Moral Assessment to Implementation
- Rethinking Sharpness-Aware Minimization as Variational Inference
- GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing
- EGG-GAE: scalable graph neural networks for tabular data imputation
- Deep neural network expressivity for optimal stopping problems
- Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction
- A scan-specific unsupervised method for parallel MRI reconstruction via implicit neural representation
- LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation
- A Linguistic Investigation of Machine Learning based Contradiction Detection Models: An Empirical Analysis and Future Perspectives
- Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes
- Convexity Certificates from Hessians
- MC-hands-1M: A glove-wearing hand dataset for pose estimation
- Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
- Multi-view Gait Recognition based on Siamese Vision Transformer
- Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation
- Hybrid-Regressive Neural Machine Translation
- High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registration
- Real Image Super-Resolution using GAN through modeling of LR and HR process
- Domain generalization Person Re-identification on Attention-aware multi-operation strategery
- Segmentation-free Direct Iris Localization Networks
- Tourist Guidance Robot Based on HyperCLOVA
- Spatio-channel Attention Blocks for Cross-modal Crowd Counting
- Machine Learning for a Sustainable Energy Future
- Distributional Adaptive Soft Regression Trees
- Variational Model Perturbation for Source-Free Domain Adaptation
- Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs
- Learning Universe Model for Partial Matching Networks over Multiple Graphs
- Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling
- CPL: Counterfactual Prompt Learning for Vision and Language Models
- Adaptive Neural Network Ensemble Using Frequency Distribution
- Leveraging a New Spanish Corpus for Multilingual and Crosslingual Metaphor Detection
- Stating Comparison Score Uncertainty and Verification Decision Confidence Towards Transparent Face Recognition
- Temporal Action Segmentation: An Analysis of Modern Techniques
- Using deep convolutional neural networks to classify poisonous and edible mushrooms found in China
- MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering
- Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation
- Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks
- BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
- The Devil in Linear Transformer
- WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization
- Revision Transformers: Instructing Language Models to Change their Values
- Language Detoxification with Attribute-Discriminative Latent Space
- Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping
- Efficient Bi-Level Optimization for Recommendation Denoising
- Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking
- Gaussian-Bernoulli RBMs Without Tears
- LAVA: Label-efficient Visual Learning and Adaptation
- Latency Aware Semi-synchronous Client Selection and Model Aggregation for Wireless Federated Learning
- Multi-Objective Recommender Systems: Survey and Challenges
- A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss
- Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
- Comparing Spectroscopy Measurements in the Prediction of in Vitro Dissolution Profile using Artificial Neural Networks
- Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation
- Differentiable Self-Adaptive Learning Rate
- Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models
- A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design
- CLIP-Driven Fine-grained Text-Image Person Re-identification
- Towards Explaining Distribution Shifts
- Training set cleansing of backdoor poisoning by self-supervised representation learning
- Fast Approximation of the Generalized Sliced-Wasserstein Distance
- Synthetic Sonar Image Simulation with Various Seabed Conditions for Automatic Target Recognition
- SignReLU neural network and its approximation ability
- Time and Cost-Efficient Bathymetric Mapping System using Sparse Point Cloud Generation and Automatic Object Detection
- Free energy model of emotional valence in dual-process perceptions
- End-to-End Entity Detection with Proposer and Regressor
- Continued Pretraining for Better Zero- and Few-Shot Promptability
- Causal Structure Learning with Recommendation System
- A Data-Driven Investigation of Noise-Adaptive Utterance Generation with Linguistic Modification
- Discovering Limitations of Image Quality Assessments with Noised Deep Learning Image Sets
- Performance of different machine learning methods on activity recognition and pose estimation datasets
- Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction
- CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
- Type-supervised sequence labeling based on the heterogeneous star graph for named entity recognition
- GSV-Cities: Toward Appropriate Supervised Visual Place Recognition
- Vision-Based Robust Lane Detection and Tracking under Different Challenging Environmental Conditions
- Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning
- Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling
- A Real-Time Wrong-Way Vehicle Detection Based on YOLO and Centroid Tracking
- Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets