Papers
Fri 6 May 2022
138 papers
- Diverse Imitation Learning via Self-Organizing Generative ModelsOffline RL and imitation learning from data → Imitation learning methods
- The Unreliability of Explanations in Few-shot Prompting for Textual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic ManipulationOffline RL and imitation learning from data → Real-world robot offline RL
- Prompt Distribution LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd CountingKnowledge distillation → Distillation for continual learning
- Collective Relevance Labeling for Passage RetrievalKnowledge distillation → General knowledge distillation methods
- SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual ReasoningLLM reasoning → Multimodal reasoning
- DagSim: Combining DAG-based model structure with unconstrained data types and relations for flexible, transparent, and modularized data simulation
- Stochastic resonance neurons in artificial neural networks
- Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration
- JUNO: Jump-Start Reinforcement Learning-based Node Selection for UWB Indoor Localization
- Deep Supervised Information Bottleneck Hashing for Cross-modal Retrieval based Computer-aided Diagnosis
- Network Gradient Descent Algorithm for Decentralized Federated Learning
- Functional2Structural: Cross-Modality Brain Networks Representation Learning
- Concepts and Algorithms for Agent-based Decentralized and Integrated Scheduling of Production and Auxiliary Processes
- Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
- AODisaggregation: toward global aerosol vertical profiles
- A modular software framework for the design and implementation of ptychography algorithms
- RCMNet: A deep learning model assists CAR-T therapy for leukemia
- Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference
- Fine-grained Intent Classification in the Legal Domain
- Inferring electrochemical performance and parameters of Li-ion batteries based on deep operator networks
- PARAFAC2×N: Coupled Decomposition of Multi-modal Data with Drift in N Modes
- Online Model Compression for Federated Learning with Large Models
- Norm-Scaling for Out-of-Distribution Detection
- DULA and DEBA: Differentiable Ergonomic Risk Models for Postural Assessment and Optimization in Ergonomically Intelligent pHRI
- Clustered Graph Matching for Label Recovery and Graph Classification
- Hitting time for Markov decision process
- When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it
- Dynamically writing coupled memories using a reinforcement learning agent, meeting physical bounds
- EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms
- Comparative Analysis of Non-Blind Deblurring Methods for Noisy Blurred Images
- Psychologically-Inspired Music Recommendation System
- Structure Learning in Graphical Models from Indirect Observations
- LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract
- Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching
- Global Multi-modal 2D/3D Registration via Local Descriptors Learning
- EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
- Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition
- Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment
- VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution
- HRCTCov19 -- A High-Resolution Chest CT Scan Image Dataset for COVID-19 Diagnosis and Differentiation
- A Data Cartography based MixUp for Pre-trained Language Models
- Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning
- Journaling Data for Daily PHQ-2 Depression Prediction and Forecasting
- MINI: Mining Implicit Novel Instances for Few-Shot Object Detection
- Physics-informed neural networks for PDE-constrained optimization and control
- Summary Markov Models for Event Sequences
- All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
- Quantifying Synthesis and Fusion and their Impact on Machine Translation
- An Efficient Minimax Optimal Estimator For Multivariate Convex Regression
- Trainable Wavelet Neural Network for Non-Stationary Signals
- Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles
- Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection
- Far from Asymptopia
- Transferring Chemical and Energetic Knowledge Between Molecular Systems with Machine Learning
- UAV-aided RF Mapping for Sensing and Connectivity in Wireless Networks
- UAV-aided Wireless Node Localization Using Hybrid Radio Channel Models
- Benchmarking Econometric and Machine Learning Methodologies in Nowcasting
- Application of Clustering Algorithms for Dimensionality Reduction in Infrastructure Resilience Prediction Models
- Example-Based Machine Translation from Text to a Hierarchical Representation of Sign Language
- Combining Humor and Sarcasm for Improving Political Parody Detection
- Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection
- Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media
- The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
- Vehicle management in a modular production context using Deep Q-Learning
- GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
- Probabilistic Control and Majorization of Optimal Control
- Designing Robust Biotechnological Processes Regarding Variabilities using Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design
- Astral Space: Convex Analysis at Infinity
- Synthetic Data -- what, why and how?
- What Makes A Good Fisherman? Linear Regression under Self-Selection Bias
- Alternating Good-for-MDP Automata
- Goal-Oriented Next Best Activity Recommendation using Reinforcement Learning
- Predicting Future Occupancy Grids in Dynamic Environment with Spatio-Temporal Learning
- HumanAL: Calibrating Human Matching Beyond a Single Task
- Towards QD-suite: developing a set of benchmarks for Quality-Diversity algorithms
- Perseus: A Simple and Optimal High-Order Method for Variational Inequalities
- A Logic-based Tractable Approximation of Probability
- Federated Channel Learning for Intelligent Reflecting Surfaces With Fewer Pilot Signals
- Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation
- Scalable computation of prediction intervals for neural networks via matrix sketching
- Imperceptible Backdoor Attack: From Input Space to Feature Representation
- Semantics-Guided Moving Object Segmentation with 3D LiDAR
- On boundary conditions parametrized by analytic functions
- Green Accelerated Hoeffding Tree
- The NT-Xent loss upper bound
- Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Data
- Geodesics, Non-linearities and the Archive of Novelty Search
- Investigating and Explaining the Frequency Bias in Image Classification
- Bridging the Domain Gap for Stance Detection for the Zulu language
- Rediscovering Argumentation Principles Utilizing Collective Attacks
- From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data
- CLIP-CLOP: CLIP-Guided Collage and Photomontage
- How to Minimize the Weighted Sum AoI in Multi-Source Status Update Systems: OMA or NOMA?
- Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
- BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching
- Fast Rate Generalization Error Bounds: Variations on a Theme
- A High-Accuracy Unsupervised Person Re-identification Method Using Auxiliary Information Mined from Datasets
All 138
- Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments
- Arabic Fake News Detection Based on Deep Contextualized Embedding Models
- Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances
- Controlled Dropout for Uncertainty Estimation
- LPGNet: Link Private Graph Networks for Node Classification
- Crop Type Identification for Smallholding Farms: Analyzing Spatial, Temporal and Spectral Resolutions in Satellite Imagery
- Fake News Detection with Heterogeneous Transformer
- Federated Learning with Noisy User Feedback
- PTFlash : A deep learning framework for isothermal two-phase equilibrium calculations
- Probabilistic learning constrained by realizations using a weak formulation of Fourier transform of probability measures
- Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation
- KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering
- Characterizing Multi-Domain False News and Underlying User Effects on Chinese Weibo
- Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization
- Incremental Data-Uploading for Full-Quantum Classification
- Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
- Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation
- Dual-Level Decoupled Transformer for Video Captioning
- Quantification of Robotic Surgeries with Vision-Based Deep Learning
- A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
- Hearing voices at the National Library -- a speech corpus and acoustic model for the Swedish language
- A Fingerprint Detection Method by Fingerprint Ridge Orientation Check
- Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users
- Generative Adversarial Neural Operators
- Differentially Private Generalized Linear Models Revisited
- Automatic Noisy Label Correction for Fine-Grained Entity Typing
- Design Target Achievement Index: A Differentiable Metric to Enhance Deep Generative Models in Multi-Objective Inverse Design
- Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime
- Optimal Propagation for Graph Neural Networks
- Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism
- Tell Me Something That Will Help Me Trust You: A Survey of Trust Calibration in Human-Agent Interaction
- Optimally tackling covariate shift in RKHS-based nonparametric regression
- Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports
- IMU Based Deep Stride Length Estimation With Self-Supervised Learning
- Variance Reduction based Partial Trajectory Reuse to Accelerate Policy Gradient Optimization
- Generate and Edit Your Own Character in a Canonical View
- Large Scale Transfer Learning for Differentially Private Image Classification
- Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery