Papers
Mon 14 Mar 2022
196 papers
- ScienceWorld: Is your Agent Smarter than a 5th Grader?LLM reasoning → Knowledge- and tool-augmented reasoning
- Uncertainty Estimation for Language Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid RetrainingLLM safety and security → Federated unlearning and poisoning
- Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph ExpertsLLM reasoning → Reasoning benchmarks and evaluation +1
- The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language ModelsEfficient LLM inference and serving → Early exit and edge inference
- On the benefits of knowledge distillation for adversarial robustnessKnowledge distillation → Federated, robust and private distillation
- MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic EnvironmentsWorld models → World modeling from LiDAR generation
- Calibration of Derivative Pricing Models: a Multi-Agent Reinforcement Learning PerspectiveDiffusion models → Flow matching, time series and science
- Efficient Language Modeling with Sparse all-MLPMixture-of-experts → MoE large language models
- Support-vector-machine with Bayesian optimization for lithofacies classification using elastic properties
- A novel evolutionary-based neuro-fuzzy task scheduling approach to jointly optimize the main design challenges of heterogeneous MPSoCs
- Reasoning over Public and Private Data in Retrieval-Based Systems
- Multigrid-augmented deep learning preconditioners for the Helmholtz equation
- Conquering Ghosts: Relation Learning for Information Reliability Representation and End-to-End Robust Navigation
- Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training
- A Decomposition-Based Hybrid Ensemble CNN Framework for Driver Fatigue Recognition
- Noisy Tensor Completion via Low-rank Tensor Ring
- RES-HD: Resilient Intelligent Fault Diagnosis Against Adversarial Attacks Using Hyper-Dimensional Computing
- Energy-Latency Attacks via Sponge Poisoning
- The Design and Implementation of a Broadly Applicable Algorithm for Optimizing Intra-Day Surgical Scheduling
- Combining AI/ML and PHY Layer Rule Based Inference -- Some First Results
- Can A Neural Network Hear the Shape of A Drum?
- Geometric reconstructions of density based clusterings
- Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction
- Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition
- Unsupervised Learning Based Focal Stack Camera Depth Estimation
- Generalized Rectifier Wavelet Covariance Models For Texture Synthesis
- Magnetic Field Prediction Using Generative Adversarial Networks
- Simulating Liquids with Graph Networks
- Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
- Safe adaptation in multiagent competition
- Toward the Detection of Polyglot Files
- On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency
- Agile Maneuvers in Legged Robots: a Predictive Control Approach
- VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction
- Physical Neural Cellular Automata for 2D Shape Classification
- Permutation Invariant Representations with Applications to Graph Deep Learning
- A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs
- Neural Network Solver for Coherent Synchrotron Radiation Wakefield Calculations in Accelerator-based Charged Particle Beams
- The TAP free energy for high-dimensional linear regression
- Denoising and feature extraction in photoemission spectra with variational auto-encoder neural networks
- TTCDist: Fast Distance Estimation From an Active Monocular Camera Using Time-to-Contact
- Convolutional-Recurrent Neural Network Proxy for Robust Optimization and Closed-Loop Reservoir Management
- Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
- Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering
- Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer
- Skydiver: A Spiking Neural Network Accelerator Exploiting Spatio-Temporal Workload Balance
- Multi Stage Screening: Enforcing Fairness and Maximizing Efficiency in a Pre-Existing Pipeline
- Don't fear the unlabelled: safe semi-supervised learning via simple debiasing
- Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
- Conformance Checking Over Stochastically Known Logs
- Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems
- VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
- Repairing Regressors for Fair Binary Classification at Any Decision Threshold
- Simplicial Attention Neural Networks
- Audiovisual Affect Assessment and Autonomous Automobiles: Applications
- Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
- Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation
- Simultaneous Learning of the Inputs and Parameters in Neural Collaborative Filtering
- L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
- A deep learning pipeline for breast cancer ki-67 proliferation index scoring
- A Neural Pairwise Ranking Model for Readability Assessment
- Unsupervised Clustering of Roman Potsherds via Variational Autoencoders
- SuperAnimal pretrained pose estimation models for behavioral analysis
- Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information
- Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning
- On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel
- Respecting causality is all you need for training physics-informed neural networks
- Revisiting the Compositional Generalization Abilities of Neural Sequence Models
- Accelerated Bayesian SED Modeling using Amortized Neural Posterior Estimation
- What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
- Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks
- Dawn of the transformer era in speech emotion recognition: closing the valence gap
- HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing
- From Big to Small: Adaptive Learning to Partial-Set Domains
- The Efficacy of Pessimism in Asynchronous Q-Learning
- A Supervised Learning Approach to Rankability
- Implicit Motion Handling for Video Camouflaged Object Detection
- CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection
- Stubborn: A Strong Baseline for Indoor Object Navigation
- Sparse random hypergraphs: Non-backtracking spectra and community detection
- Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases
- Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
- Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies
- Phenomenology of Double Descent in Finite-Width Neural Networks
- Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
- GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors
- Accelerating Plug-and-Play Image Reconstruction via Multi-Stage Sketched Gradients
- S5CL: Unifying Fully-Supervised, Self-Supervised, and Semi-Supervised Learning Through Hierarchical Contrastive Learning
- All in One: Exploring Unified Video-Language Pre-training
- Mixed Evidence for Gestalt Grouping in Deep Neural Networks
- Mobile Behavioral Biometrics for Passive Authentication
- InsetGAN for Full-Body Image Generation
- GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
- On Cyclic Solutions to the Min-Max Latency Multi-Robot Patrolling Problem
- FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems
- Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data
- SimHawNet: A Modified Hawkes Process for Temporal Network Simulation
- FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition
- TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation
All 196
- Physico-chemical properties extraction from the fluorescence spectrum with 1D-convolutional neural networks: application to olive oil
- FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing
- A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification
- Geometry of Data
- Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data
- CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
- LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network
- NeILF: Neural Incident Light Field for Physically-based Material Estimation
- Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
- RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
- Orchestrated Value Mapping for Reinforcement Learning
- Dataset and Case Studies for Visual Near-Duplicates Detection in the Context of Social Media
- RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry
- CAR: Class-aware Regularizations for Semantic Segmentation
- Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection
- Interpretable Dysarthric Speaker Adaptation based on Optimal-Transport
- CAROL: Confidence-Aware Resilience Model for Edge Federations
- Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
- Adversarial amplitude swap towards robust image classifiers
- On the Nash equilibrium of moment-matching GANs for stationary Gaussian processes
- A Bayesian approach to translators' reliability assessment
- Similarity-based prediction of Ejection Fraction in Heart Failure Patients
- Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Design
- Deep Transformers Thirst for Comprehensive-Frequency Data
- Modelling variability in vibration-based PBSHM via a generalised population form
- RCL: Recurrent Continuous Localization for Temporal Action Detection
- Disentangled Representation Learning for Text-Video Retrieval
- Privatized Graph Federated Learning
- A Two-Block RNN-based Trajectory Prediction from Incomplete Trajectory
- The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications
- Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
- MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization
- Interpretability for Language Learners Using Example-Based Grammatical Error Correction
- Self-Promoted Supervision for Few-Shot Transformer
- Soft-margin classification of object manifolds
- Active Learning by Feature Mixing
- Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks
- A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
- Rethinking Minimal Sufficient Representation in Contrastive Learning
- MTLDesc: Looking Wider to Describe Better
- Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification
- Modelling Non-Smooth Signals with Complex Spectral Structure
- Supervised segmentation of NO2 plumes from individual ships using TROPOMI satellite data
- Neural Theorem Provers Delineating Search Area Using RNN
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots
- UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
- Speeding up deep neural network-based planning of local car maneuvers via efficient B-spline path construction
- S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers
- Forward Compatible Few-Shot Class-Incremental Learning
- Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey
- XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
- Towards Neural Sparse Linear Solvers
- Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering
- Modelling word learning and recognition using visually grounded speech
- WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition
- DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network
- Uncertainty-Aware Text-to-Program for Question Answering on Structured Electronic Health Records
- SimMatch: Semi-supervised Learning with Similarity Matching
- Hierarchical Memory Learning for Fine-Grained Scene Graph Generation
- PERT: Pre-training BERT with Permuted Language Model
- Less is More: Proxy Datasets in NAS approaches
- Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
- Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations
- Communication-Efficient Federated Distillation with Active Data Sampling
- Efficient universal shuffle attack for visual object tracking
- Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition
- Attention based Memory video portrait matting
- Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram
- DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection
- Asymptotic Behavior of Bayesian Generalization Error in Multinomial Mixtures
- Accelerating DETR Convergence via Semantic-Aligned Matching
- Rethinking Stability for Attribution-based Explanations
- Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
- TSR-DSAW: Table Structure Recognition via Deep Spatial Association of Words
- The Role of Interactivity in Structured Estimation
- ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
- DIAS: A Domain-Independent Alife-Based Problem-Solving System
- Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions
- SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
- A Comparative Study on Forecasting of Retail Sales
- RecursiveMix: Mixed Learning with History
- STDAN: Deformable Attention Network for Space-Time Video Super-Resolution
- Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation
- KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling
- Semi-Discrete Normalizing Flows through Differentiable Tessellation
- Fairness Evaluation in Deepfake Detection Models using Metamorphic Testing
- SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation
- Grounding Commands for Autonomous Vehicles via Layer Fusion with Region-specific Dynamic Layer Attention
- CheckSel: Efficient and Accurate Data-valuation Through Online Checkpoint Selection
- ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
- Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions
- Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
- MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
- The Role of Local Steps in Local SGD
- Can pre-trained Transformers be used in detecting complex sensitive sentences? -- A Monsanto case study