Papers
Tue 28 Feb 2023
244 papers
- ReorientDiff: Diffusion Model based Reorientation for Object ManipulationDiffusion models → Diffusion and flow policies for robotics
- Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionKnowledge distillation → Speech and audio distillation
- Learning to Control Autonomous Fleets from Observation via Offline Reinforcement LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
- Monocular Depth Estimation using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Membership Inference Attack for Beluga Whales DiscriminationLLM safety and security → Membership inference attacks
- Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech EnhancementDiffusion models → Audio, speech and music
- Improving Expert Specialization in Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
- Synthesizing Mixed-type Electronic Health Records using Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?Diffusion models → Video generation
- FreeEagle: Detecting Complex Neural Trojans in Data-Free CasesLLM safety and security → Backdoor and data poisoning attacks
- Efficient Masked Autoencoders with Self-ConsistencyLLM reasoning → Test-time compute and efficient thinking
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Linear Spaces of Meanings: Compositional Structures in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- The In-Sample Softmax for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling MethodsDiffusion models → Diffusion foundations and sampling
- Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- FTSO: Effective NAS via First Topology Second Operator
- Interpersonal Distance Tracking with mmWave Radar and IMUs
- Practice of the conformer enhanced AUDIO-VISUAL HUBERT on Mandarin and English
- Thrill-K Architecture: Towards a Solution to the Problem of Knowledge Based Understanding
- Knowledge Discovery from Atomic Structures using Feature Importances
- The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of Paintings
- Human-Inspired Framework to Accelerate Reinforcement Learning
- An evaluation of Google Translate for Sanskrit to English translation via sentiment and semantic analysis
- Towards Measuring Ethicality of an Intelligent Assistive System
- PANACEA: An Automated Misinformation Detection System on COVID-19
- Semi-decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approach
- Semi-Supervised Constrained Clustering: An In-Depth Overview, Ranked Taxonomy and Future Research Directions
- Valid Information Guidance Network for Compressed Video Quality Enhancement
- Exploiting Multiple Abstractions in Episodic RL via Reward Shaping
- Interpretable Water Level Forecaster with Spatiotemporal Causal Attention Mechanisms
- Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction
- Texture-Based Input Feature Selection for Action Recognition
- PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing
- Deep learning for COVID-19 topic modelling via Twitter: Alpha, Delta and Omicron
- Representation Disentaglement via Regularization by Causal Identification
- Neural Auctions Compromise Bidder Information
- PixCUE: Joint Uncertainty Estimation and Image Reconstruction in MRI using Deep Pixel Classification
- The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
- Scalability and Sample Efficiency Analysis of Graph Neural Networks for Power System State Estimation
- A study on the use of perceptual hashing to detect manipulation of embedded messages in images
- Applying Plain Transformers to Real-World Point Clouds
- AR3n: A Reinforcement Learning-based Assist-As-Needed Controller for Robotic Rehabilitation
- Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics
- ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus
- Neural Nonnegative Matrix Factorization for Hierarchical Multilayer Topic Modeling
- Learning time-scales in two-layers neural networks
- Dynamic Multi-View Scene Reconstruction Using Neural Implicit Surface
- Edit at your own risk: evaluating the robustness of edited models to distribution shifts
- Efficient Approximate Recovery from Pooled Data Using Doubly Regular Pooling Schemes
- Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training
- M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
- Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy
- Tiny Classifier Circuits: Evolving Accelerators for Tabular Data
- Efficient Sensor Placement from Regression with Sparse Gaussian Processes in Continuous and Discrete Spaces
- Parameter Optimization of LLC-Converter with multiple operation points using Reinforcement Learning
- Multi-view Semantic Consistency based Information Bottleneck for Clustering
- BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis
- An Efficient Tester-Learner for Halfspaces
- High Probability Convergence of Stochastic Gradient Methods
- EvoPrompting: Language Models for Code-Level Neural Architecture Search
- Novel Machine Learning Approach for Predicting Poverty using Temperature and Remote Sensing Data in Ethiopia
- FacEDiM: A Face Embedding Distribution Model for Few-Shot Biometric Authentication of Cattle
- Automatic Scoring of Dream Reports' Emotional Content with Large Language Models
- Opto-UNet: Optimized UNet for Segmentation of Varicose Veins in Optical Coherence Tomography
- DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion
- Framelet Message Passing
- Learned Risk Metric Maps for Kinodynamic Systems
- Particle-based Online Bayesian Sampling
- 3D Coronary Vessel Reconstruction from Bi-Plane Angiography using Graph Convolutional Networks
- Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
- Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation
- Time Series Anomaly Detection in Smart Homes: A Deep Learning Approach
- VQA with Cascade of Self- and Co-Attention Blocks
- PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
- Generic-to-Specific Distillation of Masked Autoencoders
- Completeness of Atomic Structure Representations
- Kartezio: Evolutionary Design of Explainable Pipelines for Biomedical Image Analysis
- Identifying roadway departure crash patterns on rural two-lane highways under different lighting conditions: association knowledge using data mining approach
- Learning Hidden Markov Models Using Conditional Samples
- Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
- Tight Mixed-Integer Optimization Formulations for Prescriptive Trees
- Fusion of ML with numerical simulation for optimized propeller design
- Deep Learning for Mean Field Optimal Transport
- TextIR: A Simple Framework for Text-based Editable Image Restoration
- Constrained Bayesian Optimization for Automatic Underwater Vehicle Hull Design
- Semantically Consistent Person Image Generation
- Automatically Classifying Emotions based on Text: A Comparative Exploration of Different Datasets
- Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
- Minimizing the Outage Probability in a Markov Decision Process
- Generating Accurate Virtual Examples For Lifelong Machine Learning
- Is Japanese CCGBank empirically correct? A case study of passive and causative constructions
- AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers
- Heuristic Modularity Maximization Algorithms for Community Detection Rarely Return an Optimal Partition or Anything Similar
- Dissolving Is Amplifying: Towards Fine-Grained Anomaly Detection
- Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels
- Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following
- On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
- OEKG: The Open Event Knowledge Graph
- Approximately Stationary Bandits with Knapsacks
All 244
- DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks
- IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRF
- Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue
- Graph Reinforcement Learning for Operator Selection in the ALNS Metaheuristic
- Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
- Attention-based Point Cloud Edge Sampling
- Balanced Training for Sparse GANs
- Parametrizing Product Shape Manifolds by Composite Networks
- Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation
- H-AES: Towards Automated Essay Scoring for Hindi
- mmSense: Detecting Concealed Weapons with a Miniature Radar Sensor
- The 2022 NIST Language Recognition Evaluation
- Fast as CHITA: Neural Network Pruning with Combinatorial Optimization
- Metric Learning Improves the Ability of Combinatorial Coverage Metrics to Anticipate Classification Error
- IQ-Flow: Mechanism Design for Inducing Cooperative Behavior to Self-Interested Agents in Sequential Social Dilemmas
- Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers
- Transitions between quasi-stationary states in traffic systems: Cologne orbital motorways as an example
- MateRobot: Material Recognition in Wearable Robotics for People with Visual Impairments
- Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation
- Decentralised construction of a global coordinate system in a large swarm of minimalistic robots
- HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation
- Interactive Segmentation as Gaussian Process Classification
- Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits
- A Little Bit Attention Is All You Need for Person Re-Identification
- Active Learning with Combinatorial Coverage
- Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition
- GRAN: Ghost Residual Attention Network for Single Image Super Resolution
- FPCD: An Open Aerial VHR Dataset for Farm Pond Change Detection
- Toward Robust Uncertainty Estimation with Random Activation Functions
- Safe-DS: A Domain Specific Language to Make Data Science Safe
- Modern Bayesian Experimental Design
- Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face
- DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis
- Maximum Likelihood With a Time Varying Parameter
- Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners
- AdaptiveShape: Solving Shape Variability for 3D Object Detection with Geometry Aware Anchor Distributions
- Steganography of Steganographic Networks
- Large Language Models Are State-of-the-Art Evaluators of Translation Quality
- Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage
- Arbitrary Decisions are a Hidden Cost of Differentially Private Training
- Learnt Deep Hyperparameter selection in Adversarial Training for compressed video enhancement with perceptual critic
- Differentially Private Distributed Convex Optimization
- A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation
- Bayesian Kernelized Tensor Factorization as Surrogate for Bayesian Optimization
- Policy Dispersion in Non-Markovian Environment
- A Survey on Long Text Modeling with Transformers
- Text classification dataset and analysis for Uzbek language
- Estimating Head Motion from MR-Images
- Enhancing Classification with Hierarchical Scalable Query on Fusion Transformer
- TrainSim: A Railway Simulation Framework for LiDAR and Camera Dataset Generation
- Memory-aided Contrastive Consensus Learning for Co-salient Object Detection
- RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
- Scenarios and branch points to future machine intelligence
- Benchmarking Deepart Detection
- Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming
- Safe Peeling for L0-Regularized Least-Squares with supplementary material
- Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision
- SAINE: Scientific Annotation and Inference Engine of Scientific Research
- Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitis
- Ultra-low Precision Multiplication-free Training for Deep Neural Networks
- An Effective Crop-Paste Pipeline for Few-shot Object Detection
- Hierarchical Reinforcement Learning in Complex 3D Environments
- Swin Deformable Attention Hybrid U-Net for Medical Image Segmentation
- Reproducing kernel Hilbert spaces in the mean field limit
- Learning to Estimate Two Dense Depths from LiDAR and Event Data
- City-scale Pollution Aware Traffic Routing by Sampling Max Flows using MCMC
- Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation
- ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
- A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images
- Tracking Fast by Learning Slow: An Event-based Speed Adaptive Hand Tracker Leveraging Knowledge in RGB Domain
- Stochastic Gradient Descent under Markovian Sampling Schemes
- Federated Covariate Shift Adaptation for Missing Target Output Values
- PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
- DREAM: Efficient Dataset Distillation by Representative Matching
- Mesh-SORT: Simple and effective location-wise tracker with lost management strategies
- SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases
- An Algorithm and Complexity Results for Causal Unit Selection
- Distributed Subweb Specifications for Traversing the Web
- An Adaptive Method for Camera Attribution under Complex Radial Distortion Corrections
- Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Dataset
- Neural Video Compression with Diverse Contexts
- GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
- Multi-Agent Reinforcement Learning for Pragmatic Communication and Control
- Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up
- Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting
- Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context
- Practical Algorithms for Orientations of Partially Directed Graphical Models
- GNOT: A General Neural Operator Transformer for Operator Learning
- CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis
- BrainBERT: Self-supervised representation learning for intracranial recordings
- RemoteTouch: Enhancing Immersive 3D Video Communication with Hand Touch
- Efficient Implicit Neural Reconstruction Using LiDAR
- One-Shot Video Inpainting
- A Unified Representation Framework for Rideshare Marketplace Equilibrium and Efficiency
- A Token-Wise Beam Search Algorithm for RNN-T
- Deep Learning for Identifying Iran's Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM
- A semantic backdoor attack against Graph Convolutional Networks
- Knowledge Augmented Relation Inference for Group Activity Recognition
- Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes
- Sampled Transformer for Point Sets
- HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization
- Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization
- Turning a CLIP Model into a Scene Text Detector
- UniFLG: Unified Facial Landmark Generator from Text or Speech
- DC-Former: Diverse and Compact Transformer for Person Re-Identification
- Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfer
- Towards Personalized Preprocessing Pipeline Search
- BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images
- Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm
- (αD,αG)-GANs: Addressing GAN Training Instabilities via Dual Objectives
- Auxiliary Task-based Deep Reinforcement Learning for Quantum Control
- Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks
- Temporal Coherent Test-Time Optimization for Robust Video Classification
- GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting
- CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping
- Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
- Gradient-Boosted Based Structured and Unstructured Learning
- WISK: A Workload-aware Learned Index for Spatial Keyword Queries
- HugNLP: A Unified and Comprehensive Library for Natural Language Processing
- Rethink Long-tailed Recognition with Vision Transformers
- Multi-Layer Attention-Based Explainability via Transformers for Tabular Data
- DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features
- On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning
- Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
- Adversarial Attack with Raindrops
- RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention
- Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition
- A Closer Look at the Intervention Procedure of Concept Bottleneck Models
- Remote Sensing Scene Classification with Masked Image Modeling (MIM)
- Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
- Time-uniform confidence bands for the CDF under nonstationarity
- Sequential edge detection using joint hierarchical Bayesian learning
- Nonlinear Intensity, Scale and Rotation Invariant Matching for Multimodal Images
- Towards Surgical Context Inference and Translation to Gestures
- Goal Driven Discovery of Distributional Differences via Language Descriptions
- CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling
- Zero-Shot Cross-Lingual Summarization via Large Language Models
- A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions
- Weighted Sampling for Masked Language Modeling
- Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
- Global Proxy-based Hard Mining for Visual Place Recognition
- Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments
- Semantic Strengthening of Neuro-Symbolic Learning