Papers
Mon 3 Oct 2022
201 papers
- Red-Teaming the Stable Diffusion Safety FilterDiffusion models → Robustness, privacy and adversarial aspects +1
- Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental ProbesLLM reasoning → Reasoning benchmarks and evaluation
- PLOT: Prompt Learning with Optimal Transport for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-ThoughtLLM reasoning → Reasoning benchmarks and evaluation
- Robust Active DistillationKnowledge distillation → General knowledge distillation methods
- WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point IterationDiffusion models → Audio, speech and music
- Reward Learning with Trees: Methods and EvaluationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Dissipative Imitation Learning for Robust Dynamic Output FeedbackOffline RL and imitation learning from data → Imitation learning methods
- Membership Inference Attacks Against Text-to-image Generation ModelsLLM safety and security → Membership inference attacks
- Attention Distillation: self-supervised vision transformer students need more guidanceKnowledge distillation → General knowledge distillation methods
- Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceDiffusion models → Diffusion foundations and sampling
- Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic ApproachLLM reasoning → Spatial and embodied reasoning
- Offline Reinforcement Learning with Differentiable Function Approximation is Provably EfficientOffline RL and imitation learning from data → Offline RL algorithms
- Complexity-Based Prompting for Multi-Step ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
- Automated Identification of Tree Species by Bark Texture Classification Using Convolutional Neural Networks
- Towards sustainability assessment of artificial intelligence in artistic practices
- Wild Animal Classifier Using CNN
- Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication
- Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity
- Russian Web Tables: A Public Corpus of Web Tables for Russian Language Based on Wikipedia
- Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond
- Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models
- When Infodemic Meets Epidemic: a Systematic Literature Review
- Integrating Digital Twin and Advanced Intelligent Technologies to Realize the Metaverse
- Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems
- A machine learning based algorithm selection method to solve the minimum cost flow problem
- On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
- CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
- Federated Graph-based Networks with Shared Embedding
- Alternating Differentiation for Optimization Layers
- Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection
- Probabilistic Volumetric Fusion for Dense Monocular SLAM
- Random Weight Factorization Improves the Training of Continuous Neural Representations
- A systematic review of the use of Deep Learning in Satellite Imagery for Agriculture
- Interpretable Deep Tracking
- Understanding Substructures in Commonsense Relations in ConceptNet
- Enriching Vulnerability Reports Through Automated and Augmented Description Summarization
- Testing predictions of representation cost theory with CNNs
- And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?
- Estimating productivity gains in digital automation
- LOPR: Latent Occupancy PRediction using Generative Models
- Random orthogonal additive filters: a solution to the vanishing/exploding gradient of deep neural networks
- Event-based Temporally Dense Optical Flow Estimation with Sequential Learning
- Learning over time using a neuromorphic adaptive control algorithm for robotic arms
- Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
- Bayes-optimal limits in structured PCA, and how to reach them
- CaiRL: A High-Performance Reinforcement Learning Environment Toolkit
- Optimizing Data Collection for Machine Learning
- Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders
- Estimating the Performance of Entity Resolution Algorithms: Lessons Learned Through PatentsView.org
- Force-Aware Interface via Electromyography for Natural VR/AR Interaction
- One-shot Detail Retouching with Patch Space Neural Transformation Blending
- spred: Solving L1 Penalty with SGD
- A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
- Automatic Assessment of Functional Movement Screening Exercises with Deep Learning Architectures
- Diagnosis of Parkinson's Disease Based on Voice Signals Using SHAP and Hard Voting Ensemble Method
- SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scene
- Extending Compositional Attention Networks for Social Reasoning in Videos
- Rank-N-Contrast: Learning Continuous Representations for Regression
- ContraCLM: Contrastive Learning For Causal Language Model
- Introducing Vision Transformer for Alzheimer's Disease classification task with 3D input
- PersA-FL: Personalized Asynchronous Federated Learning
- TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation
- NARF22: Neural Articulated Radiance Fields for Configuration-Aware Rendering
- Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications
- Unbounded Gradients in Federated Learning with Buffered Asynchronous Aggregation
- Wheel Impact Test by Deep Learning: Prediction of Location and Magnitude of Maximum Stress
- Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep Reconstruction without Reference
- Automatic Neural Network Hyperparameter Optimization for Extrapolation: Lessons Learned from Visible and Near-Infrared Spectroscopy of Mango Fruit
- Omnigrok: Grokking Beyond Algorithmic Data
- That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulation
- LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
- Generative Category-Level Shape and Pose Estimation with Semantic Primitives
- MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples
- SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis
- The (In)Effectiveness of Intermediate Task Training For Domain Adaptation and Cross-Lingual Transfer Learning
- Nonstationary data stream classification with online active learning and siamese neural networks
- On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
- Unsupervised Model Selection for Time-series Anomaly Detection
- Improving Convolutional Neural Networks for Fault Diagnosis by Assimilating Global Features
- Decompiling x86 Deep Neural Network Executables
- Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
- Understanding Influence Functions and Datamodels via Harmonic Analysis
- New Paradigms for Exploiting Parallel Experiments in Bayesian Optimization
- Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration
- Factor-Augmented Regularized Model for Hazard Regression
- On Stability and Generalization of Bilevel Optimization Problem
- Generating Hidden Markov Models from Process Models Through Nonnegative Tensor Factorization
- CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
- Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
- SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image
- Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
- LPT: Long-tailed Prompt Tuning for Image Classification
- A New Hip Fracture Risk Index Derived from FEA-Computed Proximal Femur Fracture Loads and Energies-to-Failure
- The Long Tail of Context: Does it Exist and Matter?
- Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfaction
- Plateau in Monotonic Linear Interpolation -- A "Biased" View of Loss Landscape for Deep Networks
- Neural network for determining an asteroid mineral composition from reflectance spectra
- ASGNN: Graph Neural Networks with Adaptive Structure
- Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
All 201
- Latent State Marginalization as a Low-cost Approach for Improving Exploration
- Online Self-Concordant and Relatively Smooth Minimization, With Applications to Online Portfolio Selection and Learning Quantum States
- Efficient Bayes Inference in Neural Networks through Adaptive Importance Sampling
- Feature Embedding by Template Matching as a ResNet Block
- Policy Gradient for Reinforcement Learning with General Utilities
- Visual Prompt Tuning for Generative Transfer Learning
- Data Budgeting for Machine Learning
- A Comparative Study of Hierarchical Risk Parity Portfolio and Eigen Portfolio on the NIFTY 50 Stocks
- Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
- DOTIE - Detecting Objects through Temporal Isolation of Events using a Spiking Architecture
- Dealing with Unknown Variances in Best-Arm Identification
- NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning
- Green Learning: Introduction, Examples and Outlook
- Stability Analysis and Generalization Bounds of Adversarial Training
- UnGANable: Defending Against GAN-based Face Manipulation
- Machine Learning-Powered Course Allocation
- Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
- Hierarchical I3D for Sign Spotting
- Optimal consumption-investment choices under wealth-driven risk aversion
- Block-wise Training of Residual Networks via the Minimizing Movement Scheme
- Cooperative Multi-Agent Deep Reinforcement Learning for Reliable and Energy-Efficient Mobile Access via Multi-UAV Control
- Simple Pooling Front-ends For Efficient Audio Classification
- Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning
- How Relevant is Selective Memory Population in Lifelong Language Learning?
- Analysis of (sub-)Riemannian PDE-G-CNNs
- Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop
- PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales
- Multi-view object pose estimation from correspondence distributions and epipolar geometry
- Masked Supervised Learning for Semantic Segmentation
- Unbiased Scene Graph Generation using Predicate Similarities
- Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On
- Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer
- Learning Equivariant Segmentation with Instance-Unique Querying
- Hypothesis Engineering for Zero-Shot Hate Speech Detection
- The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection
- CBLab: Supporting the Training of Large-scale Traffic Control Policies with Scalable Traffic Simulation
- Smart-Badge: A wearable badge with multi-modal sensors for kitchen activity recognition
- Generating Synthetic Data with Locally Estimated Distributions for Disclosure Control
- MSRL: Distributed Reinforcement Learning with Dataflow Fragments
- Requirements Engineering for Machine Learning: A Review and Reflection
- Review of Clustering Methods for Functional Data
- Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition
- Smooth image-to-image translations with latent space interpolations
- Merging Classification Predictions with Sequential Information for Lightweight Visual Place Recognition in Changing Environments
- Square-root regret bounds for continuous-time episodic Markov decision processes
- Mastering Spatial Graph Prediction of Road Networks
- Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data
- Random Data Augmentation based Enhancement: A Generalized Enhancement Approach for Medical Datasets
- BVI-VFI: A Video Quality Database for Video Frame Interpolation
- Combinatorial and algebraic perspectives on the marginal independence structure of Bayesian networks
- A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training
- Limitations of neural network training due to numerical instability of backpropagation
- IPPO: Obstacle Avoidance for Robotic Manipulators in Joint Space via Improved Proximal Policy Optimization
- DDoS: A Graph Neural Network based Drug Synergy Prediction Algorithm
- HPC Storage Service Autotuning Using Variational-Autoencoder-Guided Asynchronous Bayesian Optimization
- Towards a Unified View on Visual Parameter-Efficient Transfer Learning
- Accelerate Reinforcement Learning with PID Controllers in the Pendulum Simulations
- Unsupervised Search Algorithm Configuration using Query Performance Prediction
- Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancement
- Relational program synthesis with numerical reasoning
- Meta-Learning Priors for Safe Bayesian Optimization
- Fully Transformer Network for Change Detection of Remote Sensing Images
- CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning
- D'etection de petites cibles par apprentissage profond et crit`ere a contrario
- Lexical semantics enhanced neural word embeddings
- Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection
- From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution
- An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks
- Heatmap Distribution Matching for Human Pose Estimation
- Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests
- A large sample theory for infinitesimal gradient boosting
- A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning
- Sentiment Analysis of ESG disclosures on Stock Market
- Deep Spatial Domain Generalization
- Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples
- Privacy-Preserving Feature Coding for Machines
- Statistical Efficiency of Score Matching: The View from Isoperimetry
- GenDexGrasp: Generalizable Dexterous Grasping
- Efficient acoustic feature transformation in mismatched environments using a Guided-GAN
- rPPG-Toolbox: Deep Remote PPG Toolbox
- WorldGen: A Large Scale Generative Simulator
- Efficient Meta-Learning for Continual Learning with Taylor Expansion Approximation
- PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement
- EraseNet: A Recurrent Residual Network for Supervised Document Cleaning
- Theme and Topic: How Qualitative Research and Topic Modeling Can Be Brought Together
- Information-Theoretic Analysis of Unsupervised Domain Adaptation
- SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
- Combined Dynamic Virtual Spatiotemporal Graph Mapping for Traffic Prediction
- Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
- NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation
- Taming Fat-Tailed ("Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning
- Multipod Convolutional Network
- On the infinite-depth limit of finite-width neural networks
- High Probability Convergence for Accelerated Stochastic Mirror Descent
- Some pointwise and decidable properties of non-uniform cellular automata
- Multi-view information fusion using multi-view variational autoencoders to predict proximal femoral strength
- Deep Learning for Wireless Networked Systems: a joint Estimation-Control-Scheduling Approach
- Probing of Quantitative Values in Abstractive Summarization Models
- Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithms
- Under the Cover Infant Pose Estimation using Multimodal Data
- A Non-monotonic Self-terminating Language Model