Papers

New on arXiv

Tue 6 Dec 2022

194 papers

Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised LearningLLM safety and security → Backdoor and data poisoning attacks
Enhancing Low-Density EEG-Based Brain-Computer Interfaces with Similarity-Keeping Knowledge DistillationKnowledge distillation → Distillation for medical imaging
Receding Horizon Planning with Rule Hierarchies for Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
Counterfactual reasoning: Do language models need world knowledge for causal understanding?LLM reasoning → Causal reasoning in LLMs
NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image PriorsDiffusion models → 3D, point cloud and scene generation
Complex-valued Retrievals From Noisy Images Using Diffusion ModelsDiffusion models → Inverse problems and image restoration
ADIR: Adaptive Diffusion for Image ReconstructionDiffusion models → Inverse problems and image restoration
Misspecification in Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
Neural Machine Translation with Contrastive Translation MemoriesRetrieval-augmented generation → Generation and context integration
Semantic-Conditional Diffusion Networks for Image CaptioningDiffusion models → Image generation, text-to-image and editing
Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker RecognitionKnowledge distillation → Speech and audio distillation
PRISM: Probabilistic Real-Time Inference in Spatial World ModelsWorld models → World models for navigation
Denoising diffusion probabilistic models for probabilistic energy forecastingDiffusion models → Flow matching, time series and science
Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible RobotsOffline RL and imitation learning from data → Imitation learning methods
M-VADER: A Model for Diffusion with Multimodal ContextMultimodal LLMs / vision-language models → Image editing and quality assessment +1
Leveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical ImagingKnowledge distillation → General knowledge distillation methods
Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modellingEnd-to-end autonomous driving → Cooperative and V2X driving
Pretrained Diffusion Models for Unified Human Motion SynthesisDiffusion models → Video generation
Life-long Learning for Multilingual Neural Machine Translation with Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic ModelDiffusion models → 3D, point cloud and scene generation
Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-DistillationKnowledge distillation → Speech and audio distillation
DiffusionInst: Diffusion Model for Instance SegmentationDiffusion models → Medical imaging and segmentation
Safe Inverse Reinforcement Learning via Control Barrier FunctionOffline RL and imitation learning from data → Safe offline RL
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical ExpressionLLM reasoning → Spatial and embodied reasoning
On the Discredibility of Membership Inference AttacksLLM safety and security → Membership inference attacks
An open unified deep graph learning framework for discovering drug leads
Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising
Channel charting based beamforming
PoissonMat: Remodeling Matrix Factorization using Poisson Distribution and Solving the Cold Start Problem without Input Data
Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems
Extending Universal Approximation Guarantees: A Theoretical Justification for the Continuity of Real-World Learning Tasks
A machine learning approach to support decision in insider trading detection
Three Variations on Variational Autoencoders
GAUCHE: A Library for Gaussian Processes in Chemistry
Dynamic Decision Frequency with Continuous Options
Robust Speech Recognition via Large-Scale Weak Supervision
Fuzzy Rough Sets Based on Fuzzy Quantification
Reinforcement Learning for UAV control with Policy and Reward Shaping
Intent Recognition in Conversational Recommender Systems
Enhanced Multi-Objective A* with Partial Expansion
Fine-tuned CLIP Models are Efficient Video Learners
Unsupervised Anomaly Detection in Time-series: An Extensive Evaluation and Analysis of State-of-the-art Methods
Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration
KATSum: Knowledge-aware Abstractive Text Summarization
Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE
Exploring Randomly Wired Neural Networks for Climate Model Emulation
Further analysis of multilevel Stein variational gradient descent with an application to the Bayesian inference of glacier ice models
Few-Shot Preference Learning for Human-in-the-Loop RL
Domain Translation via Latent Space Mapping
Contactless Oxygen Monitoring with Gated Transformer
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
Framework-agnostic Semantically-aware Global Reasoning for Segmentation
A neural approach to synchronization in wireless networks with heterogeneous sources of noise
Proposal of a Score Based Approach to Sampling Using Monte Carlo Estimation of Score and Oracle Access to Target Density
Reinforcement Learning for Molecular Dynamics Optimization: A Stochastic Pontryagin Maximum Principle Approach
Understanding Self-Predictive Learning for Reinforcement Learning
Drift Identification for L'evy alpha-Stable Stochastic Systems
ERNet: Unsupervised Collective Extraction and Registration in Neuroimaging Data
Supervised Tractogram Filtering using Geometric Deep Learning
Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection System
MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples
Copula Conformal Prediction for Multi-step Time Series Forecasting
ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration
Giga-SSL: Self-Supervised Learning for Gigapixel Images
First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation
Neural Cell Video Synthesis via Optical-Flow Diffusion
Robust Point Cloud Segmentation with Noisy Annotations
PODA: Prompt-driven Zero-shot Domain Adaptation
Perspective Fields for Single Image Camera Calibration
Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
RANA: Relightable Articulated Neural Avatars
Self-Supervised Correspondence Estimation via Multiview Registration
Learning the joint distribution of two sequences using little or no paired data
Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
ISAACS: Iterative Soft Adversarial Actor-Critic for Safety
Financial Risk Management on a Neutral Atom Quantum Processor
LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Towards Energy Efficient Mobile Eye Tracking for AR Glasses through Optical Sensor Technology
An Unsupervised Machine Learning Approach for Ground-Motion Spectra Clustering and Selection
Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
A Learned Simulation Environment to Model Plant Growth in Indoor Farming
FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer
Explainability as statistical inference
Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations
Robust convex biclustering with a tuning-free method
Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion
Straggler-Resilient Differentially-Private Decentralized Learning
Active Classification of Moving Targets with Learned Control Policies
Causal Inference via Style Transfer for Out-of-distribution Generalisation
Uniform-in-time propagation of chaos for mean field Langevin dynamics
On the Importance of Clinical Notes in Multi-modal Learning for EHR Data
Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using Myerson values
Unifying Short and Long-Term Tracking with Graph Hierarchies
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

All 194