Papers
Thu 26 Jan 2023
173 papers
- Understanding and contextualising diffusion modelsDiffusion models → Diffusion foundations and sampling
- Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real GeneralizationDiffusion models → Inverse problems and image restoration
- 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Learning Modulo TheoriesLLM reasoning → Reasoning benchmarks and evaluation
- Model-based Offline Reinforcement Learning with Local MisspecificationOffline RL and imitation learning from data → Offline RL algorithms
- Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise ComparisonsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based DisparitiesMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
- Simple diffusion: End-to-end diffusion for high resolution imagesDiffusion models → Diffusion foundations and sampling
- On the Importance of Noise Scheduling for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Causal Reasoning of Entities and Events in Procedural TextsLLM reasoning → Causal reasoning in LLMs
- Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
- normflows: A PyTorch Package for Normalizing Flows
- SparCA: Sparse Compressed Agglomeration for Feature Extraction and Dimensionality Reduction
- Potential Penetrative Pass (P3)
- Noncommutative C^*-algebra Net: Learning Neural Networks with Powerful Product Structure in C^*-algebra
- LAGAN: Deep Semi-Supervised Linguistic-Anthropology Classification with Conditional Generative Adversarial Neural Network
- Is Writing Prompts Really Making Art?
- Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing
- Transition-Aware Multi-Activity Knowledge Tracing
- Invariant Meta Learning for Out-of-Distribution Generalization
- Cross-domain recommendation via user interest alignment
- Nik Defense: An Artificial Intelligence Based Defense Mechanism against Selfish Mining in Bitcoin
- How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech
- Learning to Generate All Feasible Actions
- Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification
- Attacking Important Pixels for Anchor-free Detectors
- Graph Scattering beyond Wavelet Shackles
- Boundary Aware U-Net for Glacier Segmentation
- Personalised Federated Learning On Heterogeneous Feature Spaces
- Limitless stability for Graph Convolutional Networks
- Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits
- Semidefinite Relaxations for Robust Multiview Triangulation
- RMSim: Controlled Respiratory Motion Simulation on Static Patient Scans
- Efficiently predicting high resolution mass spectra with graph neural networks
- Parkinson gait modelling from an anomaly deep representation
- Are Labels Needed for Incremental Instance Learning?
- Feature space exploration as an alternative for design space exploration beyond the parametric space
- A Simple Algorithm For Scaling Up Kernel Methods
- DBGDGM: Dynamic Brain Graph Deep Generative Model
- Beyond Arabic: Software for Perso-Arabic Script Manipulation
- Discriminative Entropy Clustering and its Relation to K-means and SVM
- Detecting Pump&Dump Stock Market Manipulation from Online Forums
- A Hybrid Deep Neural Operator/Finite Element Method for Ice-Sheet Modeling
- Causal Bandits without Graph Learning
- Class-Incremental Learning with Repetition
- Universal Domain Adaptation for Remote Sensing Image Scene Classification
- Task formulation for Extracting Social Determinants of Health from Clinical Narratives
- MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods
- How does training shape the Riemannian geometry of neural network representations?
- Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation
- Coincident Learning for Unsupervised Anomaly Detection
- Style-Aware Contrastive Learning for Multi-Style Image Captioning
- Improving Cross-modal Alignment for Text-Guided Image Inpainting
- The Power of Linear Combinations: Learning with Random Convolutions
- Multimodal Event Transformer for Image-guided Story Ending Generation
- Rigid Body Flows for Sampling Molecular Crystal Structures
- Estimating Causal Effects using a Multi-task Deep Ensemble
- A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
- Causal Structural Learning from Time Series: A Convex Optimization Approach
- Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
- Unsupervised Volumetric Animation
- MusicLM: Generating Music From Text
- Certified Interpretability Robustness for Class Activation Mapping
- Joint Training of Deep Ensembles Fails Due to Learner Collusion
- Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
- Cut and Learn for Unsupervised Object Detection and Instance Segmentation
- Open Problems in Applied Deep Learning
- Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations
- LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware Summarization
- Learning Good Features to Transfer Across Tasks and Domains
- SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification
- Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
- DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
- Minimax estimation of discontinuous optimal transport maps: The semi-discrete case
- ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients
- Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates
- Understanding Finetuning for Factual Knowledge Extraction from Language Models
- Real-Time Digital Twins: Vision and Research Directions for 6G and Beyond
- Text-To-4D Dynamic Scene Generation
- Gaussian process regression and conditional Karhunen-Lo'eve models for data assimilation in inverse problems
- Self-Supervised RGB-T Tracking with Cross-Input Consistency
- AlignGraph: A Group of Generative Models for Graphs
- Online Convex Optimization with Stochastic Constraints: Zero Constraint Violation and Bandit Feedback
- Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming
- Domain-Agnostic Molecular Generation with Chemical Feedback
- A Benchmark Study by using various Machine Learning Models for Predicting Covid-19 trends
- On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
- BiBench: Benchmarking and Analyzing Network Binarization
- Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?
- Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge
- Relative-Interior Solution for the (Incomplete) Linear Assignment Problem with Applications to the Quadratic Assignment Problem
- I-24 MOTION: An instrument for freeway traffic science
- Causal Graph Discovery from Self and Mutually Exciting Time Series
- Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
- Smoothed Online Learning for Prediction in Piecewise Affine Systems
- Deep Laplacian-based Options for Temporally-Extended Exploration
- Low-Rank Winograd Transformation for 3D Convolutional Neural Networks
- Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data
- Double Deep Reinforcement Learning Techniques for Low Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots
- Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout
All 173
- Neural Inverse Operators for Solving PDE Inverse Problems
- A Graph Neural Network with Negative Message Passing for Graph Coloring
- Convolutional Learning on Simplicial Complexes
- New Approach to Malware Detection Using Optimized Convolutional Neural Network
- Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images
- Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning
- Train Hard, Fight Easy: Robust Meta Reinforcement Learning
- Two-step interpretable modeling of Intensive Care Acquired Infections
- Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation
- Conformal Prediction for Trustworthy Detection of Railway Signals
- FedHQL: Federated Heterogeneous Q-Learning
- A benchmark for toxic comment classification on Civil Comments dataset
- SQ Lower Bounds for Random Sparse Planted Vector Problem
- Dual Box Embeddings for the Description Logic EL++
- Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
- Finding Regions of Counterfactual Explanations via Robust Optimization
- uHelp: intelligent volunteer search for mutual help communities
- Discovering and Mitigating Visual Biases through Keyword Explanation
- Federated Learning over Coupled Graphs
- Generalized Planning as Heuristic Search: A new planning search-space that leverages pointers over objects
- Inspecting class hierarchies in classification-based metric learning models
- Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning
- Minerva: A File-Based Ransomware Detector
- A Systematic Review of Green AI
- Incomplete Multi-view Clustering via Prototype-based Imputation
- Random Grid Neural Processes for Parametric Partial Differential Equations
- WL meet VC
- Paraphrase Acquisition from Image Captions
- Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction
- Explore the Power of Dropout on Few-shot Learning
- Privacy-Preserving Joint Edge Association and Power Optimization for the Internet of Vehicles via Federated Multi-Agent Reinforcement Learning
- NLP as a Lens for Causal Analysis and Perception Mining to Infer Mental Health on Social Media
- PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices
- Multi-Agent Congestion Cost Minimization With Linear Function Approximations
- Neural Dynamic Focused Topic Model
- Time-sensitive Learning for Heterogeneous Federated Edge Intelligence
- Visiting Distant Neighbors in Graph Convolutional Networks
- Learning Large Scale Sparse Models
- Neurorehab: An Interface for Rehabilitation
- Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
- Cross Modal Global Local Representation Learning from Radiology Reports and X-Ray Chest Images
- Message Ritual: A Posthuman Account of Living with Lamp
- A Fully First-Order Method for Stochastic Bilevel Optimization
- GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency
- Affective Faces for Goal-Driven Dyadic Communication
- Compact Transformer Tracker with Correlative Masked Modeling
- Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
- PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation
- On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures
- Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
- Towards Knowledge-Centric Process Mining
- Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
- Detecting Building Changes with Off-Nadir Aerial Images
- SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning
- Partial advantage estimator for proximal policy optimization
- Joint action loss for proximal policy optimization
- ITstyler: Image-optimized Text-based Style Transfer
- Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
- Proximal Causal Learning of Conditional Average Treatment Effects
- Distilling Cognitive Backdoor Patterns within an Image
- Facial Expression Recognition using Squeeze and Excitation-powered Swin Transformers
- GPU-based Private Information Retrieval for On-Device Machine Learning Inference
- Efficient Hyperdimensional Computing
- Re-embedding data to strengthen recovery guarantees of clustering
- Graph Contrastive Learning for Skeleton-based Action Recognition
- Planning Automated Driving with Accident Experience Referencing and Common-sense Inferencing
- Experimenting with an Evaluation Framework for Imbalanced Data Learning (EFIDL)
- Improving Text-based Early Prediction by Distillation from Privileged Time-Series Text
- Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
- Break It Down: Evidence for Structural Compositionality in Neural Networks
- SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference
- The Projection-Enhancement Network (PEN)
- Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing