Papers
Fri 27 Jan 2023
177 papers
- Improved knowledge distillation by utilizing backward pass knowledge in neural networksKnowledge distillation → General knowledge distillation methods
- EmbedDistill: A Geometric Knowledge Distillation for Information RetrievalKnowledge distillation → Knowledge distillation for LLMs
- Minimizing Trajectory Curvature of ODE-based Generative ModelsDiffusion models → Diffusion foundations and sampling
- Case-Based Reasoning with Language Models for Classification of Logical FallaciesLLM reasoning → Reasoning benchmarks and evaluation
- Reinforcement Learning from Diverse Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Mousai: Text-to-Music Generation with Long-Context Latent DiffusionDiffusion models → Audio, speech and music
- Improving Behavioural Cloning with Positive Unlabeled LearningOffline RL and imitation learning from data → Imitation learning methods
- Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?Diffusion models → Image generation, text-to-image and editing
- Input Perturbation Reduces Exposure Bias in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?Knowledge distillation → Knowledge distillation for LLMs
- Theoretical Analysis of Offline Imitation With Supplementary DatasetOffline RL and imitation learning from data → Imitation learning methods
- A Denoising Diffusion Model for Fluid Field PredictionDiffusion models → Flow matching, time series and science
- ThoughtSource: A central hub for large language model reasoning dataLLM reasoning → Prompting and chain-of-thought reasoning
- Learning to Unlearn: Instance-wise Unlearning for Pre-trained ClassifiersLLM safety and security → Machine unlearning
- Accelerating Guided Diffusion Sampling with Splitting Numerical MethodsDiffusion models → Diffusion foundations and sampling
- PLay: Parametrically Conditioned Layout Generation using Latent DiffusionDiffusion models → Image generation, text-to-image and editing
- Talk the Walk: Synthetic Data Generation for Conversational Music RecommendationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Effect of temporal resolution on the reproduction of chaotic dynamics via reservoir computing
- Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI
- Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVM
- PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations
- Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization
- Exploring External Knowledge for Accurate modeling of Visual and Language Problems
- Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments
- A Valid Self-Report is Never Late, Nor is it Early: On Considering the "Right" Temporal Distance for Assessing Emotional Experience
- Investigating the use of ChatGPT for the scheduling of construction projects
- SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention
- Incentives to Offer Algorithmic Recourse
- Identifying the Key Attributes in an Unlabeled Event Log for Automated Process Discovery
- Context Matters: A Strategy to Pre-train Language Model for Science Education
- Multi-task Highly Adaptive Lasso
- Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learning
- Meta Temporal Point Processes
- Epsilon-Identifiability of Causal Quantities
- Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases
- In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States
- Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation
- Vertex-based reachability analysis for verifying ReLU deep neural networks
- Prompt-Based Editing for Text Style Transfer
- Alignment with human representations supports robust few-shot learning
- Practical Differentially Private Hyperparameter Tuning with Subsampling
- Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstruction
- Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data
- A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
- Byte Pair Encoding for Symbolic Music
- Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI
- Adversarial Networks and Machine Learning for File Classification
- On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease
- Reduced-Order Autodifferentiable Ensemble Kalman Filters
- On the Connection Between MPNN and Graph Transformer
- Adaptive whitening in neural populations with gain-modulating interneurons
- Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation
- Deep Quantum Error Correction
- Training Full Spike Neural Networks via Auxiliary Accumulation Pathway
- Incorporating Background Knowledge in Symbolic Regression using a Computer Algebra System
- Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
- Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
- SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
- OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks
- Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees
- Uplink Scheduling in Federated Learning: an Importance-Aware Approach via Graph Representation Learning
- Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers
- DAG Learning on the Permutahedron
- Streaming LifeLong Learning With Any-Time Inference
- Polycraft World AI Lab (PAL): An Extensible Platform for Evaluating Artificial Intelligence Agents
- Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
- Optical Flow Estimation in 360^circ Videos: Dataset, Model and Application
- A Deep Learning Method for Comparing Bayesian Hierarchical Models
- Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean
- Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning
- ActiveLab: Active Learning with Re-Labeling by Multiple Annotators
- Predicting Sentence-Level Factuality of News and Bias of Media Outlets
- A Comparative Study of Pretrained Language Models for Long Clinical Text
- Learning the Effects of Physical Actions in a Multi-modal Environment
- Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking
- PhysGraph: Physics-Based Integration Using Graph Neural Networks
- SOBER: Highly Parallel Bayesian Optimization and Bayesian Quadrature over Discrete and Mixed Spaces
- Deep Clustering Survival Machines with Interpretable Expert Distributions
- PECAN: A Deterministic Certified Defense Against Backdoor Attacks
- HDPV-SLAM: Hybrid Depth-augmented Panoramic Visual SLAM for Mobile Mapping System with Tilted LiDAR and Panoramic Visual Camera
- BOMP-NAS: Bayesian Optimization Mixed Precision NAS
- PCV: A Point Cloud-Based Network Verifier
- Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds
- From Classification Accuracy to Proper Scoring Rules: Elicitability of Probabilistic Top List Predictions
- Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
- Graph Attention with Hierarchies for Multi-hop Question Answering
- Leveraging the Third Dimension in Contrastive Learning
- Certified Invertibility in Neural Networks via Mixed-Integer Programming
- Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
- Interpreting learning in biological neural networks as zero-order optimization method
- Automatic Modulation Classification with Deep Neural Networks
- CAPoW: Context-Aware AI-Assisted Proof of Work based DDoS Defense
- ExplainableFold: Understanding AlphaFold Prediction with Explainable AI
- Gene Teams are on the Field: Evaluation of Variants in Gene-Networks Using High Dimensional Modelling
- D'etection d'Objets dans les documents num'eris'es par r'eseaux de neurones profonds
- Inter-View Depth Consistency Testing in Depth Difference Subspace
- A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
- Side Auth: Synthesizing Virtual Sensors for Authentication
- Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
- Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
All 177
- Modeling human road crossing decisions as reward maximization with visual perception limitations
- Convolutional neural networks for valid and efficient causal inference
- Meta-Learning Mini-Batch Risk Functionals
- Single-Trajectory Distributionally Robust Reinforcement Learning
- The Exploration of Knowledge-Preserving Prompts for Document Summarisation
- Pre-training for Speech Translation: CTC Meets Optimal Transport
- Semantic Network Model for Sign Language Comprehension
- Improving deep learning precipitation nowcasting by using prior knowledge
- FedPH: Privacy-enhanced Heterogeneous Federated Learning
- TransNet: Transferable Neural Networks for Partial Differential Equations
- Image Restoration with Mean-Reverting Stochastic Differential Equations
- Big portfolio selection by graph-based conditional moments method
- SLCNN: Sentence-Level Convolutional Neural Network for Text Classification
- LegendreTron: Uprising Proper Multiclass Loss Learning
- Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding
- Neural Abstractions
- Towards Personalized Review Summarization by Modeling Historical Reviews from Customer and Product Separately
- Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
- Bayesian Self-Supervised Contrastive Learning
- Deep Residual Compensation Convolutional Network without Backpropagation
- Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning
- Semi-Supervised Machine Learning: a Homological Approach
- Multilayer hypergraph clustering using the aggregate similarity matrix
- Fast Region of Interest Proposals on Maritime UAVs
- Learning the Dynamics of Sparsely Observed Interacting Systems
- HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
- Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support
- Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
- Event Causality Extraction with Event Argument Correlations
- A Multi-View Joint Learning Framework for Embedding Clinical Codes and Text Using Graph Neural Networks
- A critical look at deep neural network for dynamic system modeling
- Improved Differential-neural Cryptanalysis for Round-reduced Simeck32/64
- Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties
- Adversarial Learning for Implicit Semantic-Aware Communications
- Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty
- Robust variance-regularized risk minimization with concomitant scaling
- A Green(er) World for A.I
- Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech
- AdaBoost is not an Optimal Weak to Strong Learner
- Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding
- Exponential tail bounds and Large Deviation Principle for Heavy-Tailed U-Statistics
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
- Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
- Conformal inference is (almost) free for neural networks trained with early stopping
- Robust Transformer with Locality Inductive Bias and Feature Normalization
- Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows
- Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation
- Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
- Targeted Attacks on Timeseries Forecasting
- Feasibility and Transferability of Transfer Learning: A Mathematical Framework
- Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
- Direct Parameterization of Lipschitz-Bounded Deep Networks
- Mixed Attention Network for Hyperspectral Image Denoising
- A Comparison of Tiny-nerf versus Spatial Representations for 3d Reconstruction
- SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
- Online Learning in Stackelberg Games with an Omniscient Follower
- Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
- Deep Industrial Image Anomaly Detection: A Survey
- CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification
- Exploring Deep Reinforcement Learning for Holistic Smart Building Control
- Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
- Theme-driven Keyphrase Extraction to Analyze Social Media Discourse
- Semi-Parametric Video-Grounded Text Generation
- Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation
- Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
- Dual-View Selective Instance Segmentation Network for Unstained Live Adherent Cells in Differential Interference Contrast Images
- D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
- Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks
- Learning Vortex Dynamics for Fluid Inference and Prediction
- Neural Episodic Control with State Abstraction
- Machine Learning Approach and Extreme Value Theory to Correlated Stochastic Time Series with Application to Tree Ring Data
- Projected Subnetworks Scale Adaptation
- Diffusion Denoising for Low-Dose-CT Model
- Are Equivariant Equilibrium Approximators Beneficial?
- Alien Coding
- Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
- Multi-limb Split Learning for Tumor Classification on Vertically Distributed Data