Probing the Decision Boundaries of In-context Learning in Large Language Models
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement
Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
Instruction Mining: High-Quality Instruction Data Selection for Large Language Models
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
Estimating label quality and errors in semantic segmentation data via any model
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
Chatting with GPT-3 for Zero-Shot Human-Like Mobile Automated GUI Testing
TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
q2d: Turning Questions into Dialogs to Teach Models How to Search
Scaling Expert Language Models with Unsupervised Domain Discovery
Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities
Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula
Weakly supervised structured output learning for semantic segmentation
The Power of Ensembles for Active Learning in Image Classification
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
RHO-LOSS: Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
Multi-Task Self-Training for Learning General Representations
Dataset Distillation with Infinitely Wide Convolutional Networks
Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning
Adapting the Function Approximation Architecture in Online Reinforcement Learning
B-Pref: Benchmarking Preference-Based Reinforcement Learning
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
Exploring Bayesian Optimization: Breaking Bayesian Optimization into small, sizeable chunks
A deep active learning system for species identification and counting in camera trap images
Accelerating Deep Learning by Focusing on the Biggest Losers
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
BADGE: Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
ProductNet: a Collection of High-Quality Datasets for Product Representation Learning
End-to-End Robotic Reinforcement Learning without Reward Engineering
Data Shapley: Equitable Valuation of Data for Machine Learning
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
Computational mechanisms of curiosity and goal-directed exploration
Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
Fingerprint Policy Optimization for Robust Reinforcement Learning
Optimization, fast and slow: optimally switching between local and Bayesian optimization
Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications
Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
Less is more: sampling chemical space with active learning
ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
Learning a Generative Model for Validity in Complex Discrete Structures
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
Classification with Costly Features using Deep Reinforcement Learning
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Teaching Machines to Describe Images via Natural Language Feedback
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography
OHEM: Training Region-based Object Detectors with Online Hard Example Mining
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Just Sort It! A Simple and Effective Approach to Active Preference Learning
Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer
Algorithmic and Human Teaching of Sequential Decision Tasks
Bayesian Active Learning for Classification and Preference Learning
The wisdom of the few: a collaborative filtering approach based on expert opinions from the web
Learning and Example Selection for Object and Pattern Detection
Information-Based Objective Functions for Active Data Selection
Brief Summary of the Panel Discussion at DL Workshop @ICML 2015
Active Learning for High Dimensional Inputs Using Bayesian Convolutional Neural Networks
When Self-Driving Cars Can’t Help Themselves, Who Takes the Wheel?
How a Feel-Good AI Story Went Wrong in Flint: A Machine-Learning Model Showed Promising Results, but City Officials and Their Engineering Contractor Abandoned It.
2024-zhao-figure11-improvmeentofllmtransformerdecisionboundariesbyusingactivelearning.png
2023-kaddour-figure3-validationlossesforbertusingselectivebackpropvsreducibleholdoutvsrandomsampling.png
2023-xie-figure2-doremioptimizationoftrainingperformancetrainstwiceasfast.jpg
2009-amatriain-figure5-accuracyofnetflixmovierecommendationsbyhowmanynearbyexpertratingsareusedandweighted.jpg
2009-amatriain-figure6-expertcfvsnearnestneighborerrorrates.jpg
https://explosion.ai/blog/prodigy-annotation-tool-active-learning
https://github.com/cranmer/active_sciencing/blob/master/README.md
https://medium.com/cruise/cruise-continuous-learning-machine-30d60f4c691b
https://medium.com/pytorch/road-defect-detection-using-deep-active-learning-98d94fe854d
https://openai.com/research/dall-e-2-pre-training-mitigations
https://proceedings.neurips.cc/paper_files/paper/2007/file/a1519de5b5d44b31a01de013b9b51a80-Paper.pdf
https://research.google/blog/estimating-the-impact-of-training-data-with-reinforcement-learning/
https://research.google/blog/fluid-annotation-an-exploratory-machine-learningpowered-interface-for-faster-image-annotation/
https://research.google/blog/open-sourcing-active-question-reformulation-with-reinforcement-learning/
https://www.cs.ox.ac.uk/people/yarin.gal/website/blog_2248.html
https://www.forbes.com/sites/bradtempleton/2019/04/22/tesla-bets-farm-on-neural-network-based-autonomy-with-impressive-presentation/
https://www.probabilistic-numerics.org/assets/ProbabilisticNumerics.pdf#page=3
Probing the Decision Boundaries of In-context Learning in Large Language Models
Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge
%252Fdoc%252Freinforcement-learning%252Fmodel%252Falphago%252F2024-striethkalthoff.pdf.html
https%253A%252F%252Farxiv.org%252Fabs%252F2310.07096%2523ibm.html
https%253A%252F%252Farxiv.org%252Fabs%252F2307.08701%2523samsung.html
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
Estimating label quality and errors in semantic segmentation data via any model
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
https%253A%252F%252Farxiv.org%252Fabs%252F2305.10429%2523google.html
TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
https%253A%252F%252Farxiv.org%252Fabs%252F2305.07759%2523microsoft.html
q2d: Turning Questions into Dialogs to Teach Models How to Search
https%253A%252F%252Farxiv.org%252Fabs%252F2304.14318%2523google.html
Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities
https%253A%252F%252Fopenreview.net%252Fforum%253Fid%253DUVDAKQANOW.html
RHO-LOSS: Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
https%253A%252F%252Fkarpathy.github.io%252F2019%252F04%252F25%252Frecipe%252F.html
https%253A%252F%252Farxiv.org%252Fabs%252F1805.09501%2523google.html
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
https%253A%252F%252Farxiv.org%252Fabs%252F1511.06789%2523google.html
Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer
%252Fdoc%252Freinforcement-learning%252Fexploration%252Factive-learning%252F2015-vapnik.pdf.html
https%253A%252F%252Fprojecteuclid.org%252Fjournals%252Fannals-of-statistics%252Fvolume-39%252Fissue-1%252FRates-of-convergence-in-active-learning%252F10.1214%252F10-AOS843.full.html
%252Fdoc%252Freinforcement-learning%252Fexploration%252Factive-learning%252F2010-balcan.pdf.html
Wikipedia Bibliography:
