Improving Single-round Active Adaptation: A Prediction Variability Perspective

No abstract is available for this paper.

• Publication year

  2025

• Venue

  Trans. Mach. Learn. Res.

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers

  No identifiers available.

• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Reviving The Classics: Active Reward Modeling in Large Language Model Alignment

  2025cited by this paper
• Boundary Matters: A Bi-Level Active Finetuning Method

  2024cited by this paper
• Learning Dynamics of LLM Finetuning

  2024cited by this paper
• LLM Evaluators Recognize and Favor Their Own Generations

  2024cited by this paper
• Neural Active Learning Beyond Bandits

  2024cited by this paper
• Proxy Methods for Domain Adaptation

  2024cited by this paper
• An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

  2024cited by this paper
• LESS: Selecting Influential Data for Targeted Instruction Tuning

  2024cited by this paper
• D4: Improving LLM Pretraining via Document De-Duplication and Diversification

  2023cited by this paper
• Analyzing Generalization of Neural Networks through Loss Path Kernels

  2023cited by this paper
• One-Round Active Learning through Data Utility Learning and Proxy Models

  2023cited by this paper
• LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning

  2023cited by this paper
• Dirichlet-based Uncertainty Calibration for Active Domain Adaptation

  2023influential reference
• Active Learning Through a Covering Lens

  2022cited by this paper
• Adapting to Latent Subgroup Shifts via Concepts and Proxies

  2022cited by this paper
• Batch Active Learning from the Perspective of Sparse Approximation

  2022cited by this paper
• A Kernel-Based View of Language Model Fine-Tuning

  2022influential reference
• Improved Algorithms for Neural Active Learning

  2022cited by this paper
• Data Feedback Loops: Model-driven Amplification of Dataset Biases

  2022cited by this paper
• Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels

  2022cited by this paper
• Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

  2022cited by this paper
• Neural Active Learning with Performance Guarantees

  2021cited by this paper
• Online Continual Adaptation with Active Self-Training

  2021cited by this paper
• Zero-Round Active Learning

  2021cited by this paper
• Deep Active Learning by Leveraging Training Dynamics

  2021cited by this paper
• Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks

  2020cited by this paper
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation

  2020cited by this paper
• Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

  2020influential reference
• In Search of Lost Domain Generalization

  2020cited by this paper
• Fundamental Limits and Tradeoffs in Invariant Representation Learning

  2020cited by this paper
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

  2019influential reference
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

  2019cited by this paper
• Language Models are Unsupervised Multitask Learners

  2019cited by this paper
• Active Adversarial Domain Adaptation

  2019cited by this paper
• Wide neural networks of any depth evolve as linear models under gradient descent

  2019influential reference
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019influential reference
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks

  2018influential reference
• VisDA: The Visual Domain Adaptation Challenge

  2017cited by this paper
• Active Learning for Convolutional Neural Networks: A Core-Set Approach

  2017influential reference
• NewsQA: A Machine Comprehension Dataset

  2016cited by this paper
• SQuAD: 100,000+ Questions for Machine Comprehension of Text

  2016cited by this paper
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

  2015cited by this paper
• Character-level Convolutional Networks for Text Classification

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• CLAMShell: Speeding up Crowds for Low-latency Data Labeling

  2015cited by this paper
• The Dynamics of Micro-Task Crowdsourcing: The Case of Amazon MTurk

  2015cited by this paper
• Image-Based Recommendations on Styles and Substitutes

  2015cited by this paper
• Amazon Mechanical Turk: A Research Tool for Organizations and Information Systems Scholars

  2012cited by this paper
• Margin Based Active Learning

  2007cited by this paper

• No citing papers are available for this paper.