Alex Tamkin

Orcid: 0009-0006-0007-3746

According to our database1, Alex Tamkin authored at least 30 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.
CoRR, 2024

Bayesian Preference Elicitation with Language Models.
CoRR, 2024

Codebook Features: Sparse and Discrete Interpretability for Neural Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Collective Constitutional AI: Aligning a Language Model with Public Input.
Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

2023
Evaluating and Mitigating Discrimination in Language Model Decisions.
CoRR, 2023

Social Contract AI: Aligning AI Assistants with Implicit Group Norms.
CoRR, 2023

Eliciting Human Preferences with Language Models.
CoRR, 2023

Studying Large Language Model Generalization with Influence Functions.
CoRR, 2023

Towards Measuring the Representation of Subjective Global Opinions in Language Models.
CoRR, 2023

Operationalising the Definition of General Purpose AI Systems: Assessing Four Approaches.
CoRR, 2023

BenchMD: A Benchmark for Modality-Agnostic Learning on Medical Images and Sensors.
CoRR, 2023

Multispectral Self-Supervised Learning with Viewmaker Networks.
CoRR, 2023

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Task Ambiguity in Humans and Language Models.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Multispectral Contrastive Learning with Viewmaker Networks.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Oolong: Investigating What Makes Crosslingual Transfer Hard with Controlled Studies.
CoRR, 2022

Active Learning Helps Pretrained Models Learn the Intended Task.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

DABS 2.0: Improved Datasets and Algorithms for Universal Self-Supervision.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study.
CoRR, 2021

C5T5: Controllable Generation of Organic Molecules with Transformers.
CoRR, 2021

Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models.
CoRR, 2021

DABS: a Domain-Agnostic Benchmark for Self-Supervised Learning.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Viewmaker Networks: Learning Views for Unsupervised Representation Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020
Language Through a Prism: A Spectral Approach for Multiscale Language Representations.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Investigating Transferability in Pretrained Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Recursive Routing Networks: Learning to Compose Modules for Language Understanding.
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019

Drone.io: A Gestural and Visual Interface for Human-Drone Interaction.
Proceedings of the 14th ACM/IEEE International Conference on Human-Robot Interaction, 2019


  Loading...