Publications by Tags
Selected Papers Compression, Equivariance, Evaluation, Information Theory, Invariance, Neural Processes, NLP, Representation Learning, RLHF, Robustness, Safety, Self-Supervised Learning, Time Series, Uncertainty, VisionSelected Papers
Y. Ruan*, H. Dong*, A. Wang, S. Pitis, Y. Zhou, J. Ba, Y. Dubois, C. J. Maddison, T. Hashimoto
ICLR 2024 Spotlight Presentation πTLDR: An LM-based emulation framework for identifying the risks of LM agents at scale.
Selected Papers Evaluation, NLP, Safety,X. Li*, T. Zhang*, Y. Dubois*, R. Taori*, I. Gulrajani, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.
Selected Papers Evaluation, NLP, RLHF,Y. Dubois*, X. Li*, R. Taori*, T. Zhang*, I. Gulrajani, J. Ba, C. Guestrin, P. Liang, T. Hashimoto
NeurIPS 2023 Spotlight Presentation πTLDR: AlpacaFarm replicates the RLHF process at a fraction of the time (<24h) and cost ($<200), enabling the research community to advance instruction following research.
Selected Papers Evaluation, NLP, RLHF,R. Taori*, I. Gulrajani*, T. Zhang*, Y. Dubois*, X. Li*, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: We introduce Alpaca 7B, a instruction-following fine-tuned LLaMA model. On our preliminary evaluation, Alpaca behaves qualitatively similarly to OpenAIβs text-davinci-003, while being surprisingly small and easy/cheap to reproduce (<600$).
Selected Papers NLP, RLHF, Self-Supervised LearningY. Dubois, T. Hashimoto, P. Liang
ICML 2023 Oral Presentation πTLDR: We derive a risk decomposition for self-supervised learning and use it to evaluate 169 pretrained models.
Selected Papers Evaluation, Representation Learning, Self-Supervised Learning, VisionY. Dubois, T. Hashimoto, S. Ermon, P. Liang
NeurIPS 2022TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.
Selected Papers Invariance, Representation Learning, Self-Supervised Learning, VisionY Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionY. Dubois, D. Kiela, D. J. Schwab, R. Vedantam
NeurIPS 2020 Spotlight Presentation πTLDR: We characterize and approximate optimal representations for supervised learning.
Selected Papers Information Theory, Representation Learning, VisionCompression
Y. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionEquivariance
Y. Dubois*, J. Gordon*, A. Foong*
GitHubTLDR: A simple and unifying explanation of the neural process family, which are a collection of models that meta-learn a distribution over predictors.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionA. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner
NeurIPS 2020TLDR: We propose a translation equivariant (latent) neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionJ. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner
ICLR 2020 Oral Presentation πTLDR: We propose a translation equivariant conditional neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionEvaluation
Y. DuboisB. Galambosi, P. Liang, T. Hashimoto
ArXivTLDR: We decrease the bias of AlpacaEval for longer outputs using regression analysis.
Evaluation, NLPY. Zhang, Y. Mai, J. Somerville Roberts, R. Bommasani, Y. Dubois, P. Liang
ICLRTLDR: Multidimensional evaluation of instruction following LLM with absolute scores.
Evaluation, NLPY. Ruan*, H. Dong*, A. Wang, S. Pitis, Y. Zhou, J. Ba, Y. Dubois, C. J. Maddison, T. Hashimoto
ICLR 2024 Spotlight Presentation πTLDR: An LM-based emulation framework for identifying the risks of LM agents at scale.
Selected Papers Evaluation, NLP, Safety,X. Li*, T. Zhang*, Y. Dubois*, R. Taori*, I. Gulrajani, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.
Selected Papers Evaluation, NLP, RLHF,Y. Dubois*, X. Li*, R. Taori*, T. Zhang*, I. Gulrajani, J. Ba, C. Guestrin, P. Liang, T. Hashimoto
NeurIPS 2023 Spotlight Presentation πTLDR: AlpacaFarm replicates the RLHF process at a fraction of the time (<24h) and cost ($<200), enabling the research community to advance instruction following research.
Selected Papers Evaluation, NLP, RLHF,Y. Dubois, T. Hashimoto, P. Liang
ICML 2023 Oral Presentation πTLDR: We derive a risk decomposition for self-supervised learning and use it to evaluate 169 pretrained models.
Selected Papers Evaluation, Representation Learning, Self-Supervised Learning, VisionInformation Theory
Y Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionY. Dubois, D. Kiela, D. J. Schwab, R. Vedantam
NeurIPS 2020 Spotlight Presentation πTLDR: We characterize and approximate optimal representations for supervised learning.
Selected Papers Information Theory, Representation Learning, VisionInvariance
N. Miao, E. Mathieu, Y. Dubois, T. Rainforth, Y. W. Teh, A. Foster, H. Kim
ICML 2023TLDR: We introduce a method for automatically learning input-specific augmentations from data.
Invariance, VisionY. Dubois, T. Hashimoto, S. Ermon, P. Liang
NeurIPS 2022TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.
Selected Papers Invariance, Representation Learning, Self-Supervised Learning, VisionY Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionNLP
Y. DuboisB. Galambosi, P. Liang, T. Hashimoto
ArXivTLDR: We decrease the bias of AlpacaEval for longer outputs using regression analysis.
Evaluation, NLPY. Zhang, Y. Mai, J. Somerville Roberts, R. Bommasani, Y. Dubois, P. Liang
ICLRTLDR: Multidimensional evaluation of instruction following LLM with absolute scores.
Evaluation, NLPY. Ruan*, H. Dong*, A. Wang, S. Pitis, Y. Zhou, J. Ba, Y. Dubois, C. J. Maddison, T. Hashimoto
ICLR 2024 Spotlight Presentation πTLDR: An LM-based emulation framework for identifying the risks of LM agents at scale.
Selected Papers Evaluation, NLP, Safety,X. Li*, T. Zhang*, Y. Dubois*, R. Taori*, I. Gulrajani, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.
Selected Papers Evaluation, NLP, RLHF,Y. Dubois*, X. Li*, R. Taori*, T. Zhang*, I. Gulrajani, J. Ba, C. Guestrin, P. Liang, T. Hashimoto
NeurIPS 2023 Spotlight Presentation πTLDR: AlpacaFarm replicates the RLHF process at a fraction of the time (<24h) and cost ($<200), enabling the research community to advance instruction following research.
Selected Papers Evaluation, NLP, RLHF,R. Taori*, I. Gulrajani*, T. Zhang*, Y. Dubois*, X. Li*, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: We introduce Alpaca 7B, a instruction-following fine-tuned LLaMA model. On our preliminary evaluation, Alpaca behaves qualitatively similarly to OpenAIβs text-davinci-003, while being surprisingly small and easy/cheap to reproduce (<600$).
Selected Papers NLP, RLHF, Self-Supervised LearningS. Santurkar, Y. Dubois, R. Taori, P. Liang, T. Hashimoto
ICLR 2022TLDR: Our work performs a systematic investigation into whether additional language supervision (in CLIP) helps models learn more transferrable representations.
NLP, Representation Learning, Self-Supervised Learning, VisionY. Dubois, Gautier Dagan, Dieuwke Hupkes, Elia Bruni
ACL 2020TLDR: We propose an attention that improves extrapolation capacity of neural NLP models.
NLP, RobustnessNeural Processes
Y. Dubois*, J. Gordon*, A. Foong*
GitHubTLDR: A simple and unifying explanation of the neural process family, which are a collection of models that meta-learn a distribution over predictors.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionA. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner
NeurIPS 2020TLDR: We propose a translation equivariant (latent) neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionJ. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner
ICLR 2020 Oral Presentation πTLDR: We propose a translation equivariant conditional neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionRLHF
X. Li*, T. Zhang*, Y. Dubois*, R. Taori*, I. Gulrajani, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.
Selected Papers Evaluation, NLP, RLHF,Y. Dubois*, X. Li*, R. Taori*, T. Zhang*, I. Gulrajani, J. Ba, C. Guestrin, P. Liang, T. Hashimoto
NeurIPS 2023 Spotlight Presentation πTLDR: AlpacaFarm replicates the RLHF process at a fraction of the time (<24h) and cost ($<200), enabling the research community to advance instruction following research.
Selected Papers Evaluation, NLP, RLHF,R. Taori*, I. Gulrajani*, T. Zhang*, Y. Dubois*, X. Li*, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: We introduce Alpaca 7B, a instruction-following fine-tuned LLaMA model. On our preliminary evaluation, Alpaca behaves qualitatively similarly to OpenAIβs text-davinci-003, while being surprisingly small and easy/cheap to reproduce (<600$).
Selected Papers NLP, RLHF, Self-Supervised LearningRepresentation Learning
Y. Dubois, T. Hashimoto, P. Liang
ICML 2023 Oral Presentation πTLDR: We derive a risk decomposition for self-supervised learning and use it to evaluate 169 pretrained models.
Selected Papers Evaluation, Representation Learning, Self-Supervised Learning, VisionS. Santurkar, Y. Dubois, R. Taori, P. Liang, T. Hashimoto
ICLR 2022TLDR: Our work performs a systematic investigation into whether additional language supervision (in CLIP) helps models learn more transferrable representations.
NLP, Representation Learning, Self-Supervised Learning, VisionY. Dubois, T. Hashimoto, S. Ermon, P. Liang
NeurIPS 2022TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.
Selected Papers Invariance, Representation Learning, Self-Supervised Learning, VisionY Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionY. Dubois, D. Kiela, D. J. Schwab, R. Vedantam
NeurIPS 2020 Spotlight Presentation πTLDR: We characterize and approximate optimal representations for supervised learning.
Selected Papers Information Theory, Representation Learning, VisionRobustness
Y Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, Gautier Dagan, Dieuwke Hupkes, Elia Bruni
ACL 2020TLDR: We propose an attention that improves extrapolation capacity of neural NLP models.
NLP, RobustnessSafety
Y. Ruan*, H. Dong*, A. Wang, S. Pitis, Y. Zhou, J. Ba, Y. Dubois, C. J. Maddison, T. Hashimoto
ICLR 2024 Spotlight Presentation πTLDR: An LM-based emulation framework for identifying the risks of LM agents at scale.
Selected Papers Evaluation, NLP, Safety,Self-Supervised Learning
R. Taori*, I. Gulrajani*, T. Zhang*, Y. Dubois*, X. Li*, C. Guestrin, P. Liang, T. Hashimoto
GitHubTLDR: We introduce Alpaca 7B, a instruction-following fine-tuned LLaMA model. On our preliminary evaluation, Alpaca behaves qualitatively similarly to OpenAIβs text-davinci-003, while being surprisingly small and easy/cheap to reproduce (<600$).
Selected Papers NLP, RLHF, Self-Supervised LearningY. Dubois, T. Hashimoto, P. Liang
ICML 2023 Oral Presentation πTLDR: We derive a risk decomposition for self-supervised learning and use it to evaluate 169 pretrained models.
Selected Papers Evaluation, Representation Learning, Self-Supervised Learning, VisionS. Santurkar, Y. Dubois, R. Taori, P. Liang, T. Hashimoto
ICLR 2022TLDR: Our work performs a systematic investigation into whether additional language supervision (in CLIP) helps models learn more transferrable representations.
NLP, Representation Learning, Self-Supervised Learning, VisionY. Dubois, T. Hashimoto, S. Ermon, P. Liang
NeurIPS 2022TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.
Selected Papers Invariance, Representation Learning, Self-Supervised Learning, VisionY Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionTime Series
Y. Dubois*, J. Gordon*, A. Foong*
GitHubTLDR: A simple and unifying explanation of the neural process family, which are a collection of models that meta-learn a distribution over predictors.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionA. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner
NeurIPS 2020TLDR: We propose a translation equivariant (latent) neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionJ. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner
ICLR 2020 Oral Presentation πTLDR: We propose a translation equivariant conditional neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionUncertainty
Y. Dubois*, J. Gordon*, A. Foong*
GitHubTLDR: A simple and unifying explanation of the neural process family, which are a collection of models that meta-learn a distribution over predictors.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionA. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner
NeurIPS 2020TLDR: We propose a translation equivariant (latent) neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionJ. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner
ICLR 2020 Oral Presentation πTLDR: We propose a translation equivariant conditional neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionVision
Y. Dubois, T. Hashimoto, P. Liang
ICML 2023 Oral Presentation πTLDR: We derive a risk decomposition for self-supervised learning and use it to evaluate 169 pretrained models.
Selected Papers Evaluation, Representation Learning, Self-Supervised Learning, VisionS. Santurkar, Y. Dubois, R. Taori, P. Liang, T. Hashimoto
ICLR 2022TLDR: Our work performs a systematic investigation into whether additional language supervision (in CLIP) helps models learn more transferrable representations.
NLP, Representation Learning, Self-Supervised Learning, VisionN. Miao, E. Mathieu, Y. Dubois, T. Rainforth, Y. W. Teh, A. Foster, H. Kim
ICML 2023TLDR: We introduce a method for automatically learning input-specific augmentations from data.
Invariance, VisionY. Dubois, T. Hashimoto, S. Ermon, P. Liang
NeurIPS 2022TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.
Selected Papers Invariance, Representation Learning, Self-Supervised Learning, VisionY Ruan*, Y. Dubois*, C. J. Maddison
ICLR 2021TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.
Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, VisionY. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison
NeurIPS 2021 Spotlight Presentation πTLDR: We formalize compression with respect to ML algorithms rather than human perception.
Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, VisionY. Dubois, D. Kiela, D. J. Schwab, R. Vedantam
NeurIPS 2020 Spotlight Presentation πTLDR: We characterize and approximate optimal representations for supervised learning.
Selected Papers Information Theory, Representation Learning, VisionY. Dubois*, J. Gordon*, A. Foong*
GitHubTLDR: A simple and unifying explanation of the neural process family, which are a collection of models that meta-learn a distribution over predictors.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionA. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner
NeurIPS 2020TLDR: We propose a translation equivariant (latent) neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, VisionJ. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner
ICLR 2020 Oral Presentation πTLDR: We propose a translation equivariant conditional neural process.
Equivariance, Neural Processes, Time Series, Uncertainty, Vision