diff --git a/content/publication/du2024robotic.md b/content/publication/du2024robotic.md index e33613b..c738130 100644 --- a/content/publication/du2024robotic.md +++ b/content/publication/du2024robotic.md @@ -17,7 +17,7 @@ image_preview = "" selected = false projects = [] #url_pdf = "papers/du2024robotic.pdf" -url_preprint = "https://arxiv.org/pdf/2406.15917" +url_preprint = "https://arxiv.org/abs/2406.15917" url_code = "" url_dataset = "" url_slides = "" diff --git a/docs/404.html b/docs/404.html index d46c2d6..99c948c 100644 --- a/docs/404.html +++ b/docs/404.html @@ -237,6 +237,10 @@

Page not found

Publications

+ + @@ -253,10 +257,6 @@

Publications

  • To Err is Robotic: Rapid Value-Based Trial-and-Error during Deployment
    • - - diff --git a/docs/index.html b/docs/index.html index 57b7851..dd5506e 100644 --- a/docs/index.html +++ b/docs/index.html @@ -110,7 +110,7 @@ - + diff --git a/docs/index.xml b/docs/index.xml index ebb4add..8295544 100644 --- a/docs/index.xml +++ b/docs/index.xml @@ -6,9 +6,18 @@ Hugo -- gohugo.io en-us © 2024 Tobias Gerstenberg - Fri, 04 Oct 2024 00:00:00 +0000 + Tue, 08 Oct 2024 00:00:00 +0000 + + Self-supervised alignment with mutual information: Learning to follow principles without preference labels + https://cicl.stanford.edu/publication/franken2024sami/ + Tue, 08 Oct 2024 00:00:00 +0000 + + https://cicl.stanford.edu/publication/franken2024sami/ + + + MARPLE: A Benchmark for Long-Horizon Inference https://cicl.stanford.edu/publication/jin2024marple/ @@ -135,14 +144,5 @@ - - STaR-GATE: Teaching Language Models to Ask Clarifying Questions - https://cicl.stanford.edu/publication/andukuri2024stargate/ - Sun, 31 Mar 2024 00:00:00 +0000 - - https://cicl.stanford.edu/publication/andukuri2024stargate/ - - - diff --git a/docs/member/tobias_gerstenberg/index.html b/docs/member/tobias_gerstenberg/index.html index 00bdffc..c32cb0a 100644 --- a/docs/member/tobias_gerstenberg/index.html +++ b/docs/member/tobias_gerstenberg/index.html @@ -356,6 +356,53 @@

    Publications

    + + + (2024). + + Self-supervised alignment with mutual information: Learning to follow principles without preference labels. + Advances in Neural Information Processing Systems. + + + + +

    + + + + + + Preprint + + + + + PDF + + + + + + + + + + + + + + + + + Github + + + +

    + +
    +
    @@ -505,7 +552,7 @@

    Publications

    - + Preprint diff --git a/docs/publication/du2024robotic/index.html b/docs/publication/du2024robotic/index.html index 66691d4..9f957bf 100644 --- a/docs/publication/du2024robotic/index.html +++ b/docs/publication/du2024robotic/index.html @@ -315,7 +315,7 @@

    Abstract

    - + Preprint diff --git a/docs/publication/franken2024sami/index.html b/docs/publication/franken2024sami/index.html index 61a0a2b..51bd898 100644 --- a/docs/publication/franken2024sami/index.html +++ b/docs/publication/franken2024sami/index.html @@ -111,9 +111,9 @@ - + - + diff --git a/docs/publication/index.html b/docs/publication/index.html index df4b561..202a727 100644 --- a/docs/publication/index.html +++ b/docs/publication/index.html @@ -1597,6 +1597,19 @@

    Publications

    + + + + + + + + + + + + + @@ -1733,6 +1746,65 @@

    Publications

    +
    + +
    + + + (2024). + + Self-supervised alignment with mutual information: Learning to follow principles without preference labels. + Advances in Neural Information Processing Systems. + + + + +

    + + + + + + Preprint + + + + + PDF + + + + + + + + + + + + + + + + + Github + + + +

    + +
    + + +
    + + + + + + +
    @@ -1921,7 +1993,7 @@

    Publications

    - + Preprint diff --git a/docs/publication/index.xml b/docs/publication/index.xml index b0d1e21..b56f6ca 100644 --- a/docs/publication/index.xml +++ b/docs/publication/index.xml @@ -12,6 +12,15 @@ + + Self-supervised alignment with mutual information: Learning to follow principles without preference labels + https://cicl.stanford.edu/publication/franken2024sami/ + Tue, 08 Oct 2024 00:00:00 +0000 + + https://cicl.stanford.edu/publication/franken2024sami/ + + + MARPLE: A Benchmark for Long-Horizon Inference https://cicl.stanford.edu/publication/jin2024marple/ diff --git a/docs/publication_types/3/index.html b/docs/publication_types/3/index.html index 80f7a06..b5a0da6 100644 --- a/docs/publication_types/3/index.html +++ b/docs/publication_types/3/index.html @@ -111,7 +111,7 @@ - + @@ -238,6 +238,15 @@

    3

    +
    +

    Self-supervised alignment with mutual information: Learning to follow principles without preference labels

    +
    + + When prompting a language model (LM), users frequently expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles into … + +
    +
    + -
    -

    Anticipating the risks and benefits of counterfactual world simulation models

    -
    - - This paper examines the transformative potential of Counterfactual World Simulation Models (CWSMs). CWSMs use pieces of multi-modal evidence, such as the CCTV footage or sound recordings of a road accident, to build a high-fidelity 3D reconstruction … - -
    -
    -