EvalEval2024

Running

App Files Files Community

evijit HF staff commited on Jul 16

Commit

fd6efb2

•

1 Parent(s): 7eceac2

Update index.html

Browse files

Files changed (1) hide show

index.html +190 -121

index.html CHANGED Viewed

@@ -3,10 +3,10 @@
 <head>
   <meta charset="utf-8">
   <meta name="description"
-        content="Datafication And Distortion In Generative AI">
-  <meta name="keywords" content="Generative AI, Henrietta Lacks, Distortion, Identity Loss, AI Art">
   <meta name="viewport" content="width=device-width, initial-scale=1">
-  <title>Because of You (2024)</title>
   <link rel="preconnect" href="https://fonts.googleapis.com">
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
@@ -32,164 +32,233 @@
 </head>
 <body>
 <section class="hero">
   <div class="hero-body">
     <div class="container is-max-desktop">
       <div class="columns is-centered">
         <div class="column has-text-centered">
-          <h1 class="title is-1 publication-title">Because of You (2024)</h1>
-          <h2 class="subtitle is-3 publication-subtitle">Datafication And Distortion In Generative AI</h2>
-          <div class="is-size-5 publication-authors">
-            <span class="author-block">
-              <a href="https://www.cyberneticforests.com/" target='_blank'>Eryk Salvaggio</a><sup>1</sup>,</span>
-            <span class="author-block">
-              <a href="https://evijit.io" target='_blank'>Avijit Ghosh</a><sup>2</sup></span>
-          </div>
           <div class="is-size-5 publication-authors">
-            <span class="author-block"><sup>1</sup>Siegel Family Endowment,</span>
-            <span class="author-block"><sup>2</sup>Hugging Face</span>
           </div>
         </div>
       </div>
     </div>
   </div>
 </section>
-<section class="section">
-    <div class="container is-max-desktop">
-      <!-- Paper video. -->
-      <div class="columns is-centered">
-        <div class="column is-full">
-          <!-- <h2 class="title is-3">Video</h2> -->
-          <div class="publication-video">
-            <div style="padding:56.25% 0 0 0;position:relative;">
-              <iframe src="https://player.vimeo.com/video/906478786?h=626387a4a3" style="position:absolute;top:0;left:0;width:100%;height:100%;" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen></iframe>
-            </div><script src="https://player.vimeo.com/api/player.js"></script>
-          </div>
-        </div>
-      </div>
-      <!--/ Paper video. -->
-    </div>
-</section>
 <section class="section">
   <div class="container is-max-desktop">
-    <div class="columns is-centered has-text-justified">
-      <!-- Body. -->
-      <div class="column">
-        <div class="content">
-            <p>
-              In a 2022 paper, <a href="https://www.arxiv.org/abs/2209.07667" target='_blank'>Can There Be Art Without an Artist?</a>, Dr. Avijit Ghosh and Genoveva Fossas discussed the work of human artists within training data for generative AI tools. In the appendix, they connect the practice of scraping training data without consent to its famous precedent in biology, citing the case of <a href="https://www.medicalnewstoday.com/articles/the-stolen-cells-of-henrietta-lacks-and-their-ongoing-contribution-to-science">Henrietta Lacks:</a>
-            </p>
-            <blockquote>
-            “Henrietta Lacks is known as “immortal” for a reason – though she died of cervical cancer at age 30, scientists have used her remarkable cells countless times since. HeLa cells, that never stop dividing and hence are functionally immortal, have played a role in some of the most important medical advancements of our time. They were used to develop the polio vaccine, chemotherapy and cloning technology, among others. However, the original cells that started the immortal HeLa cell line were taken from her without her consent or the awareness of her family. Now her family is demanding compensation from Johns Hopkins University who first took the cells. The HeLa cell controversy is yet another cautionary tale about the dangers of cutting out human creators in the pursuit of technology and a lesson in ethics, privacy and consent in technological progress.”
-            </blockquote>
-            <p>
-            <em>Because of You</em> is a digital video work inspired by this connection, and subsequent conversations between Eryk Salvaggio and Dr. Avijit Ghosh, which began at a <a href="https://schedule.sxsw.com/2023/events/PP122773"> presentation on AI and art at SXSW in 2023.</a>
-            </p>
-            <p>
-            The piece is defined by its soundtrack, a recording of jazz musician <a href="https://open.spotify.com/track/3Zq0oN9QkJ1KtEvDrASIxG?si=3d9162b3b0394362">Tab Smith’s 1951 instrumental ballad, “Because of You,”</a> slowed down to a quarter of its speed while isolating specific harmonic features. The song is both a historical marker — it was released the year that Lacks’ cells were taken without her consent, reflecting Lacks’ love of dancing — recollections by family members shared that Lacks would frequent dance halls at the time that these cells were being studied and analyzed without her knowledge.
-            </p>
-            <p>
-            In its title, and in the act of stretching this song out across a broader expanse of time, we emphasize the reach of that event, but also the extension of time through Lacks’ cells and the distortions created by time and the reprocessing of memory into the abstraction of data. Who is Henrietta Lacks? She is a person, and she is the progenitor of a series of cells that survived her without her name — data about her body without reference to the person.
-            </p>
-            <p>
-            The video piece explores links between the datafication of the body and the datafication of human expression. AI generated images cannot faithfully generate an image of Lacks’ face, as there is sparse documentation of who she was. In this piece, we drawing from an AI generated image of Henrietta Lacks, which appears close to the original but then drifts toward the image of a black woman, clearly styled for 2024. We revive the memory of Henrietta Lacks through using her name in the prompt, but that memory is distant from Lacks herself: much as it is with her cells.
-            </p>
-            <figure>
-              <img src="static/images/HeLa1-small.jpg" alt="Description of the image">
-              <figcaption>A still from Because of You.</figcaption>
-          </figure>
-          <p>
-          The film is narrated by a digital voice double of Dr. Ghosh — trained on a short sample of his voice. This regenerated voice describes the abstraction of Lacks’ life into cellular data, drawing parallels to the distortions introduced to his own voice — including the removal of his Bengali Indian accent, unexpectedly replaced with the inflections of a statistically averaged North American.
-          </p>
           <p>
-          Noise is a central element of this piece. In a sense, it envisions the training of a diffusion model as an in-between place: between information, contributed by humans, and the complete stripping away of that information, which is an aspect of AI model training.
           </p>
           <p>
-          Digital static stands in for the role of Gaussian noise in the training and generation of AI images. Noise is deeply embedded into the visual language of AI images, in that its training requires the removal of information from human archives in order to learn how to rebuild images from nothing. This process of information removal and restoration — the addition and subtraction of noise — is repeated millions of times while training a diffusion based model.
           </p>
           <p>
-          Here, Salvaggio draws parallels to the “removal of information” from Lacks, in her cells and in her visage, and the removal of information from the images created by humans for training data: images which, Salvaggio has noted, includes not only visual art, but private photographs, snapshots, and even documentation of child abuse, trauma, and historic atrocities. Salvaggio’s work often emphasizes this abstract destruction and recombination of all visual culture in AI models.
           </p>
         </div>
       </div>
-      <!--/ Body. -->
   </div>
 </section>
-<section class="section" style="margin-bottom: 1em;">
-  <div class="container is-max-desktop content">
-    <h2 class="title">Bios</h2>
-    <div class="column has-text-justified">
-    <p><a href="https://www.cyberneticforests.com" target='_blank'><strong>Eryk Salvaggio</strong></a> is an Emerging Technology Research Advisor at the Siegel Family Endowment and a new media artist interested in the social and cultural impacts of artificial intelligence. His work, which is centered in creative misuse and the right to refuse, critiques the mythologies and ideologies of technologies that ignore the gaps between datasets and the world they claim to represent. A blend of <a href="https://www.cyberneticforests.com/defcon31">hacker</a>, <a href="https://www.techpolicy.press/author/eryk-salvaggio/">policy researcher</a>, <a href="https://www.cyberneticforests.com/about">designer and artist</a>, he has been published in academic journals such as <a href="https://www.sciencedirect.com/science/article/pii/S2666389920302397">Patterns</a>, <a href="https://direct.mit.edu/leon/article-abstract/56/6/575/115406/Infinite-Barnacle-The-AI-Image-and-Imagination-in">Leonardo</a>, and <a href="https://dl.acm.org/doi/10.1145/3587241">Interactions of the ACM</a>, spoken at <a href="https://www.cmc.ie/events/2024/apr/music-current-2024-eryk-salvaggio-ai-workshop">music</a> and <a href="https://www.acmi.net.au/stories-and-ideas/the-age-of-noise/">media festivals</a>, and has consulted on tech policy at the national level.</p>
-    <p><a href="https://www.evijit.io" target='_blank'><strong>Dr. Avijit Ghosh</strong></a> is an Applied Policy Researcher in the Machine Learning and Society Team at <a href="https://www.huggingface.co/">Hugging Face 🤗</a>. He works at the intersection of machine learning, ethics, and policy, aiming to implement fair ML algorithms into the real world. He has published and peer-reviewed several research papers in top ML and AI Ethics venues, and has organized academic workshops as a member of <a href="https://www.queerinai.com/">QueerInAI.</a> His work has been covered in the press, including articles in <a href="https://www.nytimes.com/2023/08/16/technology/ai-defcon-hackers.html">The New York Times</a>, <a href="https://www.forbes.com/sites/rashishrivastava/2023/09/01/ai-red-teams-google-nvidia-microsoft-meta/">Forbes</a>, <a href="https://www.theguardian.com/technology/2024/mar/16/ai-racism-chatgpt-gemini-bias">The Guardian</a>, <a href="https://www.propublica.org/article/facebook-ads-can-still-discriminate-against-women-and-older-workers-despite-a-civil-rights-settlement">Propublica</a>, <a href="https://www.wired.com/story/new-york-city-proposes-regulating-algorithms-hiring/">Wired</a>, and the <a href="https://www.technologyreview.com/2021/02/11/1017955/auditors-testing-ai-hiring-algorithms-bias-big-questions-remain/">MIT Tech Review.</a> Dr. Ghosh has been an invited speaker as a Responsible AI expert, at events held by organizations such as  <a href="https://www.sxsw.com/">SXSW</a>,  <a href="https://www.trustworthyml.org/">Trustworthy ML Initiative</a>, <a href="https://avidml.org/arva/">AI Risk and Vulnerability Alliance</a>, and <a href="https://aivillage.org/">AI Village</a>. He has also engaged with policymakers, having spoken to <a href="https://www.linkedin.com/feed/update/urn:li:activity:7149203323592617984/">US Congressional Staffers</a> and to the <a href="https://www.gov.uk/government/organisations/centre-for-data-ethics-and-innovation">UK Government Centre for Data Ethics and Innovation</a>. His research and outreach have led to real-world impact, such as helping <a href="https://apnews.com/article/technology-business-race-and-ethnicity-racial-injustice-artificial-intelligence-2fe8d3ef7008d299d9d810f0c0f7905d">shape regulation in New York City</a> and causing Facebook to <a href="https://about.fb.com/news/2022/06/expanding-our-work-on-ads-fairness/">remove their biased ad targeting algorithm.</a></p>
-  </div>
   </div>
 </section>
-<section class="section" style="margin-bottom: 1em;">
-  <div class="container is-max-desktop content">
-    <h2 class="title">News</h2>
-    <div class="column">
-    <p><strong>Apr 8, 2024: </strong><em>Because of You</em> was accepted in the <a href="https://cvpr.thecvf.com/Conferences/2024/CallForAIArt">CVPR 2024 AI Art Gallery</a>. See you in Seattle!</p>
-    <p><strong>Apr 13, 2024: </strong><em>Because of You</em> won Best AI Film at the <a href="https://filmfreeway.com/CineTechFutureFest">CineTech Future Fest</a>.</p>
-    <p><strong>June 20, 2024: </strong><em>Because of You</em> was named one of the three winning art pieces at CVPR 2024 AI Art Gallery! We were named on the <a href="https://thecvf-art.com/shortlist/">shortlist</a> ahead of the event.</p>
     </div>
   </div>
 </section>
-<footer class="footer" style="padding: 0;">
   <div class="container">
-    <div class="columns is-centered has-text-centered">
-      <div class="column is-6">
-        <div class="content">
-          <p style="text-align: center;">
-            Page built off of the <a href="https://www.github.com/nerfies/nerfies.github.io">nerfiles source code</a>.
-          </p>
-        </div>
-      </div>
     </div>
   </div>
 </footer>
-<script>
-  document.addEventListener("DOMContentLoaded", function() {
-      var links = document.getElementsByTagName("a");
-      for (var i = 0; i < links.length; i++) {
-          links[i].setAttribute("target", "_blank");
-      }
-  });
-</script>
 </body>
 </html>

 <head>
   <meta charset="utf-8">
   <meta name="description"
+        content="Evaluating Evaluations: Examining Best Practices for Measuring Broader Impacts of Generative AI">
+  <meta name="keywords" content="Generative AI, Evaluation, Social Impact, NeurIPS, Workshop">
   <meta name="viewport" content="width=device-width, initial-scale=1">
+  <title>Evaluating Evaluations (2024)</title>
   <link rel="preconnect" href="https://fonts.googleapis.com">
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
 </head>
 <body>
 <section class="hero">
   <div class="hero-body">
     <div class="container is-max-desktop">
       <div class="columns is-centered">
         <div class="column has-text-centered">
+          <h1 class="title is-1 publication-title">Evaluating Evaluations (2024)</h1>
+          <h2 class="subtitle is-3 publication-subtitle">Examining Best Practices for Measuring Broader Impacts of Generative AI</h2>
           <div class="is-size-5 publication-authors">
+            <span class="author-block">A NeurIPS Workshop</span>
           </div>
         </div>
       </div>
     </div>
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
+    <div class="columns is-centered has-text-centered">
+      <div class="column is-four-fifths">
+        <h2 class="title is-3">Workshop Overview</h2>
+        <div class="content has-text-justified">
           <p>
+            Generative AI systems are becoming increasingly prevalent in society, producing content such as text, images, audio, and video with far-reaching implications. While the NeurIPS Broader Impact statement has notably shifted norms for AI publications to consider negative societal impact, no standard exists for how to approach these impact assessments. This workshop aims to address this critical gap by bringing together experts on evaluation science and practitioners who develop and analyze technical systems.
           </p>
           <p>
+            Building upon our previous initiatives, including the FAccT 2023 CRAFT session "Assessing the Impacts of Generative AI Systems Across Modalities and Society" and our initial "Evaluating the Social Impact of Generative AI Systems" report, we have made significant strides in this area. Through these efforts, we collaboratively developed an evaluation framework and guidance for assessing generative systems across modalities. We have since crowdsourced evaluations and analyzed gaps in literature and systemic issues around how evaluations are designed and selected.
           </p>
           <p>
+            The goal of this workshop is to share our existing findings with the NeurIPS community and collectively develop future directions for effective community-built evaluations. By fostering collaboration between experts and practitioners, we aim to create more comprehensive evaluations and develop urgently needed policy recommendations for governments and AI safety organizations.
           </p>
         </div>
       </div>
+    </div>
   </div>
 </section>
+<section class="section">
+  <div class="container is-max-desktop">
+    <h2 class="title is-3">Call for Papers (CFP)</h2>
+    <div class="content has-text-justified">
+      <p>We are soliciting tiny papers (up to 2 pages long) in the following formats:</p>
+      <ol>
+        <li>Extended Abstracts: Short but complete research papers presenting original or interesting results around social impact evaluation for generative AI.</li>
+        <li>"Provocations": Novel perspectives or challenges to conventional wisdom around social impact evaluation for generative AI.</li>
+      </ol>
+      <h3 class="title is-4">Submission Guidelines</h3>
+      <ul>
+        <li>Paper Length: Maximum 2 pages, including references</li>
+        <li>Format: PDF file, using the NeurIPS conference format</li>
+        <li>Submission Portal: [Insert submission portal link here]</li>
+        <li>Anonymity: Submissions should be anonymous for blind review</li>
+      </ul>
+      <h3 class="title is-4">Themes for Submissions</h3>
+      <p>We welcome submissions addressing, but not limited to, the following themes:</p>
+      <ol>
+        <li>Conceptualization and operationalization issues in evaluations of:
+          <ul>
+            <li>Bias, stereotypes, and representational harms</li>
+            <li>Cultural values and sensitive content</li>
+            <li>Community-centered definitions of disparate performance and privacy</li>
+            <li>Documentation frameworks for financial and environmental costs of evaluations</li>
+          </ul>
+        </li>
+        <li>Ethical or consequential validity considerations for:
+          <ul>
+            <li>Data protection</li>
+            <li>Data and content moderation labor</li>
+            <li>Historical implications of evaluation data or practices for evaluation validity</li>
+          </ul>
+        </li>
+        <li>Interrogating or critiquing the theoretical basis of existing evaluations</li>
+        <li>Novel methodologies for evaluating social impact across different AI modalities</li>
+        <li>Comparative analyses of existing evaluation frameworks and their effectiveness</li>
+        <li>Case studies of social impact evaluations in real-world AI applications</li>
+      </ol>
+      <h3 class="title is-4">Important Dates</h3>
+      <ul>
+        <li>Submission Deadline: August 1, 2024</li>
+        <li>Notification of Acceptance: September 1, 2024</li>
+        <li>Workshop Date: [Insert workshop date here]</li>
+      </ul>
+    </div>
   </div>
 </section>
+<section class="section">
+  <div class="container is-max-desktop">
+    <h2 class="title is-3">Workshop Structure</h2>
+    <div class="content">
+      <p>Total Duration: 8 Hours</p>
+      <table class="table is-fullwidth">
+        <thead>
+          <tr>
+            <th>Time</th>
+            <th>Session</th>
+            <th>Description</th>
+          </tr>
+        </thead>
+        <tbody>
+          <tr>
+            <td>9:00 AM - 9:30 AM</td>
+            <td>Welcome and Introduction</td>
+            <td>
+              <ul>
+                <li>Opening remarks</li>
+                <li>Overview of workshop structure and objectives</li>
+              </ul>
+            </td>
+          </tr>
+          <tr>
+            <td>9:30 AM - 11:00 AM</td>
+            <td>Reflections on the Landscape</td>
+            <td>
+              <ul>
+                <li>Collaborative reflection on the existing landscape</li>
+                <li>Talks, panels, and breakouts by modality (text, images, audio, video, and multimodal data)</li>
+                <li>Topics: Underlying frameworks, Contextualization challenges, Defining robust evaluations, Incentive structures</li>
+              </ul>
+            </td>
+          </tr>
+          <!-- Add more rows for each session -->
+        </tbody>
+      </table>
+    </div>
+  </div>
+</section>
+<section class="section">
+  <div class="container is-max-desktop">
+    <h2 class="title is-3">Invited Speakers</h2>
+    <div class="content">
+      <h3 class="title is-4">Confirmed Speakers:</h3>
+      <ol>
+        <li>
+          <strong>Abigail Jacobs</strong>
+          <ul>
+            <li>Assistant Professor, School of Information</li>
+            <li>Assistant Professor of Complex Systems, College of Literature, Science, and the Arts</li>
+            <li>University of Michigan</li>
+          </ul>
+        </li>
+        <li>
+          <strong>Nitarshan Rajkumar</strong>
+          <ul>
+            <li>Cofounder of UK AI Safety Institute</li>
+            <li>Adviser to the Secretary of State of UK Department for Science, Innovation and Technology</li>
+          </ul>
+        </li>
+        <li>
+          <strong>Su Lin Blodgett</strong>
+          <ul>
+            <li>Senior Researcher, Microsoft Research Montreal</li>
+          </ul>
+        </li>
+      </ol>
+      <h3 class="title is-4">Tentative Speaker:</h3>
+      <ol start="4">
+        <li>
+          <strong>Abeba Birhane</strong>
+          <ul>
+            <li>Adjunct Lecturer/Assistant Professor, Trinity College Dublin</li>
+            <li>Senior Fellow in Trustworthy AI at Mozilla Foundation</li>
+          </ul>
+        </li>
+      </ol>
+    </div>
+  </div>
+</section>
+<section class="section">
+  <div class="container is-max-desktop">
+    <h2 class="title is-3">Expected Outcomes</h2>
+    <div class="content has-text-justified">
+      <p>Three months after the workshop, we aim to achieve the following outcomes:</p>
+      <ol>
+        <li>
+          <strong>Evaluation Report and Resources/Repository:</strong>
+          <ul>
+            <li>Publish a comprehensive summary of the workshop findings</li>
+            <li>Update resources including:
+              <ul>
+                <li>Documentation framework for standardizing evaluation practices</li>
+                <li>Open source repository addressing identified barriers to broader adoption of social impact evaluation of Generative AI systems</li>
+              </ul>
+            </li>
+          </ul>
+        </li>
+        <li>
+          <strong>Policy Recommendations:</strong>
+          <ul>
+            <li>Share detailed policy recommendations for investment in future directions for social impact evaluations based on group discussions and workshop outcomes</li>
+          </ul>
+        </li>
+        <li>
+          <strong>Knowledge Sharing:</strong>
+          <ul>
+            <li>Foster a more systematic and effective approach to evaluating the social impact of generative AI systems by disseminating lessons and findings to the broader AI research community</li>
+          </ul>
+        </li>
+      </ol>
     </div>
   </div>
 </section>
+<section class="section">
+  <div class="container is-max-desktop">
+    <h2 class="title is-3">Contact Information</h2>
+    <div class="content has-text-justified">
+      <p>For any queries regarding the workshop or submission process, please contact:</p>
+      <p>[Insert contact information for workshop organizers]</p>
+    </div>
+  </div>
+</section>
+<footer class="footer">
   <div class="container">
+    <div class="content has-text-centered">
+      <p>
+        Workshop on Evaluating Evaluations: Examining Best Practices for Measuring Broader Impacts of Generative AI
+      </p>
+      <p>
+        Website template borrowed from the <a href="https://github.com/nerfies/nerfies.github.io">nerfies</a> project page.
+      </p>
     </div>
   </div>
 </footer>
 </body>
 </html>