<div dir="ltr"><div dir="ltr"><div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b><font style="vertical-align:inherit"><font style="vertical-align:inherit">When: </font></font></b><font style="vertical-align:inherit"><font style="vertical-align:inherit"> Friday, April 25th at <b><font style="background-color:rgb(255,255,0)">10:30 AM CT</font></b></font></font></font></div><div><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Where: </b><span class="gmail_default"><b></b></span><span class="gmail_default">T</span></font></font>alk will be given <font style="font-weight:bold"><u style="background-color:rgb(255,255,0)">live, in-person</u></font><font style="font-weight:bold"> </font>at</font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"> TTIC, 6045 S. Kenwood Avenue</font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"> 5th Floor, Room 530<b> </b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif"><b><br></b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000"><span class="gmail_default"><b>Virtually: </b>via Panopto<b> </b>(<a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=eaed2d1c-3093-4fe3-aa73-b248011ffd78" target="_blank">Livestream</a>) </span><b><br></b></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000"><b><font style="vertical-align:inherit"><font style="vertical-align:inherit">Who: <span class="gmail_default"></span> </font></font></b>Antonio Torralba, MIT</font></p></div><div><b><font face="georgia, serif" color="#000000"><br></font></b></div><div><font face="georgia, serif" color="#000000"><b>Title: </b><span class="gmail_default"></span><span class="gmail_default"></span>Understanding large vision models</font></div><div><p></p><div><font face="georgia, serif" color="#000000"><b>Abstract: </b>In the last few years, large pretrained models have shown impressive performance in a diverse set of tasks. These models must be trained with large datasets and are, in most cases, opaque on how they process information internally. In this talk I will focus on tools to understand the inner workings of existing pretrained models. Our current line of research aims to build tools that help users understand models, while combining the flexibility of human experimentation with the scalability of automated techniques. We introduce the Multimodal Automated Interpretability Agent (MAIA), which designs experiments to answer user queries about components of AI systems. MAIA iteratively generates hypotheses, runs experiments that test these hypotheses, observes experimental outcomes, and updates hypotheses until it can answer the user query. MAIA equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. To conclude, I will talk about the role of data to train large vision models and ask if we can do away with real image datasets entirely when building a computer vision system, instead learning from noise processes.</font></div></div><div><font face="georgia, serif" color="#000000"><br></font></div><div><font face="georgia, serif" color="#000000"><br></font><div><font face="georgia, serif" color="#000000"><b><span class="gmail_default"></span>Bio:</b> Antonio Torralba is the Delta electronics Professor and head of the AI+D faculty at the Department of EECS at MIT. He received the 2010 J. K. Aggarwal Prize, the 2020 PAMI Mark Everingham Prize, the Inaugural Thomas Huang Memorial Prize by the PAMITC in 2021. In 2022, he was invested Honoris Causa doctor by the Universitat Politècnica de Catalunya - BarcelonaTech (UPC). He is a AAAI fellow.</font></div><div><font face="georgia, serif" color="#000000"><br></font></div><div><p style="box-sizing:border-box;border-radius:0px;margin:0px 0px 10px"><font face="georgia, serif" color="#000000"><span style="box-sizing:border-box;border-radius:0px;font-weight:700">Hos</span><b><span style="box-sizing:border-box;border-radius:0px">t:<u><a href="mailto:avrim@ttic.edu" target="_blank"> </a></u></span></b><b><a href="mailto:greg@ttic.edu" target="_blank">Greg Shakhnarovich</a></b></font></p></div></div><br clear="all"></div><div><br></div><span class="gmail_signature_prefix">-- </span><br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><b style="background-color:rgb(255,255,255)"><font color="#3d85c6">Brandie Jones </font></b><div><div><div><font color="#3d85c6"><b><i>Executive </i></b></font><b style="color:rgb(61,133,198)"><i>Administrative Assistant</i></b></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Toyota Technological Institute</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">6045 S. Kenwood Avenue</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Chicago, IL 60637</font></span></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><a href="http://www.ttic.edu" target="_blank">www.ttic.edu</a> </font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><br></font></span></div></div></div></div>
</div>