.

Author: faikit

app/(default)/(event)/cvpr2026/workshop/page.tsx

@@ -40,13 +40,13 @@ const speakers: {
         affiliation: 'Cambridge',
         link: 'https://contactrika.github.io/'
     },
-    {
-        name: "Edward Johns",
-        image: "/assets/person/edward_johns.jpg",
-        position: "Associate Professor",
-        affiliation: 'Imperial College London',
-        link: 'https://www.robot-learning.uk/'
-    },
+    // {
+    //     name: "Edward Johns",
+    //     image: "/assets/person/edward_johns.jpg",
+    //     position: "Associate Professor",
+    //     affiliation: 'Imperial College London',
+    //     link: 'https://www.robot-learning.uk/'
+    // },
     // {
     //     name: "Harold Soh",
     //     image: "/assets/person/harold_soh.jpg",
@@ -69,11 +69,11 @@ const speakers: {
         link: 'https://yilundu.github.io/'
     },
     {
-        name: "Angjoo Kanazawa",
-        image: "/assets/person/angjoo_kanazawa.jpg",
-        position: "Assistant Professor",
+        name: "Jiahui Lei",
+        image: "/assets/person/jiahui_lei.jpg",
+        position: "Postdoc",
         affiliation: 'UC Berkeley',
-        link: 'https://people.eecs.berkeley.edu/~kanazawa/'
+        link: 'https://jiahuilei.com/'
     },
     {
         name: "Jiatao Gu",

app/(default)/(event)/cvpr2026/workshop/schedule.tsx

@@ -105,7 +105,7 @@ const scheduleItems: {
         nameLink: "https://mczhi.github.io/",
         affiliation: "UCLA, USA",
         affiliationLogo: "/assets/brand/ucla.png",
-        title: "TBD",
+        title: "nuReasoning: Advancing Reasoning-Centric Autonomous Driving for Long-Tail Scenarios",
         recordings: {
             youtube: "",
             bilibili: "",
@@ -116,8 +116,8 @@ const scheduleItems: {
     {
         type: "talk",
         time: "2026-06-04T01:20:00",
-        name: "Angjoo Kanazawa",
-        nameLink: "https://people.eecs.berkeley.edu/~kanazawa/",
+        name: "Jiahui Lei",
+        nameLink: "https://jiahuilei.com/",
         affiliation: "UC Berkeley, USA",
         affiliationLogo: "/assets/brand/ucberkeley.png",
         title: "TBD",
@@ -126,49 +126,48 @@ const scheduleItems: {
             bilibili: "",
         },
         slides: "",
-        bio: "Angjoo Kanazawa is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. She leads the Kanazawa AI Research (KAIR) lab under BAIR. Alongside her academic work, she has served as Chief Technical Advisor for Luma AI and on the advisory board of Wonder Dynamics. She is also an Amazon Scholar in the Frontier AI & Robotics team. Previously, she was a Research Scientist at Google Research, and BAIR postdoc at UC Berkeley advised by Jitendra Malik, Alexei A. Efros and Trevor Darrell. She completed her PhD in Computer Science at the University of Maryland, College Park with my advisor David Jacobs. During her PhD, she had the pleasure to visit the Max Planck Institute in Tübingen, Germany under the guidance of Michael Black.",
+        bio: "Jiahui Lei is a post-doc researcher at UC Berkeley. Working with Prof. Angjoo Kanazawa and Prof. Trevor Darrell. Today he is focusing on 4D Vision for Robotics. Previously, he worked on 4D as well as equivariant neural networks. He pursue inspiring, useful, and elegant research on hard problems. He believe researchers are defined by their questions and their tastes. He obtained his Ph.D (2020-2025) at University of Pennsylvania GRASP Lab advised by Prof. Kostas Daniilidis. He was a student researcher at Google DeepMind with Prof. Leo Guibas, and received my bachelor's degree (2016-2020) in Automation (Control Science) with ranking 1st/141, the class of 2020, Zhejiang University. Before he studied at Dalian No.24 High School.",
     },
     {
         type: "break",
         time: "2026-06-04T02:10:00",
         title: "Lunch Break",
     },
-    {
-        type: "talk",
-        time: "2026-06-04T03:00:00",
-        name: "Edward Johns",
-        nameLink: "https://www.robot-learning.uk/",
-        affiliation: "Imperial College London, UK",
-        affiliationLogo: "/assets/brand/icl.png",
-        title: "TBD",
-        recordings: {
-            youtube: "",
-            bilibili: "",
-        },
-        slides: "",
-        bio: "Edward Johns is Director of the Robot Learning Lab at Imperial College London, where he is also an Associate Professor. He received his undergraduate and master's degrees in engineering from Cambridge University, and his PhD in computer vision from Imperial College. Following a post-doc at UCL, he returned to Imperial as a founding member of the Dyson Robotics Lab, after which he was awarded an RAEng Research Fellowship. In 2018, he joined the faculty at Imperial and founded the Robot Learning Lab in the Department of Computing, where he also teaches a graduate-level course on Robot Learning.",
-    },
+    // {
+    //     type: "talk",
+    //     time: "2026-06-04T03:00:00",
+    //     name: "Edward Johns",
+    //     nameLink: "https://www.robot-learning.uk/",
+    //     affiliation: "Imperial College London, UK",
+    //     affiliationLogo: "/assets/brand/icl.png",
+    //     title: "TBD",
+    //     recordings: {
+    //         youtube: "",
+    //         bilibili: "",
+    //     },
+    //     slides: "",
+    //     bio: "Edward Johns is Director of the Robot Learning Lab at Imperial College London, where he is also an Associate Professor. He received his undergraduate and master's degrees in engineering from Cambridge University, and his PhD in computer vision from Imperial College. Following a post-doc at UCL, he returned to Imperial as a founding member of the Dyson Robotics Lab, after which he was awarded an RAEng Research Fellowship. In 2018, he joined the faculty at Imperial and founded the Robot Learning Lab in the Department of Computing, where he also teaches a graduate-level course on Robot Learning.",
+    // },
     {
         type: "talk",
         time: "2026-06-04T03:50:00",
-        name: "Jiatao Gu",
-        nameLink: "https://jiataogu.me/",
-        affiliation: "UPenn, USA",
-        affiliationLogo: "/assets/brand/UPenn.png",
-        title: "TBD",
+        name: "Yilun Du",
+        nameLink: "https://yilundu.github.io/",
+        affiliation: "Harvard, USA",
+        affiliationLogo: "/assets/brand/Harvard.png",
+        title: "Embodied Intelligence with World Models",
         recordings: {
             youtube: "",
             bilibili: "",
         },
         slides: "",
-        bio: "Jiatao Gu is an Assistant Professor in the Department of CIS at the University of Pennsylvania. He also works part-time as a Staff Research Scientist at Apple (MLR) and has been a full-time researcher since 2022. Prior to joining Apple, he was a Research Scientist at Meta AI (FAIR Labs). He obtained his Ph.D. degree at the department of Electrical and Electronic Engineering, University of Hong Kong in 2018 and he was supervised by Prof. Victor O.K. Li. His doctoral work explored efficient neural machine translation systems. He also spent a wonderful time visiting the CILVR Lab, New York University working with Prof. Kyunghyun Cho. Before that, he obtained his Bachelor’s degree at the Electronic Engineering Department, Tsinghua University in 2014.",
+        bio: "Yilun Du is an Assistant Professor at Harvard in the Kempner Institute and CS. He received his PhD at MIT EECS, advised by Prof. Leslie Kaelbling, Prof. Tomas Lozano-Perez and Prof. Joshua B. Tenenbaum. Previously, he also obtained his bachelor's degree from MIT, was a research fellow at OpenAI, a senior research scientist at Google Deepmind, and got a gold medal at the International Biology Olympiad. His research focuses on generative models, decision making, robot learning, embodied agents, and the applications of such tools to scientific domains. His research is driven by the goal of developing AI agents that interact in the physical world, focusing on generative AI as a toolbox for solving such problems. A unique challenge in applying generative AI in this setting is the lack of available decision-making data and the necessity to generalize well to previously unseen situations. His work addresses this by proposing compositional generative modeling, where simple generative models are learned and composed together to construct complex generative models that generalize beyond the narrow amount of available data. His work has illustrated how such compositionality solves various problems in constructing AI agents ranging from complex scene understanding, trajectory planning, multimodal perception, and hierarchical planning. His work has further shown how such developed techniques can be broadly applied to settings in sciences and engineering.",
     },
     {
         type: "break",
         time: "2026-06-04T04:40:00",
         title: "Coffee Break",
     },
-
     {
         type: "talk",
         time: "2026-06-04T04:50:00",
@@ -187,17 +186,17 @@ const scheduleItems: {
     {
         type: "talk",
         time: "2026-06-04T05:40:00",
-        name: "Yilun Du",
-        nameLink: "https://yilundu.github.io/",
-        affiliation: "Harvard, USA",
-        affiliationLogo: "/assets/brand/Harvard.png",
+        name: "Jiatao Gu",
+        nameLink: "https://jiataogu.me/",
+        affiliation: "UPenn, USA",
+        affiliationLogo: "/assets/brand/UPenn.png",
         title: "TBD",
         recordings: {
             youtube: "",
             bilibili: "",
         },
         slides: "",
-        bio: "Yilun Du is an Assistant Professor at Harvard in the Kempner Institute and CS. He received his PhD at MIT EECS, advised by Prof. Leslie Kaelbling, Prof. Tomas Lozano-Perez and Prof. Joshua B. Tenenbaum. Previously, he also obtained his bachelor's degree from MIT, was a research fellow at OpenAI, a senior research scientist at Google Deepmind, and got a gold medal at the International Biology Olympiad. His research focuses on generative models, decision making, robot learning, embodied agents, and the applications of such tools to scientific domains. His research is driven by the goal of developing AI agents that interact in the physical world, focusing on generative AI as a toolbox for solving such problems. A unique challenge in applying generative AI in this setting is the lack of available decision-making data and the necessity to generalize well to previously unseen situations. His work addresses this by proposing compositional generative modeling, where simple generative models are learned and composed together to construct complex generative models that generalize beyond the narrow amount of available data. His work has illustrated how such compositionality solves various problems in constructing AI agents ranging from complex scene understanding, trajectory planning, multimodal perception, and hierarchical planning. His work has further shown how such developed techniques can be broadly applied to settings in sciences and engineering.",
+        bio: "Jiatao Gu is an Assistant Professor in the Department of CIS at the University of Pennsylvania. He also works part-time as a Staff Research Scientist at Apple (MLR) and has been a full-time researcher since 2022. Prior to joining Apple, he was a Research Scientist at Meta AI (FAIR Labs). He obtained his Ph.D. degree at the department of Electrical and Electronic Engineering, University of Hong Kong in 2018 and he was supervised by Prof. Victor O.K. Li. His doctoral work explored efficient neural machine translation systems. He also spent a wonderful time visiting the CILVR Lab, New York University working with Prof. Kyunghyun Cho. Before that, he obtained his Bachelor’s degree at the Electronic Engineering Department, Tsinghua University in 2014.",
     },
     {
         type: "panel",