<p align="center"><a href="../README.md">&larr; Back to the main README</a></p>

# 🎥 Academic Presentations

This page curates publicly accessible talks, tutorials, keynotes, seminars, guest lectures, symposia, and workshop recordings that offer broad perspectives on human-centric AI rather than presentations centered on a single paper.

> **Organization note.** Videos are grouped by their primary theme rather than assigned exclusively to one taxonomy level, since many talks connect human perception, motion, interaction, world modeling, and embodied agency.

> For multi-lecture courses with a sustained syllabus, see [Open Courseware](open-courseware.md).

## Contents

- [High-Level Perspectives on Human-Centric AI](#high-level-perspectives-on-human-centric-ai)
- [Human Foundation Models and Digital Humans](#human-foundation-models-and-digital-humans)
- [3D Humans, Motion, and Egocentric Intelligence](#3d-humans-motion-and-egocentric-intelligence)
- [World Models and Embodied Intelligence](#world-models-and-embodied-intelligence)
- [Humanoid Learning and Human-Robot Interaction](#humanoid-learning-and-human-robot-interaction)

<a id="high-level-perspectives-on-human-centric-ai"></a>

## High-Level Perspectives on Human-Centric AI

| Year | Format | Talk | Speaker / Event | Focus |
|:---:|:---|:---|:---|:---|
| 2024 | Distinguished lecture | [What We See and What We Value: AI with a Human Perspective](https://www.youtube.com/watch?v=gzOwpEupP5w) | Fei-Fei Li<br>[University of Washington Allen School Distinguished Lecture](https://www.youtube.com/watch?v=gzOwpEupP5w) | Human-centered foundations and spatial intelligence |
| 2024 | Keynote | [With Spatial Intelligence, AI Will Understand the Real World](https://www.ted.com/talks/fei_fei_li_with_spatial_intelligence_ai_will_understand_the_real_world) | Fei-Fei Li<br>[TED 2024](https://www.ted.com/talks/fei_fei_li_with_spatial_intelligence_ai_will_understand_the_real_world) | Spatial intelligence and embodied understanding |
| 2019 | Symposium archive | [Human-Centered Artificial Intelligence Symposium](https://hai.stanford.edu/events/2019-hai-symposium?section=video-archive) | Symposium speakers<br>[Stanford Institute for Human-Centered AI](https://hai.stanford.edu/events/2019-hai-symposium) | High-level perspectives on human-centered AI |

<a id="human-foundation-models-and-digital-humans"></a>

## Human Foundation Models and Digital Humans

| Year | Format | Talk | Speaker / Event | Focus |
|:---:|:---|:---|:---|:---|
| 2025 | Keynote series | [BMVA Symposium on Digital Humans](https://www.youtube.com/playlist?list=PLW8VWHVjepIt1DrtzuLqW0aPYSMsVXFET) | Tadas Baltrusaitis, Gerard Pons-Moll, Dimitris Tzionas, Abhijeet Ghosh, and Thu Nguyen-Phuoc<br>[British Machine Vision Association](https://www.bmva.org/meetings/25-05-28-DigitalHumans.html) | Digital humans, foundation models, capture, and generation |
| 2024 | Invited talk | [Learning Foundation Models for 3D Humans: A Data Request](https://www.dropbox.com/scl/fi/s5cnkmnzxx5hb3o2uiagm/SiyuTang.mp4?dl=0&rlkey=bf729wf0bmicwsm7biz4ygve4&st=hpv5zjkw) | Siyu Tang<br>[ECCV Foundation Models for 3D Humans](https://human-foundation.github.io/workshop-eccv-2024/) | Human foundation models and data scaling |
| 2024 | Invited talk | [Human Models for Embodied AI](https://www.dropbox.com/scl/fi/2cb6ua4x9dzqe5tdidlql/ECCVW2024_HumanFoundation_Xavier.mp4?dl=0&rlkey=5scm64sv60w6wcolu5xx78esg&st=ai4x8egp) | Xavier Puig<br>[ECCV Foundation Models for 3D Humans](https://human-foundation.github.io/workshop-eccv-2024/) | Human models and embodied agents |
| 2024 | Invited talk | [Towards Anatomically Correct Digital Human: From Imaging to Foundation Models](https://www.dropbox.com/scl/fi/w529zzoony2p834vtxkps/ECCVW2024_HumanFoundation_Jingyi.mp4?dl=0&rlkey=pnh061apolg5if8hnbd3dkrwn&st=hwvs5k0m) | Jingyi Yu<br>[ECCV Foundation Models for 3D Humans](https://human-foundation.github.io/workshop-eccv-2024/) | Digital humans and anatomical modeling |
| 2023 | Academic seminar | [Digital Humans](https://inf-opencast.mpi-inf.mpg.de/paella/ui/watch.html?id=5076feb5-46e2-413b-bc86-6d2b6f403ece) | Marc Habermann<br>[Saarland Informatics Campus](https://people.mpi-inf.mpg.de/~mhaberma/) | Capture, reconstruction, and animation of digital humans |
| 2022 | Distinguished lecture | [What Is a Codec Avatar?](https://www.youtube.com/watch?v=AoXMpGmihms) | Yaser Sheikh<br>[Berkeley EECS Distinguished Lecture](https://eecs.berkeley.edu/research/colloquium/221207-2/) | Photorealistic avatars and remote social presence |
| 2022 | Guest lecture | [Complete Codec Telepresence](https://www.youtube.com/watch?v=CM2rhJWiucQ) | Michael Zollhöfer<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Photorealistic avatars and telepresence |
| 2021 | Research talk | [Synthetic Data with Digital Humans](https://www.microsoft.com/en-us/research/video/synthetic-data-with-digital-humans/) | Erroll Wood and Tadas Baltrusaitis<br>[Microsoft Research](https://www.microsoft.com/en-us/research/video/synthetic-data-with-digital-humans/) | Synthetic human data for computer vision |
| 2021 | Guest lecture | [Towards Virtual Humans: Putting Realistic People in Realistic Scenes Doing Realistic Things](https://www.youtube.com/watch?v=MBHDAGCKKUQ) | Michael J. Black<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Digital humans in realistic scenes |
| 2021 | Guest lecture | [AI-Generated Digital Humans](https://www.youtube.com/watch?v=Tvk5NqCfyO8) | Hao Li<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Neural rendering and synthetic humans |
| 2020 | Guest lecture | [Perceiving Humans in the 3D World](https://www.youtube.com/watch?v=WOuCPT0lXio) | Angjoo Kanazawa<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | 3D human perception |
| 2020 | Guest lecture | [Shape Representations: Parametric Meshes vs. Implicit Functions](https://www.youtube.com/watch?v=_4E2iEmJXW8) | Gerard Pons-Moll<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Representations for 3D humans and clothing |
| 2020 | Guest lecture | [Photorealistic Telepresence](https://www.youtube.com/watch?v=2RuzbIS3fTY) | Yaser Sheikh<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Codec avatars and social telepresence |

<a id="3d-humans-motion-and-egocentric-intelligence"></a>

## 3D Humans, Motion, and Egocentric Intelligence

| Year | Format | Talk | Speaker / Event | Focus |
|:---:|:---|:---|:---|:---|
| 2025 | Invited talk | [Estimating Human Motion in World Coordinates](https://youtu.be/_cMRL_i5VmU) | Michael J. Black<br>[CVPR Global 3D Human Poses](https://g3p-workshop.github.io/) | Global human pose and motion |
| 2025 | Invited talk | [Understanding 3D Humans in Contextual 3D Spaces](https://youtu.be/QG-neoiKHvc) | Hanbyul Joo<br>[CVPR Global 3D Human Poses](https://g3p-workshop.github.io/) | 3D humans in contextual scenes |
| 2025 | Invited talk | [How to Train Your Humanoid](https://youtu.be/ip1qJAc9lag) | Angjoo Kanazawa<br>[CVPR Global 3D Human Poses](https://g3p-workshop.github.io/) | Human motion and humanoid learning |
| 2024 | Research talk | [Building Large Models for Predicting Human Motion](https://youtu.be/eVyjeJhdxB4) | C. Karen Liu<br>[Stanford Frontiers in Robotics and Machine Learning](https://forum.stanford.edu/events/2024-annual-affiliates-meeting/day-2-frontiers-robotics-and-machine-learning-workshop) | Large-scale models for human motion prediction |
| 2024 | Workshop recording | [Workshop on Human Motion Generation](https://www.youtube.com/watch?v=lkQ4sDK4u9U) | Daniel Holden, Michael Neff, Karen Liu, and Siyu Tang<br>[CVPR HuMoGen](https://humogen.github.io/2024/) | Motion generation and control |
| 2024 | Workshop recording | [New Challenges in 3D Human Understanding](https://www.youtube.com/watch?v=KwmVZhTnwHM) | Workshop speakers<br>[CVPR 2024](https://cvpr.thecvf.com/virtual/2024/workshop/23604) | 3D human reconstruction and understanding |
| 2023 | Workshop recording | [Joint 3rd Ego4D and 11th EPIC Workshop on Egocentric Vision](https://www.youtube.com/watch?v=Kc0tjwth_Mc) | Workshop speakers<br>[CVPR 2023](https://cvpr.thecvf.com/virtual/2023/workshop/18537) | Egocentric perception and action |
| 2020 | Distinguished lecture | [First-Person Perception and Interaction](https://www.microsoft.com/en-us/research/video/first-person-perception-and-interaction/) | Kristen Grauman<br>[Microsoft Research](https://www.microsoft.com/en-us/research/video/first-person-perception-and-interaction/) | Egocentric perception and human-environment interaction |
| 2020 | Guest lecture | [Sights, Sounds, and Space: Audio-Visual Learning in 3D Environments](https://www.youtube.com/watch?v=1EQ6helfvtM) | Kristen Grauman<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Egocentric and multimodal spatial learning |

<a id="world-models-and-embodied-intelligence"></a>

## World Models and Embodied Intelligence

| Year | Format | Talk | Speaker / Event | Focus |
|:---:|:---|:---|:---|:---|
| 2026 | Workshop recording | [Sense of Space: Multi-Sensory Modeling for Embodied Intelligence](https://youtu.be/LqLruZeQ6PA) | Workshop speakers<br>[CVPR 2026](https://sense-of-space.github.io/) | Spatial, tactile, and embodied intelligence |
| 2026 | Invited talk | [Observational Learning for Manipulation via Visual Imitation of Humans](https://youtu.be/LqLruZeQ6PA?t=12120) | Homanga Bharadhwaj<br>[CVPR Sense of Space](https://sense-of-space.github.io/) | Human-to-robot skill transfer |
| 2025 | Tutorial | [From Video Generation to World Model](https://www.youtube.com/watch?v=XiYayWC5pao) | Tutorial speakers<br>[CVPR 2025](https://cvpr.thecvf.com/virtual/2025/tutorial/35905) | Video generation and world models |
| 2025 | Workshop recording | [3D-LLM/VLA: Bridging Language, Vision and Action in 3D Environments](https://www.youtube.com/watch?v=3Dd3CwsVlqA) | Workshop speakers<br>[CVPR 2025](https://cvpr.thecvf.com/virtual/2025/workshop/32287) | 3D foundation models and embodied agents |
| 2025 | Workshop recording | [2nd Workshop on Embodied Humans](https://www.youtube.com/watch?v=GaCC_-qcD_k) | Workshop speakers<br>[CVPR 2025](https://cvpr.thecvf.com/virtual/2025/workshop/32359) | Virtual humans and humanoid robots |
| 2024 | Research talk | [Interactive Robotics in the Era of Large Pretrained Models](https://youtu.be/05-XbxY3aqs) | Dorsa Sadigh<br>[Stanford Frontiers in Robotics and Machine Learning](https://forum.stanford.edu/events/2024-annual-affiliates-meeting/day-2-frontiers-robotics-and-machine-learning-workshop) | Large pretrained models and interactive robotics |
| 2022 | Guest lecture | [Learning to Walk with Vision and Proprioception](https://www.youtube.com/watch?v=zjsdCiOAjNA) | Jitendra Malik<br>[TUM AI Guest Lecture Series](https://niessner.github.io/TUM-AI-Lecture-Series/) | Visuomotor learning and embodied locomotion |

<a id="humanoid-learning-and-human-robot-interaction"></a>

## Humanoid Learning and Human-Robot Interaction

| Year | Format | Talk | Speaker / Event | Focus |
|:---:|:---|:---|:---|:---|
| 2026 | Invited talk | [Scaling Whole-Body Humanoid Skills with Human Demonstration](https://youtu.be/z6vdlkJXDdY) | Tianyu Li<br>[RSS Embodied Intelligence in the Wild](https://opendrivelab.com/rss2026/workshop) | Human demonstrations and humanoid control |
| 2026 | Invited talk | [Beyond Imitation: Executable, Correctable, and Adaptable Skills for Humanoid Robots](https://youtu.be/6J5yugqOZxc) | Li Yi<br>[RSS Embodied Intelligence in the Wild](https://opendrivelab.com/rss2026/workshop) | Adaptable humanoid skills |
| 2026 | Invited talk | [Learning Personalized Whole-Arm Manipulation Around Humans](https://youtu.be/CX3A0ha4SSk) | Tapomayukh Bhattacharjee<br>[RSS Embodied Intelligence in the Wild](https://opendrivelab.com/rss2026/workshop) | Human-aware manipulation |
| 2026 | Robotics seminar | [Shaping the Future of Human-Robot Collaboration](https://www.youtube.com/watch?v=Y6baiESk-04) | Oussama Khatib<br>[MIT Robotics Seminar](https://www.youtube.com/watch?v=Y6baiESk-04) | Physical interaction and human-robot collaboration |
| 2024 | Academic seminar | [Modeling Humans for Humanoid Robots](https://www.youtube.com/watch?v=uQ-5BryUNv8) | Xiaolong Wang<br>[Stanford Robotics Seminar](https://youtu.be/uQ-5BryUNv8) | Human modeling and humanoid learning |
| 2020 | Robotics seminar | [Optimizing for Coordination with People](https://youtu.be/AQ-w5o2oGI8) | Anca Dragan<br>[Carnegie Mellon Robotics Institute Seminar](https://www.ri.cmu.edu/event/ri-seminar-anca-dragan-university-of-california-berkeley-assistant-professor-2020-02-28/) | Human-robot coordination and preference inference |
| 2020 | Talk playlist | [Emergent Behaviors in Human-Robot Systems](https://www.youtube.com/playlist?list=PLALgrVO1YLmsXdaRKWtABqONtA81J0t2O) | Workshop speakers<br>[Robotics: Science and Systems Workshop](https://iliad.stanford.edu/rss-workshop/iframe.html) | Human-robot interaction and collaboration |
| 2018 | High-level talk | [Will Artificial Intelligence Mean the End of Social Interaction?](https://vimeo.com/295242186) | Justine Cassell<br>[National Academies Distinctive Voices](https://vimeo.com/295242186) | Social interaction with virtual humans and conversational agents |
| 2017 | Robotics seminar | [Modeling Human Movements for Robotics](https://youtu.be/WymnyQlD6kc) | C. Karen Liu<br>[Robohub Robotics Talk](https://youtu.be/WymnyQlD6kc) | Human motion modeling for robot control |

---

<p align="center"><a href="../README.md">&larr; Back to the main README</a></p>