Jiafei Duan - MolmoAct2: Action Reasoning Models for Real-World Deployments
Talking Robotics #89 Speaker Jiafei Duan Title MolmoAct2: Action Reasoning Models for Real-World Deployments Speaker Bio Jiafei Duan is an incoming Assistant Professor at the National University of Singapore, School of Computing. He completed his Ph.D. in Computer Science & Engineering at the University of Washington, where he was advised by Professors Dieter Fox and Ranjay Krishna. His work lies at the intersection of robotics and computer vision, with a focus on robotics foundation models — particularly scalable data collection and generation, grounding vision–language models in robotic reasoning, and improving robust generalization in robot learning. His research has been featured in MIT Technology Review, GeekWire, VentureBeat, and Business Wire, and has appeared at top AI and robotics venues including ICLR, ICML, RSS, CoRL, ECCV, IJCAI, CoLM, and EMNLP. Among his honors are the Best Paper Award at Ubiquitous Robots 2023, the Best Paper Award at the CoRL RememberRL Workshop 2025, and a Spotlight Award at ICLR 2024. Speaker Links: Personal Website: https://duanjiafei.com Google Scholar: https://scholar.google.com/citations?... Chapters 00:00 Presenter Introduction 01:41 Presentation 44:35 Q&A 01:05:10 End Talking Robotics is a series of virtual seminars about Robotics and its interaction with other relevant fields, such as Artificial Intelligence, Machine Learning, Design Research, Human-Robot Interaction, among others. We aim to promote reflections, dialogues, and a place to network. Organized by Silvia Tulli, Riddhiman Laha, Nitin Ragothaman, and Niveditha Kalavakonda. Email: talkingrobotics at gmail dot com Web Page: https://talking-robotics.github.io Twitter: @talkingrobotics

Webinar | When Robots Learn: Safety & Trust in Adaptive Robotics | RoboSapiens EU

Sebastian Castro - Robots are complex, but your systems don’t have to be

"A Tale of Two Cultures: Can Agentic Coding Close the Gap?" plenary by Ken Goldberg at ICRA 2026

Something is jamming GPS over Europe. Here's what we found

Qianhui Men - Multimodal AI for Healthcare Decision-Making

Minghui (Scott) Zhao Seminar

Jitendra Malik: Vision and Robotics for Embodied AI

How to Start Coding | Programming for Beginners | Learn Coding | Intellipaat

Deep Dive into LLMs like ChatGPT

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Jon Arrizabalaga - Egocentric Decision-Making for Robot Autonomy

RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source

Ravi Pandya - Influence-Aware Safety for Human-Robot Interaction

Robotics' End Game: Nvidia's Jim Fan

What rebuilding AlphaGo teaches us about self-play, RL, and future of LLMs - Eric Jang

Why communities are revolting against data centers

Nicolas Perrin-Gilbert - Off-policy RL and interactive omics data exploration

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Stanford CS25: Transformers United V6 I From Language Models to Native Multimodal Intelligence

