Yuanchen Bai

Current Ph.D. student @Cornell

[Yuanchen Bai @YuanchenB36202]

@Tao_Sun7 Congrats!

[Tao Sun @Tao_Sun7]

Can robots replace humans in dirty and hazardous construction work?

Introducing: Rebarbot 1.0🤖 https://t.co/tpPwBWsMRm

The first learning-based robotic system capable of autonomous rebar installation, marking an interesting step toward automated concrete component fabrication.

[Yuanchen Bai @YuanchenB36202]

What we found:
- System architecture—not just models or context—is the key performance bottleneck
- Reasoning models (e.g. o3) plan and delegate proactively, but can overthink or misalign with goals

Paper: https://t.co/7OvJLwsK8N

[Yuanchen Bai @YuanchenB36202]

🚨 Do stronger reasoning models guarantee better real-world coordination and performance?
Not always.

🔔 Sharing our new paper: From MAS to MARS: Coordination Failures and Reasoning Trade-offs in Hierarchical Multi-Agent Robotic Systems within a Healthcare Scenario

[Tao Sun @Tao_Sun7]

Introducing WoMAP—a new active perception framework merging world models with VLMs for open-vocabulary object localization in unknown environments. Grateful to have contributed a small part.

[Zijian "Jason" Ding @jasonzding]

Glad to introduce our colloquium "Robot in 2025 as GenAI in 2022: Riding the robot wave with lessons learned from GenAI boom" in Atlanta on May 18, 2025! Don't regret missing the GenAI boom—we are about to embrace an even bigger robotics wave soon.