Welcome to PI Lab

From Agentic to Physical Intelligence

We investigate how agents can perceive complex environments, reason over what they observe, and act reliably in the real world.

Our Latest Work

CoRL 2026

CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents

Haebin Seong, Sungmin Kim, Yongjun Cho, Myunchul Joe , et al.

View Paper
ICML 2026 (Spotlight)

Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math

Guijin Son, Donghun Yang, Hitesh Laxmichand Patel, Hyunwoo Ko , et al.

View Paper
ICLR 2026

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Suwhan Choi, Jaeyoon Jung, Haebin Seong, Minchan Kim , et al.

View Paper
ICLR 2026

Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought

Guijin Son, Donghun Yang, Hitesh Laxmichand Patel, Amit Agarwal , et al.

View Paper
ICLR 2026

Teaching Metric Distance to Autoregressive Multimodal Foundational Models

Jiwan Chung, Saejin Kim, Yongrae Jo, Jaewoo Park , et al.

View Paper
ECCV 2026

Spanning Tree Autoregressive Visual Generation

Sangkyu Lee, Changho Lee, Janghoon Han, Hosung Song , et al.

View Paper
ECCV 2026

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation

Mingyeong Song, Jungbin Cho, Jisoo Kim, Ananya Bal , et al.

View Paper
COLM 2026

v1: Learning to Point Visual Tokens for Multimodal Mathematical Grounded Reasoning

Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee , et al.

View Paper

News