I am a first-year Ph.D. student in Electrical Engineering and Computer Sciences at UC Berkeley. Before Berkeley, I received B.S. degrees from the University of Southern California in Electrical and Computer Engineering (Honors) and Applied & Computational Mathematics. At USC, I worked with Prof. Bhaskar Krishnamachari in the Autonomous Networks Research Group and with Prof. Peter Beerel. I have also worked with Prof. Yinyu Ye at Stanford, Prof. Qi Zhu as a visiting scholar in the Design Automation of Intelligent Systems Lab at Northwestern, and Prof. Dionysis Kalogerias at Yale.

Research Vision

My research aims to advance general-purpose physical intelligence by developing robots and multi-agent systems that learn to perceive, plan, and act reliably under uncertainty, with meaningful guarantees on their behavior.

To this end, I study predictive world models for reasoning under partial observability, risk-aware decision-making and multi-agent coordination, and specification-guided learning and verification for robotic policies, including vision-language-action models. My goal is to develop adaptable robots that generalize across tasks and environments, improve through experience, and remain safe and robust with clearly defined guarantees.

Education

Ph.D. in Electrical Engineering and Computer Sciences
UC Berkeley
2026 – present
B.S. in Electrical and Computer Engineering (Honors)
B.S. in Applied & Computational Mathematics
University of Southern California
2021 – 2025

News

  • Sep 2026SENTINEL is accepted to NeurIPS 2026! 🎉
  • Aug 2026Started my Ph.D. in EECS at UC Berkeley.
  • Dec 2025DISPATCH released on arXiv.
  • Nov 2025Predictive Modeling in AUV Navigation submitted to IEEE IV 2026 (arXiv).
  • Sep 2025SENTINEL released, with a project page.
  • Jun 2025Distributed ML inference paper published at GLSVLSI 2025.
  • Jun 2025Started as a visiting scholar at the Design Automation of Intelligent Systems Lab, Northwestern.
  • May 2025Undergraduate thesis on online dynamic resource allocation accepted by USC.
  • Nov 2024Pedestrian detection paper published at IEEE SiPS 2024.
  • May 2024Honorable Mention, MCM 2024, for Kalman-filter-based submarine trajectory prediction.
  • Jun 2023Started as an ML intern at Tsinghua MetaCam Lab.

Selected Publications

* Equal contribution  ·  Full list

Grasping across varied mug poses

AnyMug: Pose-Agnostic Robotic Functional Grasping via Observation–Action Canonicalization

Le Qiu, Cole Harrison, Jiankai Sun, Yao Liu, Suning Huang, Qianzhong Chen, Yang You, Marco Pavone

arXiv preprint, 2026|Paper|

A single closed-loop policy grasps mugs by the handle across shapes and poses by canonicalizing observations and actions in a mug-centric frame. Trained only in simulation, it transfers zero-shot to a real Franka Panda.

SENTINEL framework overview

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents

Simon Sinong Zhan*, Philip Wang*, Justin Yao Liu*, Yiyan Peng*, Yiqi Lyu, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Zhenyang Ni, Kangrui Wang, Ruohan Zhang, Huajie Shao, Manling Li, Qi Zhu

NeurIPS 2026|Paper|Website|Code|

SENTINEL specifies safety requirements for embodied LLM agents in temporal logic and checks them at the semantic, plan, and trajectory levels. Verification in VirtualHome and AI2-THOR flags unsafe states, ordering violations, and timed hazards with interpretable counterexamples.

DISPATCH problem setting: robots, task stations, and skill compatibility

DISPATCH: Decentralized Informed Spatial Planning and Assignment of Tasks for Cooperative Heterogeneous Agents

Yao Liu, Sampad Mohanty, Elizabeth Ondula, Bhaskar Krishnamachari

arXiv preprint, 2025|Paper|Website|

Decentralized policies for fair and efficient task assignment among heterogeneous agents under partial observability, learned toward Eisenberg–Gale equilibrium allocations with attention-based GNN message passing.

Quiet multi-agent system

Quiet Multi-Agent Systems via Predictive World Modeling and Selective Communications

Anthony Goeckner, Yao Liu, Zhian Ruan, Alessandro Pinto, Qi Zhu

In submission

A conditional diffusion model infers global state from local views, and its uncertainty decides when robots need to communicate. The predictions guide MARL policies on NASA ISRU-style exploration and transport tasks.

Figures 1 and 2 from the paper: secure distributed inference and dual redundancy

An Efficient Distributed Inference Framework for IoT Systems with Byzantine Fault Detection

Xuan Zhou, U. Muhan, Yao Liu, Peter Beerel

GLSVLSI 2025|Paper|

A low-cost defense for LLM inference split across edge devices. Each device also computes a small, randomly chosen set of redundant activations, and the next layer flags any mismatch. We derive how many inferences detection takes and validate it on GPT-2 Small: with 10% overhead and 4 of 8 devices in a layer compromised, all malicious devices are identified in 39.42 inferences on average.

Figures 4 and 5 from the paper: detection experiment pipeline and example predictions on real scenes

Let's Roll: Synthetic Dataset Analysis for Pedestrian Detection Across Different Shutter Types

Yue Hu, G. Datta, K. Beerel, Yao Liu, Peter Beerel

IEEE SiPS 2024|Paper|

Can detectors skip rolling-shutter correction? We built a dataset of 21,258 frames, in paired global- and rolling-shutter images, from Unreal Engine 5 and real scenes in downtown Los Angeles. YOLOv8 fine-tuned on rolling-shutter images nearly matches global-shutter performance at IoU 0.5, and adding synthetic data to the small real set improves recall by 53.1% and mAP@0.5 by 30.3% on real rolling-shutter data.

TDOA localization: an AUV emits acoustic signals received by reference receiver s0 and receivers s1 to s4

Predictive Modeling in AUV Navigation: A Perspective from Kalman Filtering

Zizhan Tang*, Yao Liu*, Jiexi Liu

Submitted to IEEE IV 2026|Paper|

Multi-buoy TDoA measurements are fused with an adaptively tuned Kalman filter to track a submersible through communication loss. Filtered tracks yield a search heatmap, with meter-level accuracy in simulation.

Adaptive online Arrow-Debreu markets

Adaptive Online Pricing for Arrow–Debreu Markets

Guangyuan Yuan, Yao Liu, Jiawen Yang, Yang Zhan, Caihua Chen, Yinyu Ye

In preparation

Online algorithms that compute Arrow–Debreu equilibrium prices as agents arrive with incomplete information, with O(log n) regret and O(1) constraint violation.

Selected Honors

  • UC Berkeley EECS Ph.D. Fellowship, 2026
  • Gold Medal, Kaggle LMSYS Chatbot Arena Human Preference Predictions, 2024
  • Ming Hsieh Institute Undergraduate Scholar, USC (top 5 research scholars in EE), 2024
  • Discover Scholar Distinction, USC, 2025
  • Honorable Mention, Mathematical Contest in Modeling (COMAP), 2024
  • Provost Research Scholarship, USC, 2024
  • W.V.T. Rusch Engineering Honors Degree, USC, 2023
  • Richardson CURVE Award, USC, 2022–2024
  • Academic Achievement Award, USC, 2024–2025
  • Dean's List, USC, 2022–2025

Service & Teaching

Experience

Machine Learning Intern, Tsinghua University MetaCam LabJun – Aug 2023

Built a spatially adaptive CNN that removes spatially varying optical blur by learning point spread functions across the image field, trained on a ray-traced synthetic pipeline with PSF-based augmentation; improved restoration quality by 1.7% over prior baselines.