Hanyu Wang

Hanyu Wang 王涵玉

AI Research Scientist at Meta · MSL FAIR

Multimodal AI · Generative Models · Recursive Self-Improvement · Embodied AI

About

I am an AI Research Scientist at Meta FAIR.

Previously, I was a Research Scientist at Luma AI, where I was a founding researcher on Project Opal, Luma's open physical AI initiative, and a core contributor to Uni, Luma's unified multimodal reasoning and generation model. I led the real-robot work for SEAR, including harness design and experiments.

I received my Ph.D. in Computer Science from the University of Maryland, College Park, advised by Prof. Abhinav Shrivastava, in 2025.

Selected Work

SEAR: Self-Evolving Agentic Robotics
Xinyi Wang*,†, Bangzheng Li*,†, Hanyu Wang‡, Lin Zhang, Andrea Yaoyun Cui, Zhenggang Tang, Shyamal Buch§, Dejia Xu†,§
* Co-first authors · † Project leads · ‡ Real robot lead · § Co-last authors
2026 · arXiv preprint · Code coming soon

A benchmark and framework for studying how LLM agents improve robot policies through execution feedback and carry skills and lessons across tasks, under controlled time budgets. I led the real-robot work for SEAR, including harness design and experiments.

LIBERO-RIG hardware and setup perturbations with model robustness results
LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models
Andrea Yaoyun Cui, Hanyu Wang, Xinyi Wang, Bangzheng Li, Lin Zhang, Zhenggang Tang, Shyamal Buch, Dejia Xu, Matthew Tancik
2026 · arXiv preprint

A benchmark for evaluating vision-language-action models under 11 hardware and setup perturbations while keeping LIBERO tasks fixed. Evaluates nine models across 210 perturbed conditions.

Luma Uni-1
Uni-1: Luma's Unified Multimodal Reasoning and Generation Model
Luma AI · core contributor to the Uni-1.x series
2026

Uni-1 is a multimodal reasoning model that understands intention, responds to direction, and generates pixels.

NeRV-Diffusion
NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesis
Yixuan Ren, Hanyu Wang, Hao Chen, Bo He, Abhinav Shrivastava
ICLR 2026
Bridge
Growing Visual Generative Capacity for Pre-Trained MLLMs
Hanyu Wang*, Jiaming Han*, Ziyan Yang, Qi Zhao, Shanchuan Lin, Xiangyu Yue, Abhinav Shrivastava, Zhenheng Yang, Hao Chen
ICLRW 2026
Tar
Vision as a Dialect: Unifying Visual Understanding & Generation via Text-Aligned Representations
Jiaming Han, Hao Chen, Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue, Lu Jiang
NeurIPS 2025
LARP
LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
Hanyu Wang, Saksham Suri, Yixuan Ren, Hao Chen, Abhinav Shrivastava
ICLR 2025 Oral
DPG
Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
Haoyue Tang, Tian Xie, Aosong Feng, Hanyu Wang, Chenyang Zhang, Yang Bai
AISTATS 2024
MMIST
Multimodality-guided Image Style Transfer using Cross-modal GAN Inversion
Hanyu Wang, Pengxiang Wu, Kevin Dela Rosa, Chen Wang, Abhinav Shrivastava
WACV 2024
Chop & Learn
Chop & Learn: Recognizing and Generating Object-State Compositions
Nirat Saini*, Hanyu Wang*, Archana Swaminathan, Vinoj Jayasundara, Bo He, Kamal Gupta, Abhinav Shrivastava
ICCV 2023
D-NeRV
Towards Scalable Neural Representation for Diverse Videos
Bo He, Xitong Yang, Hanyu Wang, Zuxuan Wu, Hao Chen, Shuaiyi Huang, Yixuan Ren, Ser-Nam Lim, Abhinav Shrivastava
CVPR 2023
NIRVANA
NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks
Shishira R Maiya*, Sharath Girish*, Max Ehrlich, Hanyu Wang, Kwot Sin Lee, Patrick Poirson, Pengxiang Wu, Chen Wang, Abhinav Shrivastava
CVPR 2023
Neural SFC
Neural Space-filling Curves
Hanyu Wang, Kamal Gupta, Larry Davis, Abhinav Shrivastava
ECCV 2022
NeRV
NeRV: Neural Representations for Videos
Hao Chen, Bo He, Hanyu Wang, Yixuan Ren, Ser-Nam Lim, Abhinav Shrivastava
NeurIPS 2021
Shape Descriptors
Learning local shape descriptors for computing non-rigid dense correspondence
Jianwei Guo, Hanyu Wang, Zhanglin Cheng, Xiaopeng Zhang, Dong-Ming Yan
Computational Visual Media, 2020
3D Keypoint Descriptors
Learning 3D keypoint descriptors for non-rigid shape matching
Hanyu Wang*, Jianwei Guo*, Dong-Ming Yan, Weize Quan, Xiaopeng Zhang
ECCV 2018