Kevin Wang

Email Google Scholar GitHub LinkedIn Twitter/X CV

I am a PhD student at the University of Texas at Austin, advised by Prof. Atlas Wang in the VITA group.

My research centers on agentic AI, verifiable learning, and continual learning. My goal is to design agents that maintain persistent memory and improve themselves over time, with the goal of building autonomous decision-making systems that can explore, learn, and reliably deploy to unfamiliar environments, while scaling in a way we can formally verify.

I’ve also been collaborating with Prof. Sewoong Oh frorm University of Washington and Prof. Pramod Viswanath from Princeton University on multi-agent in game.

News

Mar 2026 Selected as Qualcomm Innovation Fellowship finalist.
Feb 2026 VLM-3R accepted to CVPR 2026.
Jan 2026 Neurosymbolic LoRA accepted as Oral at AAAI 2026 NeusymBridge Workshop.
Dec 2025 Presented MindGames and SPIN-Bench at Open AGI Symposium and hosted the MindGames competition at NeurIPS 2025 — great to meet all the teams!
Nov 2025 Had a detour on a startup idea and interviewed at YC — a great short journey!
Jul 2025 2 papers accepted to COLM 2025: SPIN-Bench and SWIFT.
Jul 2025 Leading organization of MindGames, a NeurIPS competition for multi-agent LLM.
Jun 2025 VideoLifter received Best Paper Award at CVPR 2025 AI4CC Workshop.

Selected Publications

* denotes equal contribution

	MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games Yunfei Xie, Kevin Wang, Bobby Cheng*, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang Preprint 2026 paper project code
	VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Zhiwen Fan, Jian Zhang, Renjie Li, Junge Zhang, Runjin Chen, Hezhen Hu, Kevin Wang, Peihao Wang, Huaizhi Qu, Shijie Zhou, Dilin Wang, Zhicheng Yan, Hongyu Xu, Justin Theiss, Tianlong Chen, Jiachen Li, Zhengzhong Tu, Zhangyang Wang, Rakesh Ranjan CVPR 2026 paper project code
	Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts Kevin Wang, Neel P Bhatt, Cong Liu, Junbo Li, Runjin Chen, Yihan Xi, Timothy Barclay, Alvaro Velasquez, Ufuk Topcu, Zhangyang Wang AAAI 2026 NeusymBridge Workshop (Oral) paper
	SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially? Kevin Wang, Jianzhu Yao, Ryan Hsieh, Haisu Zhou, Tianqing Zou, Zerui Cheng, Zhangyang Wang, Pramod Viswanath COLM 2025 paper project code
	SWIFT: Can Test-Time Scaling Improve World Foundation Model? Wenyan Cong, Hanqing Zhu, Peihao Wang, Bangya Liu, Dejia Xu, Kevin Wang, David Z Pan, Yan Wang, Zhiwen Fan, Zhangyang Wang COLM 2025 paper project code
	VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment Wenyan Cong, Hanqing Zhu, Kevin Wang, Jiahui Lei, Colton Stearns, Yuanhao Cai, Dilin Wang, Rakesh Ranjan, Matt Feiszli, Leonidas Guibas, Zhangyang Wang CVPR 2025 AI4CC Workshop (Best Paper Award) paper project code
	FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting Hengyu Liu, Yuehao Wang, Chenxin Li, Ruisi Cai, Kevin Wang, Wuyang Li, Pavlo Molchanov, Peihao Wang, Zhangyang Wang CVPR 2025 paper project code
	On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability Kevin Wang, Junbo Li, Neel P Bhatt, Yihan Xi, Qiang Liu, Ufuk Topcu, Zhangyang Wang NeurIPS 2024 Workshop on Language Gamification paper code
	LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS Kevin Wang, Zhiwen Fan, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang NeurIPS 2024 (Spotlight) paper project code
	Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search Wenqing Zheng, S P Sharan, Zhiwen Fan, Kevin Wang, Yihan Xi, Zhangyang Wang IEEE TPAMI 2024 paper code
	InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds Zhiwen Fan, Wenyan Cong, Kairun Wen, Kevin Wang*, Jian Zhang, Xinghao Ding, Danfei Xu, Boris Ivanovic, Marco Pavone, Georgios Pavlakos, Zhangyang Wang, Yue Wang Preprint 2024 paper project code
	Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation Wenqing Zheng, S P Sharan, Ajay Jaiswal, Kevin Wang, Yihan Xi, Dejia Xu, Zhangyang Wang ICML 2023 paper code

Experience

University of Texas at Austin

Mar 2022 – Present

Research Assistant, VITA Group

3D Gaussian compression achieving 15x reduction (400+ GitHub stars, NeurIPS Spotlight)
Transformer-based language model for syntax error-free Python code generation (ICML)
Symbolic visual RL with neural-guided differentiable expression search (TPAMI)

Sony

May 2025 – Aug 2025

Applied AI Research Intern

Compression and speedup of 3D Gaussian Splatting

SparkCognition

Jun 2022 – Aug 2022

Machine Learning Engineer Intern

Dual-layer classification for malware detection; 95% precision on unseen malware
Feature pruning reduced runtime by 40%; Kubernetes training reduced time by 30%

Education

University of Texas at Austin

2022 – Present

Ph.D. in Electrical & Computer Engineering, advised by Prof. Atlas Wang

University of Texas at Austin

2018 – 2022

B.S. in Computer Science & B.S. in Mathematics | GPA: 3.78/4.0

Services

Competition Organizer: MindGames (NeurIPS 2025)