Yancheng Wang

Biography

Yancheng Wang recently completed his Ph.D. in Computer Science at Arizona State University, advised by Prof. Yingzhen Yang. His research focuses on LLM reasoning and agents, LLM post-training, multimodal learning, efficient and robust deep learning, and generative models. He has research experience at Meta Superintelligence Labs, Amazon AWS AI, Amazon Alexa AI, and Kuaishou U.S. R&D Center. His work has been published in leading venues including ICML, ICLR, NeurIPS, ACL, TPAMI, IJCV, UAI, NAACL, and AAAI.

Research Interests

LLM Reasoning & Agents
LLM Post-Training
Multimodal Learning
Computer Vision
Efficient & Robust Deep Learning
Model Compression
Deep Generative Models
Graph Learning

Industrial Experience

Meta Superintelligence Labs (MSL) · Research Scientist Intern 2025

Worked on LLM post-training and multimodal learning.
Amazon AWS AI · Applied Scientist Intern 2024

Worked on automatic evaluation of LLM-powered agents in conventional scenarios.
Amazon Alexa AI · Applied Scientist Intern 2023

Worked on LLM-powered autonomous agents for general-purpose recommendation.
KuaiShou U.S. R&D Center · Research Intern 2021

Worked on neural architecture search for image reconstruction.

Publications

2026

ICML 2026

IBMA: Information Bottleneck-Based Multimodal Alignment

Yancheng Wang, Zeyu Dong, Dongfang Sun, Alvin C Silva, Teresa Wu, Yingzhen Yang

International Conference on Machine Learning (ICML), 2026

ACL 2026

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu

Findings of the Association for Computational Linguistics: ACL, 2026

ICLR 2026

VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation

Yancheng Wang, Osama Hanna, Ruiming Xie, Xianfeng Rui, Maohao Shen, Xuedong Zhang, Christian Fuegen, Jilong Wu, Debjyoti Paul, Arthur Guo, Zhihong Lei, Ozlem Kalinli, Qing He, Yingzhen Yang

International Conference on Learning Representations (ICLR), 2026

ICLR 2026

Low-Rank Few-Shot Node Classification by Node-Level Graph Diffusion

Yancheng Wang, Chengshuai Zhao, Dongfang Sun, Huan Liu, Yingzhen Yang

International Conference on Learning Representations (ICLR), 2026

2025

TPAMI

Efficient Visual Transformer by Learnable Token Merging

Yancheng Wang, Yingzhen Yang

Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

UAI 2025

Informative Synthetic Data Selection for Thorax Disease Classification

Yancheng Wang, Rajeev Goel, Marko Jojic, Alvin C Silva, Teresa Wu, Yingzhen Yang

Conference on Uncertainty in Artificial Intelligence (UAI), 2025

TMLR

Diffusion on Graph: Augmentation of Graph Structure for Node Classification

Yancheng Wang, Changyu Liu, Yingzhen Yang

Transactions on Machine Learning Research (TMLR), 2025

Preprint

Differentiable Channel Selection in Self-Attention For Person Re-Identification

Yancheng Wang, Nebojsa Jojic, Yingzhen Yang

Under Major Revision for Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

DASFAA

Declarative Privacy-Preserving Inference Queries

Hong Guan, Ansh Tiwari, Summer Gautier, Rajan Hari Ambrish, Lixi Zhou, Deepti Gupta, Yancheng Wang, Yingzhen Yang, Chaowei Xiao, Kanchan Chowdhury, Jia Zou

International Conference on Database Systems for Advanced Applications (DASFAA) Demo, 2025

2024

NAACL 2024

RecMind: Large Language Model Powered Agent for Recommendation

Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Yingzhen Yang

Findings of the Association for Computational Linguistics: NAACL, 2024

NeurIPS 2024

Learning Low-Rank Feature for Thorax Disease Classification

Yancheng Wang, Rajeev Goel, Utkarsh Nath, Silva Alvin, Teresa Wu, Yingzhen Yang

Neural Information Processing Systems (NeurIPS), 2024

ICML 2024

Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired Approach

Yancheng Wang, Ping Li, Yingzhen Yang

International Conference on Machine Learning (ICML), 2024

BigData 2024

IDNet: A Novel Identity Document Dataset via Few-Shot and Quality-Driven Synthetic Data Generation

Lulu Xie*, Yancheng Wang*, Hong Guan*, Soham Nag, Rajeev Goel, Niranjan Erappa Narayana Swamy, Yingzhen Yang, Chaowei Xiao, Jonathan Prisby, Ross Maciejewski, Jia Zou

* Co-first authors with equal contribution. IEEE International Conference on Big Data (IEEE BigData), 2024

UAI 2024

Neural Architecture Search Finds Robust Models by Knowledge Distillation

Utkarsh Nath, Yancheng Wang, Yingzhen Yang

Conference on Uncertainty in Artificial Intelligence (UAI), 2024

IJCV

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation

Utkarsh Nath, Yancheng Wang, Yingzhen Yang

International Journal of Computer Vision (IJCV), 2024

ICLR WS

Low-Rank Graph Contrastive Learning for Node Classification

Yancheng Wang, Yingzhen Yang

ICLR Workshop on Bridging the Gap Between Practice and Theory in Deep Learning, 2024

2023

AAAI 2023

Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning

Kaize Ding*, Yancheng Wang*, Yingzhen Yang, Huan Liu

* Co-first authors with equal contribution.

Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2023

Preprint

Adaptive Cross-Layer Attention for Image Restoration

Yancheng Wang, Ning Xu, Yingzhen Yang

Service

Program Committee & Reviewer

ICML 2023 - 2026 (Awarded Gold Reviewer for ICML 2026)

NeurIPS 2023 - 2026

ICLR 2023 - 2026

NeurIPS 2022, SIGKDD 2022, AAAI 2022, ICML 2022, IJCAI 2022

TPAMI, IJCV