Author

Changti Wu

Observed names: CHANGTI WU, Wu, Changti

Institutions: Shanghai Key Laboratory of Trustworthy Computing, East China Normal University

Observed institutions: Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Communication University of China

ORCID: 0009-0009-9448-6657

Observed ORCID: 0009-0009-9448-6657

OpenAlex ID: A5069583018

LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

2026 · Lian, Shijie, Yu, Bin, et al. · arXiv (Cornell University) · 27

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers

2026 · Bin Yu, Shijie Lian, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 21

Privacy-Preserving Serverless Federated Learning Scheme for Internet of Things

2024 · Changti Wu, Lei Zhang, et al. · IEEE Internet of Things Journal · 20

Dual-Server-Based Lightweight Privacy-Preserving Federated Learning

2024 · Liangyu Zhong, Lulu Wang, et al. · IEEE Transactions on Network and Service Management · 14

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks

2025 · Lian, Shijie, Wu, Changti, et al. · arXiv (Cornell University) · 13

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

2026 · Bin Yu, Shijie Lian, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 10

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

2026 · Shijie Lian, Bin Yu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 9

3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models

2026 · Yu, Bin, Lian, Shijie, et al. · arXiv (Cornell University) · 7

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning

2026 · Changti Wu, Lulu Wang, et al. · ACM International Conference on Multimedia (ACM MM) · 6

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

2026 · DeepCybo Team, Bin, Yu, et al. · arXiv (Cornell University) · 6

TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models

2026 · Bin Yu, Xinming Wang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 6

PhysBrain 1.0 Technical Report

2026 · Lian, Shijie, Yu, Bin, et al. · arXiv (Cornell University) · 5

Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments

2026 · Lin, Xiaopeng, Yang, Ruoqi, et al. · arXiv (Cornell University) · 4

SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models

2026 · Wu, Changti, Yu, Bin, et al. · arXiv (Cornell University) · 2

RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models

2026 · Bin Yu, Yao Zhang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2

The Visualization of Cross-media Knowledge Graph of Tang and Song Poetry

2021 · Wenjuan Jiang, Chunfang Li, et al. · ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter) · 2

The Realization of Cross-Media Knowledge Graph of Tang and Song Poetry

2020 · CHANGTI WU, CHUNFANG LI, et al. · International Conference on Machine Learning and Cybernetics · 2

EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding

2026 · Wu, Changti, Fan, Ruizhe, et al. · arXiv (Cornell University)

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks

2026 · Shijie Lian, Changti Wu, et al.

Verifiable Private Federated Learning Achieving Low-Communication With CUR Decomposition

2026 · Changti Wu, Lulu Wang, et al. · IEEE Transactions on Dependable and Secure Computing

Works count: 21

Citation count: 160

H-index: 7

I10-index: 6