Publications

2026

SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation

Chengyue Huang*, Khang Vo Huynh*, Sebastian Elbaum, Zsolt Kira, Lu Feng

arXiv 2026

Paper

The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models

Shivang Chopra, Shaunak Halbe, Chengyue Huang, Brisa Maneechotesuwan, Zsolt Kira

CVPR 2026 , Highlight

Paper

MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization

Chengyue Huang*, Mellon M. Zhang*, Robert Azarcon, Glen Chou, Zsolt Kira

CVPR 2026

Paper

2025

Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models

Chengyue Huang*, Yuchen Zhu*, Sichen Zhu*, Jingyun Xiao, Moises Andrade, Shivang Chopra, Zsolt Kira

ICCV-W 2025

Paper

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

Chengyue Huang*, Brisa Maneechotesuwan*, Shivang Chopra, Zsolt Kira

CVPR 2025

Paper

Directional Gradient Projection for Robust Fine-tuning of Foundation Models

Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira

ICLR 2025

Paper

2024

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models

Junjiao Tian, Chengyue Huang, Zsolt Kira

NeurIPS 2024

Paper

2022

From Local to Global: Spectral-Inspired Graph Neural Networks

Ningyuan Huang, Soledad Villar, Carey E. Priebe, Da Zheng, Chengyue Huang, Lin Yang, Vladimir Braverman

NeurIPS-W 2022

Paper

Adversarial and Implicit Modality Imputation with Applications to Depression Early Detection

Yuzhou Nie*, Chengyue Huang*, Hailun Liang, Hongteng Xu

CAAI International Conference on Artificial Intelligence (CICAI) 2022

Paper