Get started
Author

Shuoyang Sun

Observed name: Sun, Shuoyang
Observed institution: Harbin Institute of Technology
ORCID: 0009-0006-8695-7218
Observed ORCID: 0009-0006-8695-7218
OpenAlex ID: A5121824950
When History Helps and Hurts: Selective History Use across Multimodal Turns
2026 · Sun, Shuoyang, Gu, Kerui, et al. · arXiv (Cornell University)
PDF
From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
2026 · Hong, Jiaxin, Peng, Yuxin, et al. · arXiv (Cornell University)
PDF
GaussTrap: Stealthy Backdoor Attacks on 3D Gaussian Splatting for Targeted Scene Misperception
2026 · Jiaxin Hong, Sixu Chen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
2026 · Sun, Yi, Zhang, Zhiqi, et al. · arXiv (Cornell University)
PDF
Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
2026 · Chen, Sixu, Chen, Xiang, et al. · arXiv (Cornell University)
PDF
Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
2026 · Sun, Shuoyang, Dai, Chang, et al. · arXiv (Cornell University)
PDF
ScaleGS: Towards Scalable and Efficient 3d Gaussian Splatting
2026 · Shuoyang Sun, Jiaxin Hong, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
Diffusion-Based Natural Adversarial Perturbations Towards Segment Anything Model
2026 · Haodong Xiao, Wenbo Yu, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
2026 · Zhang, Zhiqi, Zhong, Xinhao, et al. · arXiv (Cornell University)
PDF
Information-Theoretic Point Cloud Defense: Harnessing Conditional Mutual Information Against Adversarial Attacks
2026 · Kaiwen Zhang, Xinhao Zhong, et al. · Lecture notes in computer science
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation
2026 · Shuoyang Sun, Jiaxin Hong, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
GaussTrap: Stealthy Backdoor Attacks on 3D Gaussian Splatting for Targeted Scene Misperception
2025 · Hong, Jiaxin, Chen, Sixu, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count:
H-index:
I10-index:
Year
Topic
Type