Scholar

Liyuan Ma

Google Scholar ID: j6T8Tk8AAAAJ

zhejiang university

image synthesis， generative modelGANDiffusion Model

Google Scholar↗

Citations & Impact

All-time

Citations

79

H-index

6

i10-index

2

Publications

15

Co-authors

0

Contact

No contact links provided.

Publications

5 items

When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance

2025

Cited

0

From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment

2025

Cited

0

C-Evolve: Consensus-based Evolution for Prompt Groups

2025

Cited

0

InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO

2025

Cited

0

Self-Guidance: Boosting Flow and Diffusion Generation on Their Own

arXiv.org · 2024

Cited

1

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)