Author

Chen-Yi Huang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

RobotAPO: Adversarial Physics Preference Optimization for Robotic Manipulation Video Generation

Robotic manipulation videos are increasingly used as visual plans for embodied agents, but optimizing purely for visual plausibility often fails to capture the fragile physical manifold of real-world interactions. Even minor physics-violating errors at the interaction boundary, such as interpenetration or premature obj...

Ke-Rui Li, Zhe Jing, Chen-Yi Huang et al. · 0 citations

#artificial intelligence Preprint Oct 2026

Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally

A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original, correct description with no trace of the target. We call this dissociation the train/inference gap,...

Arun Josephraj Arokiaraj, Chen-Yi Huang, Ze-Kun Wu et al. · 0 citations