papers

Publications (5)

cs.AI2026

Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative Side Decidable

Wenhui Chen, Jianlin Chen, Ziyao Lin +1

When a self-improving AI-for-science system claims a new capability, the evidence is usually a benchmark delta, a description-length gate, or a p-value. None separates a real gain…

cs.AI2026

Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets

Wenhui Chen, Jianlin Chen, Ziyao Lin +2

Language models are increasingly promoted from examinees to examiners: they write the test suites, answer keys, rubrics, and reward functions that define correctness for other syst…

cs.AI2026

The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale

Wenhui Chen, Jianlin Chen, Ziyao Lin +1

The paper proposes that the ability of sequence models to solve tasks depends more on their internal access structure (a compressive state channel plus a scalable index channel) th…

#sequence modeling#representation learning#information theory#model architecture
cs.CV2026

DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation

Zhechao Wang, Yiming Zeng, Lufan Ma +4

Synthesis of diverse driving scenes serves as a crucial data augmentation technique for validating the robustness and generalizability of autonomous driving systems. Current method…

eess.AS2025

FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

Tong Lei, Qinwen Hu, Ziyao Lin +5

The prevailing method for neural speech enhancement predominantly utilizes fully-supervised deep learning with simulated pairs of far-field noisy-reverberant speech and clean speec…