Zhebo Wang
3 papers · 2026–2026 · 1 venue · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Venues
Top co-authors
Research topics
Keywords
adversarial fingerprint
(2)
ownership verification
(1)
lora adapter
(1)
group relative policy optimization
(1)
text to speech
(1)
execution feedback
(1)
policy
(1)
stealthiness
(1)
homologous model variants
(1)
invariant intrinsic comprehension features
(1)
markdown tables
(1)
perplexity hiding
(1)
thoughts
(1)
dual embedding space
(1)
speaker pairs
(1)
online optimization
(1)
verification confidence score
(1)
Papers
Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
EMNLP 2026
SRAF: Stealthy and Robust Adversarial Fingerprint for Copyright Verification of Large Language Models
EMNLP 2026
TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
EMNLP 2026