Kui Zhang
3 papers · 2024–2026 · 3 venues · 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.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
generalization
(1)
surrogate model
(1)
policy training
(1)
blind face restoration
(1)
iterative training
(1)
reasoning optimization
(1)
distributed llm serving
(1)
consumer-grade gpu
(1)
prefill-decode scheduling
(1)
transmission scheduling
(1)
inference latency optimization
(1)
chunking algorithm
(1)
problem space mapping
(1)
overfitting
(1)
adversarial obfuscation
(1)
domain-consistent
(1)
Papers
Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning
AAAI 2026
Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication
EMNLP 2025
Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
ICML 2024