Xinyao Niu
3 papers · 2024–2025 · 2 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 · Silver
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
privacy preservation
(1)
responsible ai
(1)
machine unlearning
(1)
model editing
(1)
supervised fine-tuning
(1)
reward shaping
(1)
context length
(1)
right to be forgotten
(1)
continual pre-training
(1)
data mixture
(1)
gradient ascent
(1)
large language model
(1)
large-scale pretraining
(1)
chains-of-thought
(1)
domain balance
(1)
length upsampling
(1)
out-of-distribution reasoning
(1)
verifiable reward signals
(1)