Kaile Wang
4 papers · 2025–2025 · 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 · Bronze
🗺️
Taxonomy Completionist
(19)
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Machine Learning
(3)
Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory · Machine Learning
(2)
Reinforcement Learning
(1)
Generation
(1)
Methods
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
reinforcement learning from human feedback
(3)
large language model
(2)
language model alignment
(2)
preference learning
(1)
safety alignment
(1)
data compression
(1)
bayesian network
(1)
human preference
(1)
preference data
(1)
language alignment
(1)
alignment fine-tuning
(1)
model elasticity
(1)
pre-training distribution
(1)
harmful output mitigation
(1)
distribution induction
(1)
sentence-level alignment
(1)
helpful assistant
(1)
elastic collapse
(1)
helpful harmlessness
(1)
harmlessness annotation
(1)
Papers
Language Models Resist Alignment: Evidence From Data Compression
ACL 2025
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
ACL 2025
Reward Generalization in RLHF: A Topological Perspective
ACL 2025
Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction
AAAI 2025