Kaiyuan Li
5 papers · 2024–2026 · 4 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
🗺️
Taxonomy Completionist
(15)
🐣
Hot Topic Early Bird
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Machine Learning
(3)
Deep Learning
(2)
Application Areas
(2)
Core AI
(2)
Learning Types · Deep Learning
(2)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Robotics
(1)
Architectures
(1)
Capabilities
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Keywords
reinforcement learning
(1)
offline reinforcement learning
(1)
text summarization
(1)
sample complexity
(1)
policy learning
(1)
parameter sharing
(1)
online optimization
(1)
experimental design
(1)
robust performance
(1)
autoencoders
(1)
robot manipulation
(1)
language model
(1)
reward model
(1)
world model
(1)
progressive training
(1)
treatment effect
(1)
multi-view data
(1)
fairness constraint
(1)
key-value cache
(1)
inference speedup
(1)
Papers
Fairness-Aware Design for Contextual Experiments: Guaranteeing Reliability and Equity in Heterogeneous Subgroups
AAAI 2026
Progressive Supernet Training for Efficient Visual Autoregressive Modeling
CVPR 2026
Learning View-invariant World Models for Visual Robotic Manipulation
ICLR 2025
KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
NeurIPS 2024
Language Model Self-improvement by Reinforcement Learning Contemplation
ICLR 2024