Kaixuan Ji
6 papers · 2022–2025 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
👑
Triple Crown
Venues
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Learning Types · Machine Learning
(4)
Natural Language Processing
(3)
Core AI
(3)
Deep Learning
(2)
Learning Paradigms
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Application Areas
(1)
Applications
(1)
Generation · Natural Language Processing
(1)
Generation · Computer Vision
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Keywords
reinforcement learning from human feedback
(2)
prompt tuning
(2)
parameter efficiency
(2)
reinforcement learning
(2)
text-to-image generation
(1)
language model alignment
(1)
natural language understanding
(1)
nash equilibrium
(1)
policy search
(1)
self-play
(1)
text retrieval
(1)
regret bound
(1)
diffusion model
(1)
transition kernel
(1)
benchmark dataset
(1)
zero-shot generalization
(1)
policy alignment
(1)
linear mixture mdp
(1)
adversarial reward
(1)
pre-trained language model
(1)
Papers
Self-Play Preference Optimization for Language Model Alignment
ICLR 2025
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
ICLR 2024
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
ICML 2024
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
NeurIPS 2024
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
EMNLP 2023
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks
ACL 2022