Jiafei Lyu
15 papers · 2022–2026 · 7 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 ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (25) π Triple Crown
π€
Dynamic Duo
(14)
π
Keyword Champion
(2)
π
Grand Slam
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(83)
Top co-authors
Research topics
Reinforcement Learning
(11)
Methods
(10)
Machine Learning
(9)
Artificial Intelligence
(7)
Core AI
(7)
Learning Types Β· Machine Learning
(4)
Applications
(3)
Optimization & Theory
(3)
Deep Learning
(2)
Robotics
(2)
Application Areas
(2)
Capabilities
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Keywords
offline reinforcement learning
(4)
reinforcement learning
(3)
random network distillation
(2)
policy adaptation
(2)
optimal transport
(2)
sample efficiency
(2)
dynamics mismatch
(2)
dynamics shift
(2)
model-based reinforcement learning
(2)
chain-of-thought reasoning
(1)
direct preference optimization
(1)
preference learning
(1)
image generation
(1)
domain randomization
(1)
mathematical reasoning
(1)
novelty detection
(1)
benchmark evaluation
(1)
continuous control
(1)
domain adaptation
(1)
value function
(1)
Papers
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
AAAI 2026
Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint
ICLR 2025
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
AAAI 2025
SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning
AAAI 2025
VLP: Vision-Language Preference Learning for Embodied Manipulation
EMNLP 2025
World Models with Hints of Large Language Models for Goal Achieving
NAACL 2025
Cross-Domain Policy Adaptation by Capturing Representation Mismatch
ICML 2024
Exploration and Anti-Exploration with Distributional Random Network Distillation
ICML 2024
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
NeurIPS 2024
PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
ICML 2024
SEABO: A Simple Search-Based Method for Offline Imitation Learning
ICLR 2024
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
CVPR 2024
Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination
NeurIPS 2022
Efficient Continuous Control with Double Actors and Regularized Critics
AAAI 2022
Mildly Conservative Q-Learning for Offline Reinforcement Learning
NeurIPS 2022