Qiyang Li
14 papers · 2019–2026 · 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π Grand Slam
π§¬
Topic Evolution
π₯
Mega-Team Β· Squad
π
Triple Crown
ποΈ
Keyword Collector
(65)
π₯
Unstoppable Β· Bronze
π
Trend Setter
π
Century Club Β· Bronze
Top co-authors
Research topics
Reinforcement Learning
(8)
Methods
(8)
Machine Learning
(7)
Artificial Intelligence
(6)
Deep Learning
(5)
Core AI
(5)
Learning Types Β· Machine Learning
(3)
Application Areas
(2)
Applications Β· Reinforcement Learning
(2)
Architectures
(2)
Learning Types Β· Deep Learning
(2)
Models
(2)
Optimization & Theory
(2)
Natural Language Processing
(1)
Applications Β· Natural Language Processing
(1)
Keywords
offline reinforcement learning
(3)
reinforcement learning
(2)
policy optimization
(2)
sequence modeling
(1)
sample efficiency
(1)
adversarial robustness
(1)
catastrophic forgetting
(1)
policy learning
(1)
imitation learning
(1)
theorem proving
(1)
robotic manipulation
(1)
density estimation
(1)
style transfer
(1)
curriculum learning
(1)
mathematical reasoning
(1)
model selection
(1)
transformer architecture
(1)
dynamic routing
(1)
flow matching
(1)
deep reinforcement learning
(1)
Papers
AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
AAAI 2026
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
ICLR 2025
Flow Q-Learning
ICML 2025
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
ICML 2025
RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
RSS 2025
OpenEQA: Embodied Question Answering in the Era of Foundation Models
CVPR 2024
REFACTOR: Learning to Extract Theorems from Proofs
ICLR 2024
Accelerating Exploration with Unlabeled Prior Data
NeurIPS 2023
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
ICLR 2023
Understanding the Complexity Gains of Single-Task RL with a Curriculum
ICML 2023
AdaCat: Adaptive categorical discretization for autoregressive models
UAI 2022
Offline Reinforcement Learning as One Big Sequence Modeling Problem
NeurIPS 2021
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
NeurIPS 2019
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
ICLR 2019