Boxun Li
8 papers · 2021–2026 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 👥 Mega-Team · Squad
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(3)
Computer Science
(2)
Computer Vision
(2)
Natural Language Processing
(2)
Analysis
(2)
Learning Types · Deep Learning
(2)
Systems
(2)
Machine Learning
(1)
Reinforcement Learning
(1)
Applications
(1)
Architectures
(1)
Learning Types · Machine Learning
(1)
Methods
(1)
Keywords
reinforcement learning
(3)
large language model
(2)
action recognition
(1)
scene understanding
(1)
object detection
(1)
attention mechanism
(1)
human-object interaction
(1)
safety alignment
(1)
reinforcement learning from human feedback
(1)
dynamic scheduling
(1)
distributed training
(1)
interaction detection
(1)
relation reasoning
(1)
semantic embedding
(1)
end-to-end learning
(1)
training throughput
(1)
context switching
(1)
human preference
(1)
human-object interaction detection
(1)
resource scheduling
(1)
Papers
DynaRL: Flexible and Dynamic Scheduling of Large-Scale Reinforcement Learning Training
OSDI 2026
RLinf: Flexible and Efficient Large-Scale Reinforcement Learning via Macro-to-Micro Flow Transformation
OSDI 2026
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
ICML 2025
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
ACL 2025
Improving Human-Object Interaction Detection via Phrase Learning and Label Composition
AAAI 2022
Motion Sensitive Contrastive Learning for Self-Supervised Video Representation
ECCV 2022
Tracking Objects As Pixel-Wise Distributions
ECCV 2022
End-to-End Human Object Interaction Detection With HOI Transformer
CVPR 2021