Songzhu Mei
5 papers · 2023–2025 · 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 · Bronze
🗺️
Taxonomy Completionist
(18)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(3)
Deep Learning
(3)
Reinforcement Learning
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Methods
(3)
Optimization & Theory · Machine Learning
(3)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
multi-agent reinforcement learning
(3)
value factorization
(2)
large language model
(2)
distributional reinforcement learning
(1)
parameter sharing
(1)
model inference
(1)
sample selection
(1)
neural network expressivity
(1)
supervised fine-tuning
(1)
mixing network
(1)
dormant neuron
(1)
weight transfer
(1)
cooperative game
(1)
policy network
(1)
inference acceleration
(1)
heterogeneous computing
(1)
speculative decoding
(1)
game-theoretic analysis
(1)
shapley value
(1)
risk-sensitive reinforcement learning
(1)
Papers
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference
EMNLP 2025
GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
ICML 2025
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis
ACL 2025
The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
NeurIPS 2024
RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
NeurIPS 2023