Lei Song
27 papers · 2015–2026 · 10 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (61) π Conference Polyglot Β· Gold π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π€
Dynamic Duo
(16)
π
Grand Slam
π
Triple Crown
β‘
Prolific Year Β· Prolific
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Renaissance Researcher
(8)
ποΈ
Keyword Collector
(124)
Venues
Top co-authors
Research topics
Artificial Intelligence
(17)
Machine Learning
(14)
Core AI
(14)
Reinforcement Learning
(8)
Mathematics & Optimization
(7)
Learning Types Β· Machine Learning
(7)
Deep Learning
(6)
Methods
(6)
Optimization
(6)
Natural Language Processing
(5)
Architectures
(5)
Core Methods
(5)
Learning Types Β· Deep Learning
(5)
Optimization & Theory
(5)
Learning Paradigms
(4)
Keywords
graph neural network
(4)
in-context learning
(3)
few-shot learning
(3)
traveling salesman problem
(3)
combinatorial optimization
(3)
bayesian optimization
(3)
neural network
(2)
large language model
(2)
transfer learning
(2)
black-box optimization
(2)
reinforcement learning
(2)
vision-language model
(2)
question answering
(2)
information bottleneck
(2)
offline reinforcement learning
(2)
monte carlo tree search
(2)
multi-hop reasoning
(2)
text classification
(1)
catastrophic forgetting
(1)
bayesian inference
(1)
Papers
See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning
CVPR 2026
Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data Generation
IJCNLP 2025
Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning
ICLR 2025
Exploring Rationale Learning for Continual Graph Learning
AAAI 2025
From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
ICML 2025
Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models
NAACL 2025
HePa: Heterogeneous Graph Prompting for All-Level Classification Tasks
AAAI 2025
Learning to Select In-Context Demonstration Preferred by Large Language Model
ACL 2025
Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions
L4DC 2025
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
ACL 2025
Reinforced In-Context Black-Box Optimization
IJCAI 2025
Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning
ICML 2025
Diversification of Adaptive Policy for Effective Offline Reinforcement Learning
IJCAI 2024
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
ACL 2024
Monte Carlo Tree Search based Space Transfer for Black Box Optimization
NeurIPS 2024
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
ICML 2024
Protecting Your LLMs with Information Bottleneck
NeurIPS 2024
Stochastic Bayesian Optimization with Unknown Continuous Context Distribution via Kernel Density Estimation
AAAI 2024
TimeX++: Learning Time-Series Explanations with Information Bottleneck
ICML 2024
Whittle Index with Multiple Actions and State Constraint for Inventory Management
ICLR 2024
H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem
AAAI 2023
Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem
AAAI 2023
Robust Situational Reinforcement Learning in Face of Context Disturbances
ICML 2023
Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization
NeurIPS 2022
Model Checking Probabilistic Epistemic Logic for Probabilistic Multiagent Systems
IJCAI 2018
A Simple Probabilistic Extension of Modal Mu-calculus
IJCAI 2015
Planning for Stochastic Games with Co-Safe Objectives
IJCAI 2015