Chuxiong Sun
8 papers · 2024–2026 · 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
(23)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(6)
Core AI
(6)
Learning Types · Machine Learning
(6)
Deep Learning
(4)
Core Methods
(3)
Learning Types · Deep Learning
(3)
Reinforcement Learning
(2)
Methods
(2)
Natural Language Processing
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Generation
(1)
Learning Paradigms
(1)
Optimization & Theory
(1)
Keywords
large language model
(3)
causal inference
(2)
reinforcement learning
(2)
structural causal model
(2)
multi-agent communication
(2)
text generation
(1)
preference learning
(1)
contrastive learning
(1)
language model alignment
(1)
cooperative multi-agent system
(1)
graph representation
(1)
token classification
(1)
model alignment
(1)
distribution shift
(1)
test-time adaptation
(1)
counterfactual reasoning
(1)
language model
(1)
multimodal learning
(1)
feedback loop
(1)
communication efficiency
(1)
Papers
Group Causal Policy Optimization for Post-Training Large Language Models
AAAI 2026
HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
AAAI 2026
M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference
AAAI 2026
Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration
CVPR 2026
TMAE:Learning Targeted Multi-Agent Exploration via Causal Inference
AAAI 2026
Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models
IJCAI 2025
Training Language Model to Critique for Better Refinement
ACL 2025
T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration
AAAI 2024