Shunyu Liu

Affiliations

Nanyang Technological University

papers

396

total citations

papers (13)

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

ICCV 2025arXiv

220

citations

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

NEURIPS 2025arXiv

106

citations

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

NEURIPS 2025arXiv

citations

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

NEURIPS 2025arXiv

citations

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

NEURIPS 2025arXiv

citations

Holistic Semantic Representation for Navigational Trajectory Generation

AAAI 2025arXiv

citations

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

AAAI 2025arXiv

citations

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

AAAI 2025

citations

Tree of Preferences for Diversified Recommendation

NEURIPS 2025arXiv

citations

Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location

AAAI 2025

citations

Shunyu Liu

Affiliations

papers (13)

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

VORTA: Efficient Video Diffusion via Routing Sparse Attention

Lookaround Optimizer: $k$ steps around, 1 step average

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Holistic Semantic Representation for Navigational Trajectory Generation

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

Tree of Preferences for Diversified Recommendation

Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location

papers (13)

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

VORTA: Efficient Video Diffusion via Routing Sparse Attention

Lookaround Optimizer: $k$ steps around, 1 step average

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Holistic Semantic Representation for Navigational Trajectory Generation

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

Tree of Preferences for Diversified Recommendation

Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location