Jun Wang
- A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
- CMoB: Modality Valuation via Causal Effect for Balanced Multimodal Learning
- Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
- Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
- Curious Causality-Seeking Agents Learn Meta Causal World
- DGCBench: A Deep Graph Clustering Benchmark
- EconGym: A Scalable AI Testbed with Diverse Economic Tasks
- Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
- GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
- InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
- MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
- MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation
- Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
- ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
- Risk-aware Direct Preference Optimization under Nested Risk Measure
- Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
- Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
- Self-Verifying Reflection Helps Transformers with CoT Reasoning
- Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
- Switchable Token-Specific Codebook Quantization For Face Image Compression
- ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
- Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding