Profiles2024-2026ORCID 0000-0001-6533-5176
Kai Lv
Beijing Jiaotong University
7Papers
6Last author
9Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Think How Your Teammates Think: Active Inference Can Benefit Decentralized ExecutionAuthor 7 of 7AAAI 2026 · 1 citation
- Local Motion Matters: A Deconstruct–Recompose Paradigm for Reinforcement Learning Pre-training from VideosAuthor 5 of 5CVPR 2026
- Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement LearningAuthor 7 of 7ICML 2026
- CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and TimelinessAuthor 7 of 7AAAI 2025 · 7 citations
- From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-trainingAuthor 7 of 7ACM MM 2025 · 1 citation
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-IdentificationAuthor 1 of 6AAAI 2025 · 1 citation
- What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return PredictionAuthor 6 of 6AAAI 2024 · 18 citations
