Jikun Kang
Contact me at firstname dot lastname at mail dot mcgill dot ca

Room 305
McConnel Building
McGill University
I am a Ph.D. candidate at McGill University. I am fortunate to be advised by Prof. Xue (Steve) Liu.
My research interest lies in the domain of Reinforcement Learning, Meta-RL and Applied RL. Recently, I’m working on improving RL policy generalization and sample-efficiency.
news
Mar 05, 2025 | Thrilled to announce our paper “LM2: Large Memory Models for Long Context Reasoning” has been accepted at ICLR 2-25 Reasonings and Planning for LLMs. |
---|---|
Feb 26, 2025 | Happy to share new web agent benchmark: ~~WebGames~. Paper BlogPost Code |
Feb 21, 2025 | Honored to share our recent research work on memory-based Transformer models: ~~LM2: Large Memory Models~. Paper BlogPost Code |
Dec 10, 2024 | Glad to share that I have been selected as an Outstanding Reviewer for NeurIPS 2024! |
Jul 01, 2024 | I’m excited to share MindStar, our latest research on large language model reasoning. |
latest posts
selected publications
- ICLRLM2: Large Memory Models for Long Context ReasoningICLR 2025 Reasoning and Planning for LLMs, 2025
- PreprintMindstar: Enhancing math reasoning in pre-trained llms at inference timearXiv preprint arXiv:2405.16265, 2024
- ICMLThink Before You Act: Decision Transformers with Internal Working MemoryarXiv preprint arXiv:2305.16338, 2024
- IWQoSIncentive Temperature Control for Green Colocation Data Centers via Reinforcement LearningIn IEEE/ACM International Symposium on Quality of Service (IWQoS), 2024
- Smart GridPeer-to-Peer Energy Trading and Energy Conversion in Interconnected Multi-Energy Microgrids Using Multi-Agent Deep Reinforcement LearningIEEE Trans. Smart Grid, 2022
- CoRL