Project
Topics
1. Adaptive Resource Allocation Strategies (e.g. Load Balancing) for Distributed Large Language Models in Edge AI Networks
-
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models (NeurIPS 2024) neurips
-
Learning with Adaptive Resource Allocation (ICML 2024) pmlr
Team Members: Shale Lucas, Omar Stevens
2. Standardized Benchmarking of Multi-Agent Distributed Machine Learning in Augmented Reality
- BenchMARL: Benchmarking Multi-Agent Reinforcement Learning (NeurIPS 2024) neurips
- Simulating autonomous agents in augmented reality sciencedirect
Team Members: Parthkumar Joshi, Klea Meta
3. Resilient Data Routing Algorithms for NextGen Multi-Agent Connected Autonomous Vehicle Networks
- Autonomous Agents for Collaborative Task Under Information Asymmetry (NeurIPS 2024) neurips
- Fault-Tolerant Consensus of Multi-Agent System With Distributed Adaptive Protocol (IEEE Transactions on Cybernetics, 2015) nih
Team Members: Marcley Colin, Mustafa Ahmet Must Donmez
4. Leveraging Distributed AI in NextGen Networks for Real-Time Autonomous Risk Management
- Risk Management for Distributed Arbitrage Systems: Integrating Artificial Intelligence (ICAIFI 2025) arxiv
- AI re-shaping financial modeling (Nature 2025) nature
Team Members: Erik Brobyn, Arnav Deepaware
5. Real-time State Synchronization Solutions for Decentralized AI Agents Over Slow Networks
- Decentralized Training of Foundation Models in Heterogeneous Environments (NeurIPS 2022) neurips
- Fine-tuning Language Models Over Slow Networks Using Activation Compression with Guarantees (NeurIPS 2022) neurips
Team Members: Brandon Bedoya, Haoliang Zhang
6. Fault-Tolerant Consensus Algorithms for Multi-Agent Networks Facing Random Attacks and Sensor Failures in Multimodal Models (e.g. Vision Language Models)
- Fault-Tolerant Consensus of Multi-Agent Systems Subject to Multiple Faults and Random Attacks (2024) hull
- Fault-Tolerant Consensus of Multi-Agent System With Distributed Adaptive Protocol (IEEE Transactions on Cybernetics, 2015) nih
Team Members: Gaurav Gupta, Joshua Kenneth Jimenez
7. Distributed Multi-Agent Augmented Reality Environments Using Game-Theoretic Theory of Mind for Strategic Interaction
-
Distributed Computing Meets Game Theory: Robust Mechanisms for Rational Secret Sharing and Multiparty Computation (PODC 2006) cornell
- Dynamics at the Boundary of Game Theory and Distributed Computing (ACM EC 2017) columbia
Team Members: Alhassana Diallo, Sadia Nawaz
8. Multi-Agent MIMO Strategies for Robust Communication in Distributed Wireless Networks
- Multi-Agent Coordination via Multi-Level Communication (NeurIPS 2024) neurips
- Machine Learning Helps Robot Swarms Coordinate (Caltech, 2020) caltech
Team Members: Minning Liu, Emmanuelle Padilla
9. Interpretable Multi-Agent Coordination Algorithms for Heterogenous (Urban/Suburban/Rural) Autonomous Mobility Networks
- Language Grounded Multi-agent Reinforcement Learning with Zero-shot Ad-hoc Teamwork (NeurIPS 2024) neurips
- Autonomous Agents for Collaborative Task Under Information Asymmetry (NeurIPS 2025) neurips
Team Members: Rivaldo Lumelino, Alexandr Voronovich
10. Power Management and Energy-Efficient Protocols for Distributed AI Agents on Resource-Constrained Devices
-
Distributed Task Offloading and Resource Allocation for Latency Sensitive Mobile Edge Computing (arxiv, 2024) arxiv
-
Learning with Adaptive Resource Allocation (ICML 2024) pmlr
Team Members: Mehedi Hasan, Aidan Adonis Pena
11. Distributed Vision-Language Model (VLM) Framework for Optimizing Building Engineering (e.g. HVACs, Regulations, Energy Efficiency Monitoring)
- Distributed VLMs: Efficient Vision-Language Processing through Cloud-Edge Collaboration (2025) columbia
- Opportunities of applying Large Language Models in building energy sector sciencedirect
Team Members: Christopher Luis Barbosa Jr, Sean Jenkins
ADDITIONAL PROJECT IDEAS WHICH ARE NOT TAKEN BY ANY STUDENT TEAM YET
12. Efficient and Interpretable Communication Protocols in Deep Multi-Agent Reinforcement Learning and Control Systems
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning (NeurIPS 2016) neurips
- Language Grounded Multi-agent Reinforcement Learning with Zero-shot Ad-hoc Teamwork (NeurIPS 2024) neurips
13. Secure and Private Cooperation Protocols for Large Swarm Robotic Missions
- Secure and Secret Cooperation in Robotic Swarms (MIT, 2023) mit
- Machine Learning Helps Robot Swarms Coordinate (Caltech, 2020) caltech
14. Semantic Web Integration for Communication and Knowledge Sharing in Autonomous Multi-Agent Systems
-
From Semantic Web and MAS to Agentic AI (arxiv, 2024) arxiv
-
Multi-Agent Coordination via Multi-Level Communication (NeurIPS 2024) neurips
15. Dynamic Task Offloading and Optimization Frameworks for Edge-Aware Multi-Agent Distributed Job Scheduling (e.g. Phones/AR/Connected Autonomous Vehicles)
-
Dynamic Task Offloading Edge-Aware Optimization Framework for AI-Driven UAV Networks (Nature Scientific Reports 2024) nature
-
Distributed Task Offloading and Resource Allocation for Latency Sensitive Mobile Edge Computing (arxiv, 2024) arxiv
16. Smart Arbitration and Decision-Making Protocols for Decentralized Agentic Systems in Heterogeneous Environments
- Multi-Agent Coordination via Multi-Level Communication (NeurIPS 2024) neurips
- Decentralized Safe and Scalable Multi-Agent Control under Limited Actuation (ICRA 2025) arxiv
17. Multi-Agent Planning Under Unreliable and Bandwidth-Limited Network Conditions
- Decentralized Training of Foundation Models in Heterogeneous Environments (NeurIPS 2022) neurips
- Fine-tuning Language Models Over Slow Networks Using Activation Compression with Guarantees (NeurIPS 2022) neurips
18. AI Agents for Distributed Chip Design
- MACO: A Multi-Agent LLM-Based Hardware/Software Co-Design Framework for CGRAs (Arxiv 2025) arxiv
- MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging arxiv