4 papers
GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
Yunzhe Wang, Runhui Xu, Kexin Zheng +4
Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to pe…
Towards AI-Assisted Generation of Military Training Scenarios
Soham Hans, Volkan Ustun, Benjamin Nye +2
Achieving expert-level performance in simulation-based training relies on the creation of complex, adaptable scenarios, a traditionally laborious and resource intensive process. Al…
X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning
Yunzhe Wang, Soham Hans, Volkan Ustun
Human team tactics emerge from each player's individual perspective and their ability to anticipate, interpret, and adapt to teammates' intentions. While advances in video understa…
Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning
Volkan Ustun, Soham Hans, Rajay Kumar +1
Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Fra…