dynamic environments
Environments that change over time, necessitating AI systems to adapt their strategies and actions in response to new conditions or information. This is especially relevant in real-time applications.
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
- CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
- DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
- Decoupled Entropy Minimization
- EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
- EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
- HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
- Human-assisted Robotic Policy Refinement via Action Preference Optimization
- Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors
- NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes
- Open-World Drone Active Tracking with Goal-Centered Rewards
- PlayerOne: Egocentric World Simulator
- PlayerOne: Egocentric World Simulator
- RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
- Reliably detecting model failures in deployment without labels
- VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
- When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions
- Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs