This paper proposes QAROO, an AI-driven online task offloading framework for wireless-powered mobile edge computing (MEC) networks. It integrates quantum neural networks, attention mechanisms, and recurrent neural networks to co-optimize computing and energy resources, offering an efficient and stable solution for dynamic IoT environments.

This paper evaluates the use of AI-based reinforcement learning agents for developing an AI-assisted pilot training module for specific aircraft aerobatic maneuvers. It demonstrates that AI can learn and execute various complex maneuvers with a quality comparable to professional pilots, utilizing both real pilot data and artificially created trajectories.

This paper introduces an AI-based Automatic Ground Collision Avoidance System (AGCAS) for advanced jet trainers. It utilizes a customized Soft Actor-Critic (SAC) algorithm, integrated with a custom Convolutional Neural Network (CNN) and hyperparameter optimization, to enhance safety and operational capabilities by effectively avoiding ground collisions within limited observation spaces.

This article introduces a pilot-activated recovery system (PARS) for advanced jet trainers that uses an advanced reinforcement learning (RL) architecture, specifically a Soft Actor-Critic (SAC) model, to improve operational efficiency and aircraft upset recovery while considering negative-g forces on the pilot. The system outperforms conventional control methods in expert evaluations.

This paper introduces a theoretical framework for accelerating the evaluation of Conditional Value-at-Risk (CVaR) value functions in Partially Observable Markov Decision Processes (POMDPs) with formal performance guarantees. It derives novel CVaR bounds for random variables, enabling faster policy evaluation through action elimination using simplified models.

This paper introduces RebuttalAgent, an AI framework that grounds academic rebuttal in Theory of Mind (ToM) to generate strategic and persuasive responses. It proposes a ToM-Strategy-Response (TSR) pipeline, supported by a large-scale synthetic dataset (RebuttalBench) and a specialized evaluation model (Rebuttal-RM), significantly outperforming existing models in automated and human evaluations.

MonoRace is an autonomous drone racing system that utilizes a monocular camera and IMU to achieve champion-level performance, notably winning the A2RL 2025 competition. It features robust state estimation combining neural-network-based gate segmentation with a drone model, an offline optimization procedure, and a neural network for guidance and control.

The paper introduces a comprehensive method and ecosystem (NexAU, NexA4A, NexGAP) to overcome limitations in scaling interactive environments for training agentic Large Language Models (LLMs). This infrastructure enables the systematic generation of diverse, complex, and realistically grounded interaction trajectories for LLMs.

This paper introduces Reward Forcing, a novel framework for efficient streaming video generation that tackles issues like diminished motion dynamics and over-reliance on initial frames. It achieves state-of-the-art performance by combining EMA-Sink for improved long-term context and Rewarded Distribution Matching Distillation (Re-DMD) to enhance motion quality.

This paper introduces Stage-Aware Reinforcement (StARe), a novel module that decomposes long-horizon robotic manipulation tasks into semantically meaningful stages, providing dense, interpretable reinforcement signals. Integrated into the Imitation → Preference → Interaction (IPI) fine-tuning pipeline, StARe significantly improves the performance and robustness of Vision-Language-Action (VLA) models on complex manipulation tasks.