Ming Zhu

Wei Cai, Jian Zhao, Yuchen Yuan et al.

Multimodal Large Language Models (MLLMs), despite their advances, are hindered by their high hallucination tendency and heavy reliance on brittle, linear reasoning processes, leading to failures in complex tasks. To address these limitations, we introduce Visual Attention Reasoning (VAR), a novel framework that recasts grounded reasoning as a structured search over a reasoning trajectory space. VAR decomposes the reasoning process into two key stages: traceable evidence grounding and search-based chain-of-thought (CoT) generation, which incorporates a backtracking mechanism for self-correction. The search is guided by a multi-faceted reward function with semantic and geometric self-verification components, which penalize outputs that are not faithfully grounded in the visual input. We provide a theoretical analysis for our search strategy, validating its capability to find the correct solution with high probability. Experimental results show that our 7B model, VAR-7B, sets a new state-of-the-art on a comprehensive suite of hallucination and safety benchmarks, significantly outperforming existing open-source models and demonstrating competitive performance against leading proprietary systems.

Jiajun Ou, Xiao Guo, Ming Zhu et al.

The rapid development of unmanned aerial vehicles (UAV) puts forward a higher requirement for autonomous obstacle avoidance. Due to the limited payload and power supply, small UAVs such as quadrotors usually carry simple sensors and computation units, which makes traditional methods more challenging to implement. In this paper, a novel framework is demonstrated to control a quadrotor flying through crowded environments autonomously with monocular vision. The framework adopts a two-stage architecture, consisting of a sensing module and a decision module. The sensing module is based on an unsupervised deep learning method. And the decision module uses dueling double deep recurrent Q-learning to eliminate the adverse effects of limited observation capacity of an on-board monocular camera. The framework enables the quadrotor to realize autonomous obstacle avoidance without any prior environment information or labeled datasets for training. The trained model shows a high success rate in the simulation and a good generalization ability for transformed scenarios.

Ming Zhu, Xiao-Yang Liu, Anwar Walid

Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities. Hot spots easily appear in road intersections, where effective communication among vehicles is challenging. UAVs may serve as relays with the advantages of low price, easy deployment, line-of-sight links, and flexible mobility. In this paper, we study a UAV-assisted vehicular network where the UAV jointly adjusts its transmission control (power and channel) and 3D flight to maximize the total throughput. First, we formulate a Markov decision process (MDP) problem by modeling the mobility of the UAV/vehicles and the state transitions. Secondly, we solve the target problem using a deep reinforcement learning method, namely, the deep deterministic policy gradient (DDPG), and propose three solutions with different control objectives. Deep reinforcement learning methods obtain the optimal policy through the interactions with the environment without knowing the environment variables. Considering that environment variables in our problem are unknown and unmeasurable, we choose a deep reinforcement learning method to solve it. Moreover, considering the energy consumption of 3D flight, we extend the proposed solutions to maximize the total throughput per unit energy. To encourage or discourage the UAV's mobility according to its prediction, the DDPG framework is modified, where the UAV adjusts its learning rate automatically. Thirdly, in a simplified model with small state space and action space, we verify the optimality of proposed algorithms. Comparing with two baseline schemes, we demonstrate the effectiveness of proposed algorithms in a realistic model.