Author name cluster

Yirong Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

UrbanNav: Learning Language-Guided Embodied Urban Navigation from Web-Scale Human Trajectories

Yanghong Mei
Yirong Yang
Longteng Guo
Qunbo Wang
Ming-Ming Yu
Xingjian He
Wenjun Wu
Jing Liu

Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial references, diverse landmarks, and dynamic street scenes. Current visual navigation methods are typically limited to simulated or off-street environments, and often rely on precise goal formats, such as specific coordinates or images. This limits their effectiveness for autonomous agents like last-mile delivery robots navigating unfamiliar cities. To address these limitations, we introduce UrbanNav, a scalable framework that trains embodied agents to follow free-form language instructions in diverse urban settings. Leveraging web-scale city walking videos, we develop an scalable annotation pipeline that aligns human navigation trajectories with language instructions grounded in real-world landmarks. UrbanNav encompasses over 1,500 hours of navigation data and 3 million instruction-trajectory-landmark triplets, capturing a wide range of urban scenarios. Our model learns robust navigation policies to tackle complex urban scenarios, demonstrating superior spatial reasoning, robustness to noisy instructions, and generalization to unseen urban settings. Experimental results show that UrbanNav significantly outperforms existing methods, highlighting the potential of large-scale web video data to enable language-guided, real-world urban navigation for embodied agents.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

MingMing Yu
Fei Zhu
Wenzhuo Liu
Yirong Yang
Qunbo Wang
Wenjun Wu
Jing Liu

Embodied agents are expected to perform object navigation in dynamic, open-world environments. However, existing approaches typically rely on static trajectories and a fixed set of object categories during training, overlooking the real-world requirement for continual adaptation to evolving scenarios. To facilitate related studies, we introduce the continual object navigation benchmark, which requires agents to acquire navigation skills for new object categories while avoiding catastrophic forgetting of previously learned knowledge. To tackle this challenge, we propose C-Nav, a continual visual navigation framework that integrates two key innovations: (1) A dual-path anti-forgetting mechanism, which comprises feature distillation that aligns multi-modal inputs into a consistent representation space to ensure representation consistency, and feature replay that retains temporal features within the action decoder to ensure policy consistency. (2) An adaptive sampling strategy that selects diverse and informative experiences, thereby reducing redundancy and minimizing memory overhead. Extensive experiments across multiple model architectures demonstrate that C-Nav consistently outperforms existing approaches, achieving superior performance even compared to baselines with full trajectory retention, while significantly lowering memory requirements. The code will be publicly available at \url{https: //bigtree765. github. io/C-Nav-project}.

PDF Details

YNIMG Journal 2020 Journal Article

Manganese-enhanced MRI reveals changes within brain anxiety and aversion circuitry in rats with chronic neuropathic pain- and anxiety-like behaviors

Sabrina L. McIlwrath
Marena A. Montera
Katherine M. Gott
Yirong Yang
Colin M. Wilson
Reed Selwyn
Karin N. Westlund

Chronic pain often predicts the onset of psychological distress. Symptoms including anxiety and depression after pain chronification reportedly are caused by brain remodeling/recruitment of the limbic and reward/aversion circuitries. Pain is the primary precipitating factor that has caused opioid overprescribing and continued overuse of opioids leading to the current opioid epidemic. Yet experimental pain therapies often fail in clinical trials. Better understanding of underlying pathologies contributing to pain chronification is needed to address these chronic pain related issues. In the present study, a chronic neuropathic pain model persisting 10 weeks was studied. The model develops both anxiety- and pain-related behavioral measures to mimic clinical pain. The manganese-enhanced magnetic resonance imaging (MEMRI) utilized improved MRI signal contrast in brain regions with higher neuronal activity in the rodent chronic constriction trigeminal nerve injury (CCI-ION) model. T1-weighted MEMRI signal intensity was increased compared to controls in supraspinal regions of the anxiety and aversion circuitry, including anterior cingulate gyrus (ACC), amygdala, habenula, caudate, ventrolateral and dorsomedial periaqueductal gray (PAG). Despite continuing mechanical hypersensitivity, MEMRI T1 signal intensity as the neuronal activity measure, was not significantly different in thalamus and decreased in somatosensory cortex (S1BF) of CCI-ION rats compared to naïve controls. This is consistent with decreased fMRI BOLD signal intensity in thalamus and cortex of patients with longstanding trigeminal neuropathic pain reportedly associated with gray matter volume decrease in these regions. Significant increase in MEMRI T2 signal intensity in thalamus of CCI-ION animals was indication of tissue water content, cell dysfunction and/or reactive astrogliosis. Decreased T2 signal intensity in S1BF cortex of rats with CCI-ION was similar to findings of reduced T2 signals in clinical patients with chronic orofacial pain indicating prolonged astrocyte activation. These findings support use of MEMRI and chronic rodent models for preclinical studies and therapeutic trials to reveal brain sites activated only after neuropathic pain has persisted in timeframes relevant to clinical pain and to observe treatment effects not possible in short-term models which do not have evidence of anxiety-like behaviors. Potential improvement is predicted in the success rate of preclinical drug trials in future studies with this model.

Details DOI