arXiv subjects

Chujie Wang

Publications and source records attributed to Chujie Wang.

4 recordsLinked to original sources

arXiv2026

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained manipulation, however, benefits from anticipating how wrist-local interactions may evolve under the global task context. To address this limitation, we present World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling. Given current multi-view observations and a task instruction, W2-VLA contextualizes a set of latent modeling tokens as a compact interface between the vision-language model and the wrist predictor. Conditioned on this interface and the observed wrist history, the predictor forecasts future wrist latents, which are transformed into future-aware context for action prediction. In addition, we introduce W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence. These annotations provide auxiliary supervision that shapes the task-conditioned latent interface. Experiments on LIBERO, RoboTwin 2.0, and real-world manipulation tasks demonstrate improved fine-grained and contact-sensitive manipulation across both single-arm and bimanual settings, while maintaining action-generation rates above 80 Hz.

cs.RO↗

arXiv2025

OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection

Open-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although existing methods are pretrained on large vision-language datasets, their inference is still limited to fixed category names, creating a gap between multimodal training and unimodal inference. Previous work has shown that improving textual representation can significantly enhance OVOD performance, indicating that the textual space is still underexplored. To this end, we propose OVOD-Agent, which transforms passive category matching into proactive visual reasoning and self-evolving detection. Inspired by the Chain-of-Thought (CoT) paradigm, OVOD-Agent extends the textual optimization process into an interpretable Visual-CoT with explicit actions. OVOD's lightweight nature makes LLM-based management unsuitable; instead, we model visual context transitions as a Weakly Markovian Decision Process (w-MDP) over eight state spaces, which naturally represents the agent's state, memory, and interaction dynamics. A Bandit module generates exploration signals under limited supervision, helping the agent focus on uncertain regions and adapt its detection policy. We further integrate Markov transition matrices with Bandit trajectories for self-supervised Reward Model (RM) optimization, forming a closed loop from Bandit exploration to RM learning. Experiments on COCO and LVIS show that OVOD-Agent provides consistent improvements across OVOD backbones, particularly on rare categories, confirming the effectiveness of the proposed framework.

cs.AI↗

arXiv2025

VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis

The current remote sensing image analysis task is increasingly evolving from traditional object recognition to complex intelligence reasoning, which places higher requirements on the model's reasoning ability and the flexibility of tool invocation. To this end, we propose a new multimodal agent framework, Vision-Interleaved Chain-of-Thought Framework (VICoT), which implements explicit multi-round reasoning by dynamically incorporating visual tools into the chain of thought. Through a stack-based reasoning structure and a modular MCP-compatible tool suite, VICoT enables LLMs to efficiently perform multi-round, interleaved vision-language reasoning tasks with strong generalization and flexibility.We also propose the Reasoning Stack distillation method to migrate complex Agent behaviors to small, lightweight models, which ensures the reasoning capability while significantly reducing complexity. Experiments on multiple remote sensing benchmarks demonstrate that VICoT significantly outperforms existing SOTA frameworks in reasoning transparency, execution efficiency, and generation quality.

cs.AI↗

arXiv2018

Deep Learning-based Intelligent Dual Connectivity for Mobility Management in Dense Network

Ultra-dense network deployment has been proposed as a key technique for achieving capacity goals in the fifth-generation (5G) mobile communication system. However, the deployment of smaller cells inevitably leads to more frequent handovers, thus making mobility management more challenging and reducing the capacity gains offered by the dense network deployment. In order to fully reap the gains for mobile users in such a network environment, we propose an intelligent dual connectivity mechanism for mobility management through deep learning-based mobility prediction. We first use LSTM (Long Short Term Memory) algorithm, one of deep learning algorithms, to learn every user equipment's (UE's) mobility pattern from its historical trajectories and predict its movement trends in the future. Based on the corresponding prediction results, the network will judge whether a handover is required for the UE. For the handover case, a dual connection will be established for the related UE. Thus, the UE can get the radio signal from two base stations in the handover process. Simulation results verify that the proposed intelligent dual connectivity mechanism can significantly improve the quality of service of mobile users in the handover process while guaranteeing the network energy efficiency.

cs.NI↗