arXiv subjects

Guanhua Zhu

Publications and source records attributed to Guanhua Zhu.

5 recordsLinked to original sources

arXiv2026

From Uncertainty to Action: Learning to Steer LLM Agents

Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to correct an agent, but whether it can guide these decisions remains unclear. We steer agent trajectories separately at every non-terminal step with each of four mechanisms and run each continuation to completion. The resulting stepwise outcome table (SOT) holds about 82,000 counterfactual continuations of 1,864 trajectories from three benchmarks and two agents. It shows that uncertainty can identify failing trajectories, but that no single signal reliably locates the step at which steering helps. We therefore propose VoS (Value of Steering), a trajectory-level monitor, offline or online, that learns from SOT the value of steering at each step and decides where to steer by it. A harm-budgeted trigger decides whether to steer, limiting the fraction of successful trajectories that VoS disturbs. VoS improves on unmodified execution in all 12 settings of benchmark, agent, and offline or online use, by 7.8 points on average, and outperforms the strongest of five existing uncertainty-triggered methods in 11, by 2.9 points on average. Ablations show that training on measured outcomes and a tight harm budget are both essential.

cs.AI↗

arXiv2026

SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration

Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short video sequences and suffer from significant performance degradation when processing long-horizon free-viewpoint video (LFVV). Motivated by bit allocation theory, we analyze dynamic-anchor-based volumetric video representation within a rate-distortion optimization framework and propose \textbf{SoLAR}, which is the first error-resilient streamable FVV framework that maintains stable reconstruction quality on long sequences without requiring group-of-pictures partitioning. We propose the Anchor Activation Dynamics (AAD), which enables dynamic anchors to model non-rigid transformations by dynamically activating informative anchors and suppressing redundant ones. Furthermore, we introduce Latent Discrepancy Aware Recalibration (LaDAR), which is a mechanism to identify discrepancies between latent representations and recalibrate the correspondences encoded in the network, effectively mitigating error propagation in LFVV without compromising real-time performance or storage compactness. Extensive experiments demonstrate that \textbf{SoLAR} achieves state-of-the-art reconstruction performance while maintaining minimum storage overhead, which provides a new direction for LFVV reconstruction and advances the practical deployment of immersive systems. Demo free-viewpoint videos are provided in the supplementary material.

cs.CV↗

arXiv2024

Utilizing Autoregressive Networks for Full Lifecycle Data Generation of Rolling Bearings for RUL Prediction

The prediction of rolling bearing lifespan is of significant importance in industrial production. However, the scarcity of high-quality, full lifecycle data has been a major constraint in achieving precise predictions. To address this challenge, this paper introduces the CVGAN model, a novel framework capable of generating one-dimensional vibration signals in both horizontal and vertical directions, conditioned on historical vibration data and remaining useful life. In addition, we propose an autoregressive generation method that can iteratively utilize previously generated vibration information to guide the generation of current signals. The effectiveness of the CVGAN model is validated through experiments conducted on the PHM 2012 dataset. Our findings demonstrate that the CVGAN model, in terms of both MMD and FID metrics, outperforms many advanced methods in both autoregressive and non-autoregressive generation modes. Notably, training using the full lifecycle data generated by the CVGAN model significantly improves the performance of the predictive model. This result highlights the effectiveness of the data generated by CVGans in enhancing the predictive power of these models.

cs.LG↗

arXiv2023

Utilizing Multiple Inputs Autoregressive Models for Bearing Remaining Useful Life Prediction

Accurate prediction of the Remaining Useful Life (RUL) of rolling bearings is crucial in industrial production, yet existing models often struggle with limited generalization capabilities due to their inability to fully process all vibration signal patterns. We introduce a novel multi-input autoregressive model to address this challenge in RUL prediction for bearings. Our approach uniquely integrates vibration signals with previously predicted Health Indicator (HI) values, employing feature fusion to output current window HI values. Through autoregressive iterations, the model attains a global receptive field, effectively overcoming the limitations in generalization. Furthermore, we innovatively incorporate a segmentation method and multiple training iterations to mitigate error accumulation in autoregressive models. Empirical evaluation on the PMH2012 dataset demonstrates that our model, compared to other backbone networks using similar autoregressive approaches, achieves significantly lower Root Mean Square Error (RMSE) and Score. Notably, it outperforms traditional autoregressive models that use label values as inputs and non-autoregressive networks, showing superior generalization abilities with a marked lead in RMSE and Score metrics.

cs.LG↗

arXiv2023

Utilizing VQ-VAE for End-to-End Health Indicator Generation in Predicting Rolling Bearing RUL

The prediction of the remaining useful life (RUL) of rolling bearings is a pivotal issue in industrial production. A crucial approach to tackling this issue involves transforming vibration signals into health indicators (HI) to aid model training. This paper presents an end-to-end HI construction method, vector quantised variational autoencoder (VQ-VAE), which addresses the need for dimensionality reduction of latent variables in traditional unsupervised learning methods such as autoencoder. Moreover, concerning the inadequacy of traditional statistical metrics in reflecting curve fluctuations accurately, two novel statistical metrics, mean absolute distance (MAD) and mean variance (MV), are introduced. These metrics accurately depict the fluctuation patterns in the curves, thereby indicating the model's accuracy in discerning similar features. On the PMH2012 dataset, methods employing VQ-VAE for label construction achieved lower values for MAD and MV. Furthermore, the ASTCN prediction model trained with VQ-VAE labels demonstrated commendable performance, attaining the lowest values for MAD and MV.

cs.LG↗