Yuqing He

Yixuan Yang, Yuqing He, Song Li

The Muon optimizer has recently demonstrated remarkable empirical success in training large language models. However, the theoretical understanding of its mechanisms remains limited. Current convergence guarantees for Muon rely heavily on smoothness assumptions, leaving its non-smooth convergence behavior largely unexplored. In this work, we take a step toward bridging this gap by investigating Spectral Descent (SD), a simplified variant of Muon, together with its truncated counterpart, Truncated Spectral Descent (TSD). Under convexity, Lipschitz continuity, and sharpness conditions, we establish global linear convergence for both SD and TSD in non-smooth convex formulations. We also study regularized variants equipped with decoupled weight decay and derive sublinear convergence guarantees through their connection with Frank-Wolfe methods. Finally, we apply our theoretical framework to robust low-rank matrix recovery under mixed sparse and dense noise regimes and provide rigorous recovery guarantees. Numerical experiments support the theoretical findings and demonstrate the effectiveness of Muon-type methods for non-smooth optimization.

Yuqing He, Yousef Heider, Bernd Markert

This manuscript presents a practical method for incorporating trained Neural Networks (NNs) into the Finite Element (FE) framework using a user material (UMAT) subroutine. The work exemplifies crystal plasticity, a complex inelastic non-linear path-dependent material response, with a wide range of applications in ABAQUS UMAT. However, this approach can be extended to other material behaviors and FE tools. The use of a UMAT subroutine serves two main purposes: (1) it predicts and updates the stress or other mechanical properties of interest directly from the strain history; (2) it computes the Jacobian matrix either through backpropagation or numerical differentiation, which plays an essential role in the solution convergence. By implementing NNs in a UMAT subroutine, a trained machine learning model can be employed as a data-driven constitutive law within the FEM framework, preserving multiscale information that conventional constitutive laws often neglect or average. The versatility of this method makes it a powerful tool for integrating machine learning into mechanical simulation. While this approach is expected to provide higher accuracy in reproducing realistic material behavior, the reliability of the solution process and the convergence conditions must be paid special attention. While the theory of the model is explained in [Heider et al. 2020], exemplary source code is also made available for interested readers [https://doi.org/10.25835/6n5uu50y]

Bo Chen, Decai Li, Yuqing He et al.

Technologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do not consider the mining of relationships, which include spatial relationships between human and scene elements as well as causal relationships in temporal action sequences. In fact, human beings are good at using spatial and causal relational reasoning mechanism to predict the actions of others. Inspired by this idea, we proposed a Spatial and Causal Relationship based Graph Reasoning Network (SCR-Graph), which can be used to predict human actions by modeling the action-scene relationship, and causal relationship between actions, in spatial and temporal dimensions respectively. Here, in spatial dimension, a hierarchical graph attention module is designed by iteratively aggregating the features of different kinds of scene elements in different level. In temporal dimension, we designed a knowledge graph based causal reasoning module and map the past actions to temporal causal features through Diffusion RNN. Finally, we integrated the causality features into the heterogeneous graph in the form of shadow node, and introduced a self-attention module to determine the time when the knowledge graph information should be activated. Extensive experimental results on the VIRAT datasets demonstrate the favorable performance of the proposed framework.

Peng Yin, Rangaprasad Arun Srivatsan, Yin Chen et al.

Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions and changing viewpoints. It depends on a brute-force, time-consuming sequential matching method. We propose MRS-VPR, a multi-resolution, sampling-based place recognition method, which can significantly improve the matching efficiency and accuracy in sequential matching. The novelty of this method lies in the coarse-to-fine searching pipeline and a particle filter-based global sampling scheme, that can balance the matching efficiency and accuracy in the long-term navigation task. Moreover, our model works much better than SeqSLAM when the testing sequence has a much smaller scale than the reference sequence. Our experiments demonstrate that the proposed method is efficient in locating short temporary trajectories within long-term reference ones without losing accuracy compared to SeqSLAM.

Peng Yin, Lingyun Xu, Xueqian Li et al.

Visual Place Recognition (VPR) is an important component in both computer vision and robotics applications, thanks to its ability to determine whether a place has been visited and where specifically. A major challenge in VPR is to handle changes of environmental conditions including weather, season and illumination. Most VPR methods try to improve the place recognition performance by ignoring the environmental factors, leading to decreased accuracy decreases when environmental conditions change significantly, such as day versus night. To this end, we propose an end-to-end conditional visual place recognition method. Specifically, we introduce the multi-domain feature learning method (MDFL) to capture multiple attribute-descriptions for a given place, and then use a feature detaching module to separate the environmental condition-related features from those that are not. The only label required within this feature learning pipeline is the environmental condition. Evaluation of the proposed method is conducted on the multi-season \textit{NORDLAND} dataset, and the multi-weather \textit{GTAV} dataset. Experimental results show that our method improves the feature robustness against variant environmental conditions.

Peng Yin, Yuqing He, Lingyun Xu et al.

Loop Closure Detection (LCD) is the essential module in the simultaneous localization and mapping (SLAM) task. In the current appearance-based SLAM methods, the visual inputs are usually affected by illumination, appearance and viewpoints changes. Comparing to the visual inputs, with the active property, light detection and ranging (LiDAR) based point-cloud inputs are invariant to the illumination and appearance changes. In this paper, we extract 3D voxel maps and 2D top view maps from LiDAR inputs, and the former could capture the local geometry into a simplified 3D voxel format, the later could capture the local road structure into a 2D image format. However, the most challenge problem is to obtain efficient features from 3D and 2D maps to against the viewpoints difference. In this paper, we proposed a synchronous adversarial feature learning method for the LCD task, which could learn the higher level abstract features from different domains without any label data. To the best of our knowledge, this work is the first to extract multi-domain adversarial features for the LCD task in real time. To investigate the performance, we test the proposed method on the KITTI odometry dataset. The extensive experiments results show that, the proposed method could largely improve LCD accuracy even under huge viewpoints differences.

Peng Yin, Yuqing He, Na Liu et al.

Loop closure detection (LCD) is the key module in appearance based simultaneously localization and mapping (SLAM). However, in the real life, the appearance of visual inputs are usually affected by the illumination changes and texture changes under different weather conditions. Traditional methods in LCD usually rely on handcraft features, however, such methods are unable to capture the common descriptions under different weather conditions, such as rainy, foggy and sunny. Furthermore, traditional handcraft features could not capture the highly level understanding for the local scenes. In this paper, we proposed a novel condition directed multi-domain adversarial learning method, where we use the weather condition as the direction for feature inference. Based on the generative adversarial networks (GANs) and a classification networks, the proposed method could extract the high-level weather-invariant features directly from the raw data. The only labels required here are the weather condition of each visual input. Experiments are conducted in the GTAV game simulator, which could generated lifelike outdoor scenes under different weather conditions. The performance of LCD results shows that our method outperforms the state-of-arts significantly.