arXiv subjects

Ming Hao

Publications and source records attributed to Ming Hao.

6 recordsLinked to original sources

arXiv2026

ConvMem: Convolutional Memory for Long-Context Reasoning

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead to overfitting on specific datasets. To overcome these limitations, we propose ConvMem, a training-free, highly parallelizable framework that reformulates long-context reasoning as a hierarchical convolution. Inspired by CNNs, ConvMem treats an LLM prompted with a specific query as a convolutional kernel. This kernel summarizes text segments hierarchically, shortening the reasoning path from a linear chain into a logarithmic tree. Specifically, ConvMem integrates \textit{Configurable Strides} and \textit{Skip Connections} to ensure robust evidence capture and propagation, while employing \textit{Multi-Kernel Convolution} to decompose complex queries into disentangled semantic channels. This design not only mitigates error accumulation but also enables massive parallelization across both text segments and reasoning threads. Experiments on RULER-HotpotQA and RULER-2WikiMultiHopQA demonstrate that ConvMem outperforms training-free baselines and avoids the risk of overfitting to parametric priors often observed in RL-trained models on out-of-distribution tasks.

cs.AI↗

arXiv2026

ActionNex: A Virtual Outage Manager for Cloud Computing

Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven decisions under partial observability. We present \textbf{ActionNex}, a production-grade agentic system that supports end-to-end outage assistance, including real-time updates, knowledge distillation, and role- and stage-conditioned next-best action recommendations. ActionNex ingests multimodal operational signals (e.g., outage content, telemetry, and human communications) and compresses them into critical events that represent meaningful state transitions. It couples this perception layer with a hierarchical memory subsystem: long-term Key-Condition-Action (KCA) knowledge distilled from playbooks and historical executions, episodic memory of prior outages, and working memory of the live context. A reasoning agent aligns current critical events to preconditions, retrieves relevant memories, and generates actionable recommendations; executed human actions serve as an implicit feedback signal to enable continual self-evolution in a human-agent hybrid system. We evaluate ActionNex on eight real Azure outages (8M tokens, 4,000 critical events) using two complementary ground-truth action sets, achieving 71.4\% precision and 52.8-54.8\% recall. The system has been piloted in production and has received positive early feedback.

cs.AI↗

arXiv2023

ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging

The conventional recipe for Automatic Speech Recognition (ASR) models is to 1) train multiple checkpoints on a training set while relying on a validation set to prevent overfitting using early stopping and 2) average several last checkpoints or that of the lowest validation losses to obtain the final model. In this paper, we rethink and update the early stopping and checkpoint averaging from the perspective of the bias-variance tradeoff. Theoretically, the bias and variance represent the fitness and variability of a model and the tradeoff of them determines the overall generalization error. But, it's impractical to evaluate them precisely. As an alternative, we take the training loss and validation loss as proxies of bias and variance and guide the early stopping and checkpoint averaging using their tradeoff, namely an Approximated Bias-Variance Tradeoff (ApproBiVT). When evaluating with advanced ASR models, our recipe provides 2.5%-3.7% and 3.1%-4.6% CER reduction on the AISHELL-1 and AISHELL-2, respectively.

cs.CL↗

arXiv2023

Exploiting Neighborhood Structural Features for Change Detection

In this letter, a novel method for change detection is proposed using neighborhood structure correlation. Because structure features are insensitive to the intensity differences between bi-temporal images, we perform the correlation analysis on structure features rather than intensity information. First, we extract the structure feature maps by using multi-orientated gradient information. Then, the structure feature maps are used to obtain the Neighborhood Structural Correlation Image (NSCI), which can represent the context structure information. In addition, we introduce a measure named matching error which can be used to improve neighborhood information. Subsequently, a change detection model based on the random forest is constructed. The NSCI feature and matching error are used as the model inputs for training and prediction. Finally, the decision tree voting is used to produce the change detection result. To evaluate the performance of the proposed method, it was compared with three state-of-the-art change detection methods. The experimental results on two datasets demonstrated the effectiveness and robustness of the proposed method.

cs.CV↗

arXiv2022

Positional uncertainty and quality assurance of digital elevation change detection (DECD)

Studies on rapid change detection of large area urgently need to be extended from 2D image to digital elevation model (DEM) due to the challenge of changes caused by disasters. This research investigates positional uncertainty of digital elevation change detection (DECD) caused by different degrees of DEM complexity and DEM misregistration. Unfortunately, using three-sigma rule (3σR) for DECD is disturbed by accuracy of parameter estimation, which is affected by the outliers (i.e., varied DEM) from DEM differencing samples. Hence, to reduce the aforementioned uncertainty of DECD, we propose a new strategy of quality assurance, adaptively censored three-sigma rule (AC3σR), in which with the samples censored, outliers of global DEM differencing samples outside the standard deviations of the mean calculated by moment estimation are iteratively removed. Compared with the 3σR and censored three-sigma rule (C3σR) that is similar to AC3σR but without iteration for both simulation and real-world data experiments, the proposed global AC3σR method always exhibits the highest accuracies of DECD in terms of both the overall accuracies 0.99967, 0.98740 and kappa coefficients 0.99598, 0.81803 respectively, and the strongest robustness with a large convergence interval [0, 0.30010] under the simulated maximum registration error and most complex terrain complexity conditions.

physics.geo-ph↗

arXiv2019

Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly. However, the point cloud is sparse, unstructured, and unordered, which cannot be recognized accurately by a traditional convolutional neural network (CNN) nor a recurrent neural network (RNN). Fortunately, a graph convolutional neural network (Graph CNN) can process sparse and unordered data. Hence, we propose a linked dynamic graph CNN (LDGCNN) to classify and segment point cloud directly in this paper. We remove the transformation network, link hierarchical features from dynamic graphs, freeze feature extractor, and retrain the classifier to increase the performance of LDGCNN. We explain our network using theoretical analysis and visualization. Through experiments, we show that the proposed LDGCNN achieves state-of-art performance on two standard datasets: ModelNet40 and ShapeNet.

cs.CV↗