arXiv subjects

Ming Gao

Publications and source records attributed to Ming Gao.

At least 19 recordsLinked to original sources

arXiv2026

MatrixFSDP: communication-free matrix optimizers under ZeRO-3 parameter sharding

Matrix optimizers such as Muon are attractive for large-scale training because they can improve convergence and token efficiency over coordinate-wise optimizers. Muon does this by orthogonalizing momentum-smoothed matrix updates with Newton-Schulz, producing spectrum-balanced updates that require the complete 2D matrix as input. This exposes a systems mismatch: FSDP/ZeRO-3 saves memory by making the optimizer see shards, not whole matrices. Existing systems therefore either reconstruct matrices at every optimizer step, paying weight-sized communication after backward, or make the update local by using ZeRO-1 owner placement with full parameters resident. MatrixFSDP takes a third path: it changes where ZeRO-3 shards live, not the optimizer being computed. For each 2D weight, one data-parallel rank owns the whole matrix and the other ranks hold empty shards; non-matrix tensors are packed into tail owners and stay on AdamW. The ordinary backward reduction then lands the full Muon input on the owner, so Newton-Schulz runs locally with no optimizer-step matrix collective. Forward and backward still materialize and reshard parameters; the runtime challenge is to make that uneven layout efficient and correct. MatrixFSDP does so with MatrixShard metadata, a balance-aware owner planner, deterministic owner-segment P2P collectives, owner-buffer pinning, and owner-shard checkpoint resharding. The resulting update matches full-matrix Muon while preserving ZeRO-3-scale memory: on 64 A100s, MatrixFSDP reduces optimizer-step latency over stock FSDP2-Muon by 4.2x on one node and 54.6x on eight nodes, reaches up to 2.15x end-to-end speedup, and runs model sizes where ZeRO-1 owner placement exceeds an 80 GB GPU.

cs.DC↗

arXiv2026

Phase-Time Array Enabled Multistatic Sensing with Multi-Level Fusion for UAV Localization

Multistatic collaborative sensing eliminates self-interference, achieves spatial diversity gains, and enables wide-range seamless integrated sensing and communication (ISAC). However, conventional data fusion methods suffer from severe error amplification in geometry-sensitive regions. In addition, the conventional analog phased array solution introduces large beam sweeping overhead, whereas the fully digital arrays request high hardware cost. We propose a multistatic sensing framework enabled by a phase-time array (PTA). The rainbow beamforming maps spatial directions to orthogonal frequency division multiplexing (OFDM) subcarriers, achieving wide-angle coverage with a single radio frequency (RF) chain. We develop two parameter-level schemes-a geometry-aware analytical estimator (GDOP-WLS) and a lightweight multilayer perceptron (PF-MLP)-to mitigate the effects of topological singularities. Additionally, an end-to-end signal-level convolutional neural network (SF-CNN) directly estimates target coordinates from raw signals, avoiding cascaded estimation errors. The results demonstrate that the parameter-level schemes ensure robust convergence under adverse geometric conditions with minimal computational latency. Conversely, the signal-level scheme achieves sub-meter precision but requires an increased computational load. Consequently, the proposed framework establishes a scalable solution for collaborative surveillance of unmanned aerial vehicles (UAVs), providing flexible trade-offs among hardware complexity, latency, and accuracy.

eess.SP↗

arXiv2026

Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents

Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy Optimization (GRPO) being a widely used training algorithm. However, GRPO-style algorithms still face several challenges in multi-hop search settings. First, correct intermediate steps are often penalized when the final answer is wrong. Second, training is highly unstable, often causing degradation of natural language ability or even catastrophic training collapse. Our analysis attributes these issues to coarse-grained advantage assignment and an imbalance between positive and negative advantages. To address these problems, we propose CalibAdv, an advantage calibration method specifically designed for search agents that enables more accurate and more stable modeling of penalties and rewards. Specifically, CalibAdv leverages the correctness of intermediate steps to downscale excessive negative advantages at a fine-grained level. It then further rebalances positive and negative advantages to improve training stability. Importantly, CalibAdv adopts a lightweight design that calibrates advantages from standard rollout signals, making it simple and easy to deploy. Extensive experiments across three models and seven benchmarks demonstrate that CalibAdv improves both model performance and training stability. Our code is available at https://github.com/wujwyi/CalibAdv.

cs.CL↗

arXiv2026

GECAM discovery of a peculiar magnetar X-ray burst (MXB 221120) from SGR J1935+2154 associated with a fast radio burst

Fast radio bursts (FRBs) are enigmatic cosmic transients of millisecond duration observed in the radio band. The identification of FRB-associated magnetar X-ray bursts (MXBs) from galactic magnetar SGR J1935+2154 suggests that at least a fraction of FRBs can be produced from magnetar activity. However, the sample size of FRB-associated MXBs is still very small. Here we report a bright and peculiar FRB-associated MXB from SGR J1935+2154 detected by GECAM on November 20, 2022, dubbed MXB 221120. We find that both temporal and spectral properties of MXB 221120 exhibit distinctive features. Its light curve could be generally described by a single FRED function with superposition of several narrow pulses. Interestingly, we identify a possible QPO feature with center frequency of ~18 Hz in this MXB. The time-integrated spectrum is best fitted by a blackbody model with temperature (kT ) of 18.6 keV, rendering it the first thermal spectrum FRB-associated MXB from SGR J1935+2154. Compared to other MXBs with single emission episode, MXB 221120 has longer duration and higher blackbody temperature, making it an outlier in the burst sample. These results indicate that MXB 221120 may be produced by a special mechanism with extreme physical conditions.

astro-ph.HE↗

arXiv2026

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning

Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally informative, overlooking the crucial role of sample quality. To address this, we propose Plausible Negative Samples (PNS), a method that synthesizes high-quality negative samples exhibiting expected format and structural coherence while ultimately yielding incorrect answers. PNS trains a dedicated model via reverse reinforcement learning (RL) guided by a composite reward combining format compliance, accuracy inversion, reward model assessment, and chain-of-thought evaluation, generating responses nearly indistinguishable from correct solutions. We further validate PNS as a plug-and-play data source for preference optimization across three backbone models on seven mathematical reasoning benchmarks. Results demonstrate that PNS consistently outperforms other negative sample synthesis methods, achieving an average improvement of 2.03% over RL-trained models.

cs.LG↗

arXiv2025

TReFT: Taming Rectified Flow Models For One-Step Image Translation

Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time applications. Although the recent adversarial training paradigm, CycleGAN-Turbo, works in pretrained diffusion models for one-step image translation, we find that directly applying it to RF models leads to severe convergence issues. In this paper, we analyze these challenges and propose TReFT, a novel method to Tame Rectified Flow models for one-step image Translation. Unlike previous works, TReFT directly uses the velocity predicted by pretrained DiT or UNet as output-a simple yet effective design that tackles the convergence issues under adversarial training with one-step inference. This design is mainly motivated by a novel observation that, near the end of the denoising process, the velocity predicted by pretrained RF models converges to the vector from origin to the final clean image, a property we further justify through theoretical analysis. When applying TReFT to large pretrained RF models such as SD3.5 and FLUX, we introduce memory-efficient latent cycle-consistency and identity losses during training, as well as lightweight architectural simplifications for faster inference. Pretrained RF models finetuned with TReFT achieve performance comparable to sota methods across multiple image translation datasets while enabling real-time inference.

cs.CV↗

arXiv2025

A Predictive and Sampled-Data Barrier Method for Safe and Efficient Quadrotor Control

This paper proposes a cascaded control framework for quadrotor trajectory tracking with formal safety guarantees. First, we design a controller consisting of an outer-loop position model predictive control (MPC) and an inner-loop nonlinear attitude control, enabling decoupling of position safety and yaw orientation. Second, since quadrotor safety constraints often involve high relative degree, we adopt high order control barrier functions (HOCBFs) to guarantee safety. To employ HOCBFs in the MPC formulation that has formal guarantees, we extend HOCBFs to sampled-data HOCBF (SdHOCBFs) by introducing compensation terms, ensuring safety over the entire sampling interval. We show that embedding SdHOCBFs as control-affine constraints into the MPC formulation guarantees both safety and optimality while preserving convexity for real-time implementations. Finally, comprehensive simulations are conducted to demonstrate the safety guarantee and high efficiency of the proposed method compared to existing methods.

eess.SY↗

arXiv2025

Optimality and computational barriers in variable selection under dependence

We study the optimal sample complexity of variable selection in linear regression under general design covariance, and show that subset selection is optimal while under standard complexity assumptions, efficient algorithms for this problem do not exist. Specifically, we analyze the variable selection problem and provide the optimal sample complexity with exact dependence on the problem parameters for both known and unknown sparsity settings. Moreover, we establish a sample complexity lower bound for any efficient estimator, highlighting a gap between the statistical efficiency achievable by combinatorial algorithms (such as subset selection) compared to efficient algorithms (such as those based on convex programming). The proofs rely on a finite-sample analysis of an information criterion estimator, which may be of independent interest. Our results emphasize the optimal position of subset selection, the critical role played by restricted eigenvalues, and characterize the statistical-computational trade-off in high-dimensional variable selection.

math.ST↗

arXiv2025

Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.

cs.LG↗

arXiv2025

Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation

Session-based recommendation (SBR) is mainly based on anonymous user interaction sequences to recommend the items that the next user is most likely to click. Currently, the most popular and high-performing SBR methods primarily leverage graph neural networks (GNNs), which model session sequences as graph-structured data to effectively capture user intent. However, most GNNs-based SBR methods primarily focus on modeling the ID sequence information of session sequences, while neglecting the rich semantic information embedded within them. This limitation significantly hampers model's ability to accurately infer users' true intention. To address above challenge, this paper proposes a novel SBR approach called Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation (LLM-DMsRec). The method utilizes a pre-trained GNN model to select the top-k items as candidate item sets and designs prompts along with a large language model (LLM) to infer multi-semantic intents from these candidate items. Specifically, we propose an alignment mechanism that effectively integrates the semantic intent inferred by the LLM with the structural intent captured by GNNs. Extensive experiments conducted on the Beauty and ML-1M datasets demonstrate that the proposed method can be seamlessly integrated into GNNs framework, significantly enhancing its recommendation performance.

cs.IR↗

arXiv2025

Optimal structure learning and conditional independence testing

We establish a fundamental connection between optimal structure learning and optimal conditional independence testing by showing that the minimax optimal rate for structure learning problems is determined by the minimax rate for conditional independence testing in these problems. This is accomplished by establishing a general reduction between these two problems in the case of poly-forests, and demonstrated by deriving optimal rates for several examples, including Bernoulli, Gaussian and nonparametric models. Furthermore, we show that the optimal algorithm in these settings is a suitable modification of the PC algorithm. This theoretical finding provides a unified framework for analyzing the statistical complexity of structure learning through the lens of minimax testing.

math.ST↗

arXiv2025

A Novel Solver for QUBO Problems: Performance Analysis and Comparative Study with State-of-the-Art Algorithms

Quadratic Unconstrained Binary Optimization (QUBO) provides a versatile framework for representing NP-hard combinatorial problems, yet existing solvers often face trade-offs among speed, accuracy, and scalability. In this work, we introduce a quantum-inspired solver (QIS) that unites branch-and-bound pruning, continuous gradient-descent refinement, and quantum-inspired heuristics within a fully adaptive control architecture. We benchmark QIS3 against eight state-of-the-art solvers, including genetic algorithms, coherent Ising machines, simulated bifurcation, parallel tempering, simulated annealing, our prior QIS2 version, D-Wave's simulated-annealing (Neal), and Gurobi on three canonical QUBO problem classes: Max-Cut, NAE-3SAT, and Sherrington-Kirkpatrick spin glass problems. Under a uniform runtime budget, QIS3 attains the best solution on nearly all instances, achieving optimality in 94% of max-cut instances. These results establish QIS3 as a robust, high-performance solver that bridges classical exact strategies and quantum-inspired heuristics for scalable QUBO optimization.

quant-ph↗

arXiv2025

The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition

Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing systems achieved significant improvements over the baseline: the top AVSD model achieved a Diarization Error Rate (DER) of 8.09%, improving by 7.43%; the top AVSR system achieved a Character Error Rate (CER) of 9.48%, improving by 10.62%; and the best AVDR system achieved a concatenated minimum-permutation Character Error Rate (cpCER) of 11.56%, improving by 72.49%.

cs.SD↗

arXiv2025

CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection

Cross-layer feature pyramid networks (CFPNs) have achieved notable progress in multi-scale feature fusion and boundary detail preservation for salient object detection. However, traditional CFPNs still suffer from two core limitations: (1) a computational bottleneck caused by complex feature weighting operations, and (2) degraded boundary accuracy due to feature blurring in the upsampling process. To address these challenges, we propose CFMD, a novel cross-layer feature pyramid network that introduces two key innovations. First, we design a context-aware feature aggregation module (CFLMA), which incorporates the state-of-the-art Mamba architecture to construct a dynamic weight distribution mechanism. This module adaptively adjusts feature importance based on image context, significantly improving both representation efficiency and generalization. Second, we introduce an adaptive dynamic upsampling unit (CFLMD) that preserves spatial details during resolution recovery. By adjusting the upsampling range dynamically and initializing with a bilinear strategy, the module effectively reduces feature overlap and maintains fine-grained boundary structures. Extensive experiments on three standard benchmarks using three mainstream backbone networks demonstrate that CFMD achieves substantial improvements in pixel-level accuracy and boundary segmentation quality, especially in complex scenes. The results validate the effectiveness of CFMD in jointly enhancing computational efficiency and segmentation performance, highlighting its strong potential in salient object detection tasks.

cs.CV↗

arXiv2025

Circuit Diagram Retrieval Based on Hierarchical Circuit Graph Representation

In the domain of analog circuit design, the retrieval of circuit diagrams has drawn a great interest, primarily due to its vital role in the consultation of legacy designs and the detection of design plagiarism. Existing image retrieval techniques are adept at handling natural images, which converts images into feature vectors and retrieval similar images according to the closeness of these vectors. Nonetheless, these approaches exhibit limitations when applied to the more specialized and intricate domain of circuit diagrams. This paper presents a novel approach to circuit diagram retrieval by employing a graph representation of circuit diagrams, effectively reformulating the retrieval task as a graph retrieval problem. The proposed methodology consists of two principal components: a circuit diagram recognition algorithm designed to extract the circuit components and topological structure of the circuit using proposed GAM-YOLO model and a 2-step connected domain filtering algorithm, and a hierarchical retrieval strategy based on graph similarity and different graph representation methods for analog circuits. Our methodology pioneers the utilization of graph representation in the retrieval of circuit diagrams, incorporating topological features that are commonly overlooked by standard image retrieval methods. The results of our experiments substantiate the efficacy of our approach in retrieving circuit diagrams across of different types.

cs.AR↗

arXiv2025

Machine Learning Relationships between Nanoporous Structures and Electrochemical Performance in MOF Supercapacitors

The development of supercapacitors is impeded by the unclear relationships between nanoporous electrode structures and electrochemical performance, primarily due to challenges in decoupling the complex interdependencies of various structural descriptors. While machine learning (ML) techniques offer a promising solution, their application is hindered by the lack of large, unified databases. Herein, we use constant-potential molecular simulation to construct a unified supercapacitor database with hundreds of metal-organic framework (MOF) electrodes. Leveraging this database, well-trained decision-tree-based ML models achieve fast, accurate, and interpretable predictions of capacitance and charging rate, experimentally validated by a representative case. SHAP analyses reveal that specific surface area (SSA) governs gravimetric capacitance while pore size effects are minimal, attributed to the strong dependence of electrode-ion coordination on SSA rather than pore size. SSA and porosity, respectively, dominate volumetric capacitance in 1D-pore and 3D-pore MOFs, pinnacling the indispensable effects of pore dimensionality. Meanwhile, porosity is found to be the most decisive factor in the charging rate for both 1D-pore and 3D-pore MOFs. Especially for 3D-pore MOFs, an exponential increase with porosity is observed in both ionic conductance and in-pore ion diffusion coefficient, ascribed to loosened ion packing. These findings provide profound insights for the design of high-performance supercapacitor electrodes.

cond-mat.mtrl-sci↗

arXiv2024

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization

The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations. When a general-purpose LLM serves as the RAG generator, it often suffers from inadequate response informativeness, response robustness, and citation quality. Past approaches to tackle these limitations, either by incorporating additional steps beyond generating responses or optimizing the generator through supervised fine-tuning (SFT), still failed to align with the RAG requirement thoroughly. Consequently, optimizing the RAG generator from multiple preference perspectives while maintaining its end-to-end LLM form remains a challenge. To bridge this gap, we propose Multiple Perspective Preference Alignment for Retrieval-Augmented Generation (PA-RAG), a method for optimizing the generator of RAG systems to align with RAG requirements comprehensively. Specifically, we construct high-quality instruction fine-tuning data and multi-perspective preference data by sampling varied quality responses from the generator across different prompt documents quality scenarios. Subsequently, we optimize the generator using SFT and Direct Preference Optimization (DPO). Extensive experiments conducted on four question-answer datasets across three LLMs demonstrate that PA-RAG can significantly enhance the performance of RAG generators. Our code and datasets are available at https://github.com/wujwyi/PA-RAG.

cs.CL↗

arXiv2024

DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model

Efficient and accurate extraction of electrical parameters from circuit datasheets and design documents is critical for accelerating circuit design in Electronic Design Automation (EDA). Traditional workflows often rely on engineers manually searching and extracting these parameters, which is time-consuming, and prone to human error. To address these challenges, we introduce DocEDA, an automated system that leverages advanced computer vision techniques and Large Language Models (LLMs) to extract electrical parameters seamlessly from documents. The layout analysis model specifically designed for datasheet is proposed to classify documents into circuit-related parts. Utilizing the inherent Chain-of-Thought reasoning capabilities of LLMs, DocEDA automates the extraction of electronic component parameters from documents. For circuit diagrams parsing, an improved GAM-YOLO model is hybrid with topology identification to transform diagrams into circuit netlists. Then, a space mapping enhanced optimization framework is evoked for optimization the layout in the document. Experimental evaluations demonstrate that DocEDA significantly enhances the efficiency of processing circuit design documents and the accuracy of electrical parameter extraction. It exhibits adaptability to various circuit design scenarios and document formats, offering a novel solution for EDA with the potential to transform traditional methodologies.

cs.AR↗