arXiv subjects

Mingyu Guo

Publications and source records attributed to Mingyu Guo.

At least 37 records · Page 2Linked to original sources

arXiv2026

Delay-Aware Large-Small Model Collaboration over LEO Satellite Networks

In this paper, we introduce a delay-aware largesmall model collaboration scheme for low Earth orbit (LEO) satellite networks, which can balance the computational load among satellites and the communication load across inter-satellite links. Specifically, computational resource constrained remote sensing satellites are responsible for data collection and local processing using small models, while collaborating with computing satellites that provide large model processing. To minimize the service delay, we formulate a joint optimization problem for offloading decision and routing strategy design, which is transformed into a decentralized partially observable Markov decision process. To solve the problem, we develop a multi-agent reinforcement learning (MARL)-based algorithm with offline policy training and online bisection search. The offline trained policy determines routing strategies, while online bisection search iteratively adjusts the offloading decisions. Simulation results demonstrate that the proposed scheme can reduce the service delay by up to 31.85% compared with the benchmarks.

cs.DC↗

arXiv2026

The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open environments, agents are highly susceptible to stealthy contextual corruption, such as targeted prompt injections. We reveal a critical structural vulnerability in current multi-agent systems: response-level aggregation collapses when corrupted agents form a local majority. Because voting aggregates fully-formed conclusions, it is blind to flawed intermediate logic. To overcome this systematic limitation, we propose the Token-Level Round-Robin (RR) Collaboration, where agents sequentially interleave generation within a shared auto-regressive context. We formalize this process as a discrete-time dynamical system, proving that token-level interleaving transitions aggregation from a brittle counting of final votes (a linear sum) to a dynamic, interwoven chain of logic (a non-linear operator product). Through this theoretical lens, we prove that the honest model's restorative pull can overpower adversarial corruptions, even when corrupted agents form a majority. We conduct an exhaustive empirical evaluation across diverse reasoning benchmarks and demonstrate that while MAJ collapses when corrupted agents reach a majority, RR maintains robust accuracy well beyond this critical threshold.

cs.CL↗

arXiv2026

Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

Generative advertising in large language model (LLM) responses requires optimizing sponsorship configurations under two strict constraints: the strategic behavior of advertisers and the high cost of stochastic generations. To address this, we propose the Incentive-Aware Multi-Fidelity Mechanism (IAMFM), a unified framework coupling Vickrey-Clarke-Groves (VCG) incentives with Multi-Fidelity Optimization to maximize expected social welfare. We compare two algorithmic instantiations (elimination-based and model-based), revealing their budget-dependent performance trade-offs. Crucially, to make VCG computationally feasible, we introduce Active Counterfactual Optimization, a "warm-start" approach that reuses optimization data for efficient payment calculation. We provide formal guarantees for approximate strategy-proofness and individual rationality, establishing a general approach for incentive-aligned, budget-constrained generative processes. Experiments demonstrate that IAMFM outperforms single-fidelity baselines across diverse budgets.

cs.GT↗

arXiv2026

Experimental Powder X-ray Diffraction Crystal Structure Determination with RealPXRD-Solver

Determining crystal structures from experimental powder X-ray diffraction data remains challenging because peak overlap, preferred orientation, and impurity phases obscure atomic arrangements. We present RealPXRD-Solver, a generative model trained on 6,250,238 theoretical structures with experiment-mimicking augmentations and a universal encoder of d-spacing--intensity fingerprints, enabling both lattice-conditioned and lattice-free inference. RealPXRD-Solver reaches a 98.3% Top-20 match rate on a 10,000-structure theoretical benchmark and achieves Top-1/Top-20 accuracies of 77.9%/91.9% on CNRS and 78.8%/92.9% on RRUFF experimental datasets, and it solved 39 previously unreported Powder Diffraction File entries.

cond-mat.mtrl-sci↗

arXiv2026

Building Large-Scale Drone Defenses from Small-Team Strategies

Defending against large adversarial drone swarms requires coordination methods that scale effectively beyond conventional multi-agent optimisation. In this paper, we propose to scale strategies proven effective in small defender teams by integrating them as modular components of larger forces using our proposed framework. A dynamic programming (DP) decomposition assembles these components into large teams in polynomial time, enabling efficient construction of scalable defenses without exhaustive evaluation. Because a unit that is strong in isolation may not remain strong when combined, we sample across multiple small-team candidates. Our framework iterates between evaluating large-team outcomes and refining the pool of modular components, allowing convergence on increasingly effective strategies. Experiments demonstrate that this partitioning approach scales to substantially larger scenarios while preserving effectiveness and revealing cooperative behaviours that direct optimisation cannot reliably discover.

cs.MA↗

arXiv2026

Evolving LLM-Derived Control Policies for Residential EV Charging and Vehicle-to-Grid Energy Optimization

This research presents a novel application of Evolutionary Computation to the domain of residential electric vehicle (EV) energy management. While reinforcement learning (RL) achieves high performance in vehicle-to-grid (V2G) optimization, it typically produces opaque "black-box" neural networks that are difficult for consumers and regulators to audit. Addressing this interpretability gap, we propose a program search framework that leverages Large Language Models (LLMs) as intelligent mutation operators within an iterative prompt-evaluation-repair loop. Utilizing the high-fidelity EV2Gym simulation environment as a fitness function, the system undergoes successive refinement cycles to synthesize executable Python policies that balance profit maximization, user comfort, and physical safety constraints. We benchmark four prompting strategies: Imitation, Reasoning, Hybrid and Runtime, evaluating their ability to discover adaptive control logic. Results demonstrate that the Hybrid strategy produces concise, human-readable heuristics that achieve 118% of the baseline profit, effectively discovering complex behaviors like anticipatory arbitrage and hysteresis without explicit programming. This work establishes LLM-driven Evolutionary Computation as a practical approach for generating EV charging control policies that are transparent, inspectable, and suitable for real residential deployment.

cs.NE↗

arXiv2026

MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving

Trajectory planning is a core task in autonomous driving, requiring the prediction of safe and comfortable paths across diverse scenarios. Integrating Multi-modal Large Language Models (MLLMs) with Reinforcement Learning (RL) has shown promise in addressing "long-tail" scenarios. However, existing methods are constrained to single-turn reasoning, limiting their ability to handle complex tasks requiring iterative refinement. To overcome this limitation, we present MTDrive, a multi-turn framework that enables MLLMs to iteratively refine trajectories based on environmental feedback. MTDrive introduces Multi-Turn Group Relative Policy Optimization (mtGRPO), which mitigates reward sparsity by computing relative advantages across turns. We further construct an interactive trajectory understanding dataset from closed-loop simulation to support multi-turn training. Experiments on the NAVSIM benchmark demonstrate superior performance compared to existing methods, validating the effectiveness of our multi-turn reasoning paradigm. Additionally, we implement system-level optimizations to reduce data transfer overhead caused by high-resolution images and multi-turn sequences, achieving 2.5x training throughput. Our data, models, and code will be made available soon.

cs.RO↗

arXiv2026

A Graph Neural Network for the Era of Large Atomistic Models

Foundation models, or large atomistic models (LAMs), aim to universally represent the ground-state potential energy surface (PES) of atomistic systems as defined by density functional theory (DFT). The scaling law is pivotal in the development of large models, suggesting that their generalizability in downstream tasks consistently improves with increased model size, expanded training datasets, and larger computational budgets. In this study, we present DPA3, a multi-layer graph neural network founded on line graph series (LiGS), designed explicitly for the era of LAMs. We demonstrate that the generalization error of the DPA3 model adheres to the scaling law. The scalability in the number of model parameters is attained by stacking additional layers within DPA3. Additionally, the model employs a dataset encoding mechanism that decouples the scaling of training data size from the model size within its multi-task training framework. When trained as problem-oriented potential energy models, the DPA3 model exhibits superior accuracy in the majority of benchmark cases, encompassing systems with diverse features, including molecules, bulk materials, surface and cluster catalysts, two-dimensional materials, and battery materials. When trained as a LAM on the OpenLAM-v1 dataset, the DPA-3.1-3M model exhibits lowest overall zero-shot generalization error across 12 downstream tasks spanning a diverse array of research domains. This performance suggests superior accuracy as an out-of-the-box potential model, requiring minimal fine-tuning data for downstream scientific applications.

physics.comp-ph↗

arXiv2026

Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers

Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assumption and propose \textbf{Calibration Attention (CalAttn)}, a \emph{representation-aware} calibration module for vision transformers that couples instance-wise temperature scaling to transformer token geometry under a proper scoring objective. CalAttn predicts a sample-specific temperature from the \texttt{[CLS]} token and backpropagates calibration gradients into the backbone, thereby reshaping the uncertainty structure of the representation rather than post-hoc adjusting confidence. This yields \emph{token-conditioned uncertainty modulation} with negligible overhead ($<0.1\%$ additional parameters). Across multiple datasets with ViT/DeiT/Swin backbones, CalAttn consistently improves calibration while preserving accuracy, achieving relative ECE reductions of $3.7\%$ to $77.7\%$ over strong baselines across diverse training objectives. Our results indicate that treating calibration as a representation-level problem is a practical and effective direction for trustworthy uncertainty estimation in transformers. Code: [https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-](https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-)

cs.CV↗

arXiv2026

Multi-Task Fine-Tuning Enables Robust Out-of-Distribution Generalization in Atomistic Models

Accurate de novo molecular and materials design requires structure-property models that generalize beyond known regimes. Although pretrained atomistic models achieve strong in-distribution accuracy after fine-tuning, their reliability under out-of-distribution (OOD) conditions remains unclear. We identify a critical failure mode in downstream adaptation: standard fine-tuning induces representation collapse, erasing pretrained chemical and structural priors and severely degrading OOD performance. To address this limitation, we propose multi-task fine-tuning (MFT), which jointly optimizes downstream property prediction with a physically grounded force-field objective inherited from pretraining. This approach preserves essential chemical priors while enabling task-specific adaptation. Across molecular and materials benchmarks, MFT consistently improves OOD generalization, approaching the theoretical limit set by in-distribution accuracy, while outperforming standard fine-tuning, training from scratch, and state-of-the-art task-specific models. These results establish safe adaptation as a central requirement for large atomistic models and position MFT as a practical and data-efficient pathway toward robust molecular and materials discovery.

physics.comp-ph↗

arXiv2025

On the Edge of Core (Non-)Emptiness: An Automated Reasoning Approach to Approval-Based Multi-Winner Voting

Core stability is a natural and well-studied notion for group fairness in multi-winner voting, where the task is to select a committee from a pool of candidates. We study the setting where voters either approve or disapprove of each candidate; here, it remains a major open problem whether a core-stable committee always exists. In this work, we develop an approach based on mixed-integer linear programming for deciding whether and when core-stable committees are guaranteed to exist. In contrast to SAT-based approaches popular in computational social choice, our method can produce proofs for a specific number of candidates independent of the number of voters. In addition to these computational gains, our program lends itself to a novel duality-based reformulation of the core stability problem, from which we obtain new existence results in special cases. Further, we use our framework to reveal previously unknown relationships between core stability and other desirable properties, such as notions of priceability.

cs.GT↗

arXiv2025

Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit texture generation by providing a semantic anchor. Recent advances have integrated semantic priors from pretrained visual encoders to further enhance LDMs, yet they still denoise semantic and VAE-encoded texture synchronously, neglecting such ordering. Observing these, we propose Semantic-First Diffusion (SFD), a latent diffusion paradigm that explicitly prioritizes semantic formation. SFD first constructs composite latents by combining a compact semantic latent, which is extracted from a pretrained visual encoder via a dedicated Semantic VAE, with the texture latent. The core of SFD is to denoise the semantic and texture latents asynchronously using separate noise schedules: semantics precede textures by a temporal offset, providing clearer high-level guidance for texture refinement and enabling natural coarse-to-fine generation. On ImageNet 256x256 with guidance, SFD achieves FID 1.06 (LightningDiT-XL) and FID 1.04 (1.0B LightningDiT-XXL), while achieving up to 100x faster convergence than the original DiT. SFD also improves existing methods like ReDi and VA-VAE, demonstrating the effectiveness of asynchronous, semantics-led modeling. Project page and code: https://yuemingpan.github.io/SFD.github.io/.

cs.CV↗

arXiv2025

Co-Evolutionary Defence of Active Directory Attack Graphs via GNN-Approximated Dynamic Programming

Modern enterprise networks increasingly rely on Active Directory (AD) for identity and access management. However, this centralization exposes a single point of failure, allowing adversaries to compromise high-value assets. Existing AD defense approaches often assume static attacker behavior, but real-world adversaries adapt dynamically, rendering such methods brittle. To address this, we model attacker-defender interactions in AD as a Stackelberg game between an adaptive attacker and a proactive defender. We propose a co-evolutionary defense framework that combines Graph Neural Network Approximated Dynamic Programming (GNNDP) to model attacker strategies, with Evolutionary Diversity Optimization (EDO) to generate resilient blocking strategies. To ensure scalability, we introduce a Fixed-Parameter Tractable (FPT) graph reduction method that reduces complexity while preserving strategic structure. Our framework jointly refines attacker and defender policies to improve generalization and prevent premature convergence. Experiments on synthetic AD graphs show near-optimal results (within 0.1 percent of optimality on r500) and improved performance on larger graphs (r1000 and r2000), demonstrating the framework's scalability and effectiveness.

cs.CR↗

arXiv2025

LAMBench: A Benchmark for Large Atomistic Models

Large Atomistic Models (LAMs) have undergone remarkable progress recently, emerging as universal or fundamental representations of the potential energy surface defined by the first-principles calculations of atomistic systems. However, our understanding of the extent to which these models achieve true universality, as well as their comparative performance across different models, remains limited. This gap is largely due to the lack of comprehensive benchmarks capable of evaluating the effectiveness of LAMs as approximations to the universal potential energy surface. In this study, we introduce LAMBench, a benchmarking system designed to evaluate LAMs in terms of their generalizability, adaptability, and applicability. These attributes are crucial for deploying LAMs as ready-to-use tools across a diverse array of scientific discovery contexts. We benchmark ten state-of-the-art LAMs released prior to August 1, 2025, using LAMBench. Our findings reveal a significant gap between the current LAMs and the ideal universal potential energy surface. They also highlight the need for incorporating cross-domain training data, supporting multi-fidelity modeling, and ensuring the models' conservativeness and differentiability. As a dynamic and extensible platform, LAMBench is intended to continuously evolve, thereby facilitating the development of robust and generalizable LAMs capable of significantly advancing scientific research. The LAMBench code is open-sourced at https://github.com/deepmodeling/lambench, and an interactive leaderboard is available at https://www.aissquare.com/openlam?tab=Benchmark.

physics.comp-ph↗

arXiv2025

LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition

Vision Transformers (ViTs) have revolutionized large-scale visual modeling, yet remain underexplored in face recognition (FR) where CNNs still dominate. We identify a critical bottleneck: CNN-inspired training paradigms fail to unlock ViT's potential, leading to suboptimal performance and convergence instability.To address this challenge, we propose LVFace, a ViT-based FR model that integrates Progressive Cluster Optimization (PCO) to achieve superior results. Specifically, PCO sequentially applies negative class sub-sampling (NCS) for robust and fast feature alignment from random initialization, feature expectation penalties for centroid stabilization, performing cluster boundary refinement through full-batch training without NCS constraints. LVFace establishes a new state-of-the-art face recognition baseline, surpassing leading approaches such as UniFace and TopoFR across multiple benchmarks. Extensive experiments demonstrate that LVFace delivers consistent performance gains, while exhibiting scalability to large-scale datasets and compatibility with mainstream VLMs and LLMs. Notably, LVFace secured 1st place in the ICCV 2021 Masked Face Recognition (MFR)-Ongoing Challenge (March 2025), proving its efficacy in real-world scenarios. Project is available at https://github.com/bytedance/LVFace.

cs.CV↗

arXiv2025

ContentV: Efficient Training of Video Generation Models with Limited Compute

Recent advances in video generation demand increasingly efficient training recipes to mitigate escalating computational costs. In this report, we present ContentV, an 8B-parameter text-to-video model that achieves state-of-the-art performance (85.14 on VBench) after training on 256 x 64GB Neural Processing Units (NPUs) for merely four weeks. ContentV generates diverse, high-quality videos across multiple resolutions and durations from text prompts, enabled by three key innovations: (1) A minimalist architecture that maximizes reuse of pre-trained image generation models for video generation; (2) A systematic multi-stage training strategy leveraging flow matching for enhanced efficiency; and (3) A cost-effective reinforcement learning with human feedback framework that improves generation quality without requiring additional human annotations. All the code and models are available at: https://contentv.github.io.

cs.CV↗

arXiv2025

Towards Self-Improvement of Diffusion Models via Group Preference Optimization

Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and the labor-intensive process of collecting and annotating high-quality data. In this work, we demonstrate that preference pairs with marginal differences can degrade DPO performance. Since DPO relies exclusively on relative ranking while disregarding the absolute difference of pairs, it may misclassify losing samples as wins, or vice versa. We empirically show that extending the DPO from pairwise to groupwise and incorporating reward standardization for reweighting leads to performance gains without explicit data selection. Furthermore, we propose Group Preference Optimization (GPO), an effective self-improvement method that enhances performance by leveraging the model's own capabilities without requiring external data. Extensive experiments demonstrate that GPO is effective across various diffusion models and tasks. Specifically, combining with widely used computer vision models, such as YOLO and OCR, the GPO improves the accurate counting and text rendering capabilities of the Stable Diffusion 3.5 Medium by 20 percentage points. Notably, as a plug-and-play method, no extra overhead is introduced during inference.

cs.CV↗

arXiv2025

Adaptive Wizard for Removing Cross-Tier Misconfigurations in Active Directory

Security vulnerabilities in Windows Active Directory (AD) systems are typically modeled using an attack graph and hardening AD systems involves an iterative workflow: security teams propose an edge to remove, and IT operations teams manually review these fixes before implementing the removal. As verification requires significant manual effort, we formulate an Adaptive Path Removal Problem to minimize the number of steps in this iterative removal process. In our model, a wizard proposes an attack path in each step and presents it as a set of multiple-choice options to the IT admin. The IT admin then selects one edge from the proposed set to remove. This process continues until the target $t$ is disconnected from source $s$ or the number of proposed paths reaches $B$. The model aims to optimize the human effort by minimizing the expected number of interactions between the IT admin and the security wizard. We first prove that the problem is $\mathcal{\#P}$-hard. We then propose a set of solutions including an exact algorithm, an approximate algorithm, and several scalable heuristics. Our best heuristic, called DPR, can operate effectively on larger-scale graphs compared to the exact algorithm and consistently outperforms the approximate algorithm across all graphs. We verify the effectiveness of our algorithms on several synthetic AD graphs and an AD attack graph collected from a real organization.

cs.AI↗