arXiv subjects

Tao Luo

Publications and source records attributed to Tao Luo.

At least 55 records · Page 3Linked to original sources

arXiv2026

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models

Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $π_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation mechanism - the vector field dynamics - presents a critical yet unexplored security vulnerability, particularly backdoor vulnerabilities. Existing backdoor attacks designed for autoregressive discretization VLAs cannot be directly applied to this new continuous dynamics. We introduce FlowHijack, the first backdoor attack framework to systematically target the underlying vector-field dynamics of flow-matching VLAs. Our method combines a novel $τ$-conditioned injection strategy, which manipulates the initial phase of the action generation, with a dynamics mimicry regularizer. Experiments demonstrate that FlowHijack achieves high attack success rates using stealthy, context-aware triggers where prior works failed. Crucially, it preserves benign task performance and, by enforcing kinematic similarity, generates malicious actions that are behaviorally indistinguishable from normal actions. Our findings reveal a significant vulnerability in continuous embodied models, highlighting the urgent need for defenses targeting the model's internal generative dynamics.

cs.CV↗

arXiv2026

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

cs.AI↗

arXiv2026

ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation

Large Language Model (LLM)-based agents show promise for e-commerce conversational shopping, yet existing implementations lack the interaction depth and contextual breadth required for complex product research. Meanwhile, the Deep Research paradigm, despite advancing information synthesis in web search, suffers from domain gaps when transferred to e-commerce. We propose ProductResearch, a multi-agent framework that synthesizes high-fidelity, long-horizon tool-use trajectories for training robust e-commerce shopping agents. The framework employs a User Agent to infer nuanced shopping intents from behavioral histories, and a Supervisor Agent that orchestrates iterative collaboration with a Research Agent to generate synthetic trajectories culminating in comprehensive, insightful product research reports. These trajectories are rigorously filtered and distilled through a reflective internalization process that consolidates multi-agent supervisory interactions into coherent single-role training examples, enabling effective fine-tuning of LLM agents for complex shopping inquiries. Extensive experiments show that a compact MoE model fine-tuned on our synthetic data achieves substantial improvements over its base model in response comprehensiveness, research depth, and user-perceived utility, approaching the performance of frontier proprietary deep research systems and establishing multi-agent synthetic trajectory training as an effective and scalable paradigm for enhancing LLM-based shopping assistance.

cs.AI↗

arXiv2026

Reply to "Threefold error in the reported zero-field cooled magnetic moment of single crystal $La_2SmNi_2O_7$ (arXiv: 2602.23240)"

We respond to the critique by Aleksandr V. Korolev and Evgeny F. Talantsev on the superconducting phase fraction ($f$) calculations in Li et al. Nature 649, 871-878 (2026). First, the weak upturn in the low-temperature tail of our data has been confirmed to originate from the background, and the paramagnetic Meissner effect is absent in our case; thus, field-cooled (FC) data can be used for superconducting phase fraction calculations. Second, demagnetization effect must be calculated based on the actual measured moment as a function of $f$, which has been well-established and routinely employed in the superconductivity community. In contrast, Korolev and Talantsev treated the demagnetization field as a constant; thus, their calculation underestimates $f$ by a factor of $(1-Nχ_{meas})(1-N)$. This factor is close to 1/3, given $N$ = 0.849, $χ_{meas}$ = -1.313 in our study, which explains the origin of their deviated result (nearly three times smaller than our results). Third, our sample is a homogeneous high-quality bulk single crystal, evidenced by various techniques, making the existence of multiple discrete superconducting regions highly unlikely. We conclude that the superconducting phase fraction calculations reported in Li et al. Nature 649, 871-878 (2026) are not invalidated by the analyses presented in Korolev et al. arXiv: 2602.23240 (2026).

cond-mat.supr-con↗

arXiv2026

ASSESS: A Semantic and Structural Evaluation Framework for Statement Similarity

Despite significant strides in statement autoformalization, a critical gap remains in the development of automated evaluation metrics capable of assessing formal translation quality. Existing metrics often fail to balance semantic and structural information: string-based methods neglect semantics, whereas proof-based approaches offer no graded similarity when proofs fail. To address these issues, we introduce ASSESS (A Semantic and Structural Evaluation Framework for Statement Similarity), which captures syntactic structure by transforming formal statements into operator trees and computes a real-valued similarity score using our novel TransTED (Transformation Tree Edit Distance) Similarity metric by incorporating semantic transformations. For rigorous validation, we present EPLA (Evaluating Provability and Likeness for Autoformalization), a benchmark comprising 1,247 expert-annotated formal statement pairs derived from miniF2F and ProofNet, distinctively labeled for both semantic provability and structural likeness. Experiments on the EPLA benchmark demonstrate that TransTED Similarity surpasses existing methods, achieving state-of-the-art accuracy and Kappa score. The benchmark dataset, code, and detailed experimental results are available at https://github.com/XiaoyangLiu-sjtu/ASSESS.

cs.LG↗

arXiv2026

Convergence of high-index saddle dynamics for degenerate saddle points on critical manifolds

The high-index saddle dynamics (HiSD) method provides a powerful framework for finding saddle points and constructing solution landscapes. While originally derived for nondegenerate critical points, HiSD has demonstrated empirical success in degenerate cases, where the Hessian matrix exhibits zero eigenvalues. However, the mathematical and numerical analysis of HiSD for degenerate saddle points remains unexplored. In this paper, utilizing Morse-Bott functions, we present a rigorous analysis of HiSD for computing degenerate saddle points on a critical manifold. We prove the local convergence of the continuous HiSD and establish the linear convergence rate of the discrete HiSD algorithm. Furthermore, we provide a theoretical explanation for the gradient alignment tendency, revealing that the gradient direction asymptotically aligns with a specific Hessian eigenvector. Our analysis also elucidates the flexibility in selecting the index for HiSD in the context of degenerate saddle points. We validate our analytical results through numerical experiments on neural-network loss landscapes and demonstrate that momentum-accelerated variants of HiSD achieve rapid convergence to degenerate saddle points.

math.NA↗

arXiv2026

SSBE-PINN: A Sobolev Boundary Scheme Boosting Stability and Accuracy in Elliptic/Parabolic PDE Learning

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs), yet they often fail to achieve accurate convergence in the H1 norm, especially in the presence of boundary approximation errors. In this work, we propose a novel method called Sobolev-Stable Boundary Enforcement (SSBE), which redefines the boundary loss using Sobolev norms to incorporate boundary regularity directly into the training process. We provide rigorous theoretical analysis demonstrating that SSBE ensures bounded H1 error via a stability guarantee and derive generalization bounds that characterize its robustness under finite-sample regimes. Extensive numerical experiments on linear and nonlinear PDEs, including Poisson, heat, and elliptic problems, show that SSBE consistently outperforms standard PINNs in terms of both relative L2 and H1 errors, even in high-dimensional settings. The proposed approach offers a principled and practical solution for improving gradient fidelity and overall solution accuracy in neural network based PDE solvers.

math.NA↗

arXiv2025

An Anti-Interference AFDM System: Interference Impacts Analyses and Parameter Optimization

This paper proposes an anti-interference affine frequency division multiplexing (AFDM) system to ensure reliability and resource efficiency under malicious high-power interference originating from adversarial devices in high-mobility scenarios. Closed-form expressions of interferences in the discrete affine Fourier transform (DAFT) domain are derived by utilizing the stationary phase principle and the Affine Fourier transform convolution theorem, which indicates that interference impacts can be classified into stationary and non-stationary categories. On this basis, we reveal the analytical relationship between packet throughput and the paramerters of spread spectrum and error correction coding in our proposed anti-interference system, which enables the design of a parameter optimization algorithm that maximizes packet throughput. For reception, by jointly utilizing the autocorrelation function of spreading sequence and the cyclic-shift property of AFDM input-output relation, we design a linear-complexity correlation-based DAFT domain detector (CDD) capable of achieving full diversity gain, which performs correlation-based equalization to avoid matrix inversion. Numerical results validate the accuracy of the derived closed-form expressions and verify that the proposed anti-interference AFDM system could achieve high packet throughput under interference in high-mobility scenarios.

cs.IT↗

arXiv2025

MMIF-AMIN: Adaptive Loss-Driven Multi-Scale Invertible Dense Network for Multimodal Medical Image Fusion

Multimodal medical image fusion (MMIF) aims to integrate images from different modalities to produce a comprehensive image that enhances medical diagnosis by accurately depicting organ structures, tissue textures, and metabolic information. Capturing both the unique and complementary information across multiple modalities simultaneously is a key research challenge in MMIF. To address this challenge, this paper proposes a novel image fusion method, MMIF-AMIN, which features a new architecture that can effectively extract these unique and complementary features. Specifically, an Invertible Dense Network (IDN) is employed for lossless feature extraction from individual modalities. To extract complementary information between modalities, a Multi-scale Complementary Feature Extraction Module (MCFEM) is designed, which incorporates a hybrid attention mechanism, convolutional layers of varying sizes, and Transformers. An adaptive loss function is introduced to guide model learning, addressing the limitations of traditional manually-designed loss functions and enhancing the depth of data mining. Extensive experiments demonstrate that MMIF-AMIN outperforms nine state-of-the-art MMIF methods, delivering superior results in both quantitative and qualitative analyses. Ablation experiments confirm the effectiveness of each component of the proposed method. Additionally, extending MMIF-AMIN to other image fusion tasks also achieves promising performance.

cs.CV↗

arXiv2025

Quantum Chromatic Number of Subgraphs of Orthogonality Graphs and the Distance-2 Hamming Graph

The determination of the quantum chromatic number of graphs has attracted considerable attention recently. However, there are few families of graphs whose quantum chromatic numbers are determined. A notable exception is the family of orthogonality graphs, whose quantum chromatic numbers are fully determined. In this paper, we extend these results by determining the exact quantum chromatic number of several subgraphs of the orthogonality graphs. Using the technique of combinatorial designs, we also determine the quantum chromatic number of the distance-2 Hamming graph, whose edges consist of binary vectors of Hamming distance 2, for infinitely many length.

math.CO↗

arXiv2025

Embedding principle of homogeneous neural network for classification problem

In this paper, we study the Karush-Kuhn-Tucker (KKT) points of the associated maximum-margin problem in homogeneous neural networks, including fully-connected and convolutional neural networks. In particular, We investigates the relationship between such KKT points across networks of different widths generated. We introduce and formalize the \textbf{KKT point embedding principle}, establishing that KKT points of a homogeneous network's max-margin problem ($P_Φ$) can be embedded into the KKT points of a larger network's problem ($P_{\tildeΦ}$) via specific linear isometric transformations. We rigorously prove this principle holds for neuron splitting in fully-connected networks and channel splitting in convolutional neural networks. Furthermore, we connect this static embedding to the dynamics of gradient flow training with smooth losses. We demonstrate that trajectories initiated from appropriately mapped points remain mapped throughout training and that the resulting $ω$-limit sets of directions are correspondingly mapped, thereby preserving the alignment with KKT directions dynamically when directional convergence occurs. We conduct several experiments to justify that trajectories are preserved. Our findings offer insights into the effects of network width, parameter redundancy, and the structural connections between solutions found via optimization in homogeneous networks of varying sizes.

cs.LG↗

arXiv2025

Convergence Guarantees for Gradient-Based Training of Neural PDE Solvers: From Linear to Nonlinear PDEs

We present a unified convergence theory for gradient-based training of neural network methods for partial differential equations (PDEs), covering both physics-informed neural networks (PINNs) and the Deep Ritz method. For linear PDEs, we extend the neural tangent kernel (NTK) framework for PINNs to establish global convergence guarantees for a broad class of linear operators. For nonlinear PDEs, we prove convergence to critical points via the Łojasiewicz inequality under the random feature model, eliminating the need for strong over-parameterization and encompassing both gradient flow and implicit gradient descent dynamics. Our results further reveal that the random feature model exhibits an implicit regularization effect, preventing parameter divergence to infinity. Theoretical findings are corroborated by numerical experiments, providing new insights into the training dynamics and robustness of neural network PDE solvers.

math.NA↗

arXiv2025

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical evidence showing improved reasoning capabilities under small initialization scales in language models, we employ the gradient flow analytical framework established in [Zhou et al. NeurIPS 2022] to systematically investigate linearized Transformer training dynamics. Our theoretical analysis dissects the dynamics of attention modules into two distinct stages. In the first stage, asymmetric weight perturbations from random initialization sustain non-degenerate gradient dynamics in parameter matrices, facilitating systematic escape from small initialization regimes. Subsequently, these matrices undergo condensation, progressively aligning toward the target orientation. In the second stage, the previously static key-query matrices actively participate in training, driving the normalized matrices toward asymptotic rank collapse. This two-stage framework generalizes classical directional convergence results.

cs.LG↗

arXiv2025

ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data

Autoformalization, the automatic translation of mathematical content from natural language into machine-verifiable formal languages, has seen significant progress driven by advances in large language models (LLMs). Nonetheless, a primary barrier to further improvements is the limited availability of parallel corpora that map informal mathematical text to its formal counterpart. To address this limitation, we propose ATLAS (Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data), a novel data generation framework designed to produce large-scale, high-quality parallel corpora of theorem statements. Distinct from prior approaches, ATLAS begins with a concept repository, accelerates the improvement of the student model through expert iteration combined with knowledge distillation, and introduces two novel augmentation strategies that exploit the structural characteristics of formal languages. Running the proposed ATLAS framework for 10 iterations, we construct an undergraduate-level dataset of 117k theorem statements and develop the ATLAS Translator by fine-tuning Llama3.1-8B-Instruct with LoRA. This model establishes a new state of the art, demonstrating statistically significant improvements over both the Herald Translator and the Kimina-Autoformalizer across all benchmarks (p<0.05, two-sided t-test). Furthermore, we demonstrate that the full-parameter fine-tuning of a stronger base model on the ATLAS dataset leads to superior performance. The datasets, model, and code are available at https://github.com/XiaoyangLiu-sjtu/ATLAS.

cs.CL↗

arXiv2025

Semi-Discrete in Time Method for Time-Dependent Equations by Random Neural Basis

Neural network-based solvers for partial differential equations (PDEs) have attracted considerable attention, yet they often face challenges in accuracy and computational efficiency. In this work, we focus on time-dependent PDEs and observe that coupling space and time in a single network can increase the difficulty of approximation. To address this, we propose a semi-discrete in time method (SDTM) which leverages classical numerical time integrators and random neural basis (RNB). Additional adaptive operations are introduced to enhance the network's ability to capture features across scales to ensure uniform approximation accuracy for multi-scale PDEs. Numerical experiments demonstrate the framework's effectiveness and confirm the convergence of the temporal integrator as well as the network's approximation performance.

math.NA↗

arXiv2025

Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding

Spiking neural networks (SNNs) promise high energy efficiency, particularly with time-to-first-spike (TTFS) encoding, which maximizes sparsity by emitting at most one spike per neuron. However, such energy advantage is often unrealized because inference requires evaluating a temporal decay function and subsequent multiplication with the synaptic weights. This paper challenges this costly approach by repurposing a physical hardware `bug', namely, the natural signal decay in optoelectronic devices, as the core computation of TTFS. We fabricated a custom indium oxide optoelectronic synapse, showing how its natural physical decay directly implements the required temporal function. By treating the device's analog output as the fused product of the synaptic weight and temporal decay, optoelectronic synaptic TTFS (named Otters) eliminates these expensive digital operations. To use the Otters paradigm in complex architectures like the transformer, which are challenging to train directly due to the sparsity issue, we introduce a novel quantized neural network-to-SNN conversion algorithm. This complete hardware-software co-design enables our model to achieve state-of-the-art accuracy across seven GLUE benchmark datasets and demonstrates a 1.77$\times$ improvement in energy efficiency over previous leading SNNs, based on a comprehensive analysis of compute, data movement, and memory access costs using energy measurements from a commercial 22nm process. Our work thus establishes a new paradigm for energy-efficient SNNs, translating fundamental device physics directly into powerful computational primitives. All codes and data are open source.

cs.LG↗

arXiv2025

Prospects of $|V_{us}|$ and axial vector form factors in $Λ\to pe^{-}{\barν}_{e}$ decay at STCF

We report a feasibility study of the semileptonic decay $Λ\to pe^{-} {\barν}_{e}$ by using a fast simulation software package at STCF. With an anticipated integrated luminosity of 3.4 trillion $J/ψ$ per year at a center-of-mass energy at 3.097 GeV, the statistical sensitivity of the branching fraction is determined to be 0.15\%. The statistical sensitivities of form factors $g_{av}$ and $g_w$ are determined to be 0.4\% and 2.15\%, respectively. Combining this result with $g_1(0)$ from Lattice QCD, we can obtain the projected sensitivity of $|V_{us}|$, to be 0.9\%, which is comparable to the precision obtained through meson decay measurements. The precise measurement to be obtained at STCF will provide a rigorous test of Standard Model.

hep-ex↗

arXiv2025

Conceptual Design Report of Super Tau-Charm Facility: The Accelerator

Electron-positron colliders operating in the GeV region of center-of-mass energies or the Tau-Charm energy region, have been proven to enable competitive frontier research, due to its several unique features. With the progress of high energy physics in the last two decades, a new-generation Tau-Charm factory, Super Tau Charm Facility (STCF) has been actively promoting by the particle physics community in China. STCF holds great potential to address fundamental questions such as the essence of color confinement and the matter-antimatter asymmetry in the universe in the next decades. The main design goals of STCF are with a center-of-mass energy ranging from 2 to 7 GeV and a peak luminosity surpassing 5*10^34 cm^-2s^-1 that is optimized at a center-of-mass energy of 4 GeV, which is about 50 times that of the currently operating Tau-Charm factory - BEPCII. The STCF accelerator is composed of two main parts: a double-ring collider with the crab-waist collision scheme and an injector that provides top-up injections for both electron and positron beams. As a typical third-generation electron-positron circular collider, the STCF accelerator faces many challenges in both accelerator physics and technology. In this paper, the conceptual design of the STCF accelerator complex is presented, including the ongoing efforts and plans for technological R&D, as well as the required infrastructure. The STCF project aims to secure support from the Chinese central government for its construction during the 15th Five-Year Plan (2026-2030) in China.

physics.acc-ph↗