Searcharxiv⌕ Search

arXiv subjects

Junjie Wu

Publications and source records attributed to Junjie Wu.

At least 37 records · Page 2Linked to original sources
arXiv2026

Real-time decoding of quantum error correction codes using high-performance computing

Quantum error correction (QEC) is indispensable for building scalable fault-tolerant quantum computers. Effective QEC demands stringent real-time decoding: the decoder must process syndrome measurements and determine corrections within a time scale--typically on the order of microseconds, to avoid data backlog. Scaling to large number of logical qubits further necessitates significant computational resources. In this work, we propose an architecture, called \emph{THQLink}, for real-time decoding of quantum error correction codes using high-performance computing (HPC) resources. The network connecting the HPC and the control system of quantum processing unit (QPU) is built on TH-Express and can be adapted to different quantum technologies and their associated control stacks. We report a round-trip latency of 2.944 $μ$s on average, with an incremental overhead of 130 ns per additional hop. Using a parallel window strategy, we demonstrate real-time decoding (1 $μ$s per QEC round) of the surface code up to distance 19 using a matching-based decoder on CPUs. Our work presents a scalable framework for real-time decoding in fault-tolerant quantum computing. It can be readily applied to quantum-centric supercomputers that feature tight integration between QPU and HPC resources, thereby enabling efficient support for hybrid quantum-classical algorithms and computation-intensive workloads offloaded from the QPU.

quant-ph↗
arXiv2026

Inter-Residue Geometry Attention for Antibody-Specific Epitope Prediction

Antibody-specific epitope prediction aims to identify which antigen residues are recognized by a given antibody, a task that depends on the three-dimensional complementarity between antibody CDRs and the antigen surface. Existing methods usually leverage PLM embeddings and inject structure through additional graph, surface, or point-cloud encoders, where the positional mechanism inside attention remains largely tied to one-dimensional sequence order. For proteins, the analogue of a token offset is not only sequence separation, but also the three-dimensional displacement between residues after folding. This raises a question, can folded residue geometry serve as the positional mechanism of attention itself? We propose Local-Frame 3D Rotary Position Encoding (LF3DRoPE), which expresses inter-residue displacements in backbone-defined local frames and injects them directly into rotary attention. This design preserves continuous directional geometry while ensuring invariance to global $\mathrm{SE}(3)$ transformations. On the AsEP benchmark, LF3DRoPE achieves state-of-the-art $\mathrm{MCC}$ on both ratio and epitope-group splits. Ablations and rigid transformation tests show that local three-dimensional geometry provides information beyond sequence-order attention while preserving invariance to arbitrary global coordinate systems. Mutation ranking results further indicate that LF3DRoPE captures antigen-specific structural compatibility.

cs.AI↗
arXiv2026

Expressive Power and Limitations of Multi-photon Quantum Neural Networks

Quantum neural networks (QNNs) have shown promise in leveraging quantum computation for machine learning tasks. Utilizing multiple identical photons as input, multi-photon quantum neural networks (MPQNNs) have the potential to enhance the expressivity through increasing the photon number. However, how precisely the expressivity of an MPQNN is affected by an increase in photon number, and whether it can be infinitely enhanced by increasing the photon number, remains unexplored. In this work, we quantitatively estimate the expressivity of this model by deriving upper bounds on approximation error in two cases. In the case of a fixed observable, there exists a threshold that scales linearly with the mode number. Below the threshold, the expressivity of an MPQNN can be enhanced polynomially by increasing the photon number. Above the threshold, however, increasing the photon number does not affect the expressivity. In the case of a trainable observable, the expressivity can always be enhanced polynomially by increasing the photon number. These findings are then validated by numerical simulations. Our work elucidates the performance enhancement of multi-photon quantum feature in QNNs, as well as its limitations, offering guidance for leveraging multi-photon advantages in quantum machine learning.

quant-ph↗
arXiv2026

Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation

Estimating heterogeneous treatment effects is central to targeted interventions, such as personalized promotions and precision medicine. We focus on the conditional average treatment effect (CATE), a standard estimand for characterizing such heterogeneity. Even under standard identification conditions, finite-sample CATE estimation requires learning the nuisance structure for covariate adjustment and treatment-effect heterogeneity, often together with an effective representation of X. Raw numerical and categorical encodings can leave semantic relations and higher-order interactions implicit, making this joint task locally unstable. A motivating study further shows that this instability appears through partially separable assignment- and heterogeneity-side channels. Building on this observation, we propose CURL (Causal Uncertainty-guided Representation Learning), a plug-in adapter that uses estimator uncertainty to allocate pretrained semantic capacity to locally unstable units. CURL queries a frozen LLM through two role-conditioned prompts, constructs assignment- and heterogeneity-oriented representations from the observed covariates, and routes them through separated pathways. On four benchmarks, CURL improves ten host learners in most settings, while ablation, refinement-dynamics, route-reassignment, and probe analyses support the intended design and roles of the two channels.

cs.LG↗
arXiv2026

EvoOMG: An Evolution-Oriented Multi-Agent Guidance Framework for Heterogeneous Legacy-and-MLO Wi-Fi Networks

The gradual deployment of Wi-Fi 7/8 multi-link operation (MLO) will lead to long-term coexistence between legacy non-MLO stations (STAs) and MLO-capable STAs in WLANs. This mixed deployment makes throughput optimization challenging because legacy STAs follow single-link contention and transmission, whereas MLO-capable STAs can exploit multiple links with richer access opportunities. Existing learning-based methods usually treat such networks as homogeneous systems and directly map the current observation to a complete MAC action, which cannot faithfully represent both legacy single-link and MLO multi-link behaviors. To address this issue, we propose EvoOMG, an evolution-oriented multi-agent guidance framework for heterogeneous legacy-and-MLO Wi-Fi networks. EvoOMG reformulates throughput optimization as a standard-constrained staged multi-agent decision problem. Each agent encodes recent channel, queue, contention, and transmission histories, first generates contention guidance, and then produces aggregation guidance conditioned on the preceding access stage and standard-specific feasibility constraints. This autoregressive design follows the Wi-Fi MAC order of ``contention before transmission'' while preserving distinct protocol behaviors of legacy and MLO-capable STAs. NS-3 evaluations show that EvoOMG improves scheduled goodput, convergence stability, and MLO link utilization over static enhanced distributed channel access (EDCA), one-step MADDPG, and independent-learning baselines, achieving substantial performance gains in representative mixed-standard scenarios.

cs.NI↗
arXiv2026

Extraction of a structural short-range order descriptor from nanobeam electron diffraction patterns using a transfer learning approach

Amorphous solids exhibit structural short-range order despite lacking long-range crystalline order, with this structural descriptor found to be important for determining mechanical properties. Nanobeam electron diffraction offers a potential route for experimental characterization of structural short-range order, yet efforts to date have been primarily qualitative in nature. In this work, machine learning approaches based on transfer learning are used to enable quantitative analysis of nanobeam electron diffraction data from amorphous solids. A ResNet-18 model is trained on simulated diffraction patterns taken from different locations within simulated metallic glasses and amorphous grain boundary complexions in the Cu-Zr alloy system that were created with hybrid molecular dynamics and Monte Carlo simulations. The disorder parameter is found to be a superior target structural descriptor compared to traditional Voronoi indices for this task. The model achieves a low validation mean absolute error across diffraction patterns corresponding to different interaction volumes, demonstrating excellent performance and potential transferability. Testing was performed using other simulated nanobeam electron diffraction data as well as experimental nanobeam electron diffraction patterns, showing that the model can reliably capture spatial variations in local structural state. As a whole, this framework is able to overcome the challenges in the quantitative experimental characterization of structural short-range order, enabling improved characterization of amorphous solids and the exploration of structure-property relationships.

cond-mat.mtrl-sci↗
arXiv2026

Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation

World action models~(WAMs) have shown great promise for autonomous driving and urban navigation. Built upon Vision-Language-Action models or video generation models, existing approaches suffer key limitations: (1) High inference latency due to future observation prediction at test time, and (2) tightly coupled video and action modeling leading to representational mismatch and degraded generalization. To address both issues, we propose Metis, an end-to-end WAM framework that decouples video generation and action prediction. Specifically, Metis employs a Mixture-of-Transformers architecture with dedicated experts for video generation and action prediction, preserving the intrinsic distributional properties of each task. To enhance efficiency, we introduce an asymmetric attention mask that enables joint training of both experts while allowing the action model to bypass explicit video generation during inference. This design ensures training-inference consistency and significantly reduces computational costs without compromising planning performance. Extensive experiments demonstrate state-of-the-art performance on the NAVSIM navhard and navtest benchmarks and the CityWalker navigation benchmark, validating both the generalizability and efficiency across diverse tasks. Real-robot deployments further confirm the practical feasibility of our approach.

cs.CV↗
arXiv2026

An iterative Ising decoder for quantum error correction codes

The Ising framework maps the decoding problem in quantum error correction onto ground-state optimization of a classical Hamiltonian, in which $X$-$Z$ error correlations enter as cross terms. Under phenomenological depolarizing noise, the exact joint formulation contains up to 8-body interactions for the toric code and 10-body for the $6.6.6$ color code. These high-order terms degrade solver convergence, inflate runtime, and raise the auxiliary spin overhead when embedding into native 2-body Ising hardware. In this work, we propose the iterative low-order decoding (ILOD) algorithm, which alternates between $X$- and $Z$-type sub-Hamiltonians, approximating cross-type correlations through Bayesian priors that reweight each type's couplings using the other type's inferred error configuration. This halves the maximum body count of interaction terms in the Hamiltonian, accelerating the solver, restoring convergence at larger code distances, and reducing the total spin count for 2-body embedding by a factor of $2.5$. For the toric code, ILOD attains a threshold of $4.73%$ versus $4.83%$ for the joint formulation, with the empirical runtime ratio scaling as $(0.81)^d$. For the $6.6.6$ color code, their thresholds agree within statistical uncertainty for small code distances, and ILOD remains convergent for larger distances where the joint formulation fails to converge despite a larger annealing budget.

quant-ph↗
arXiv2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

cs.CL↗
arXiv2026

Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting

Zero-shot time series forecasting aims to predict future values for previously unseen series, requiring models to generalize temporal dynamics beyond the training distribution. While recent foundation models achieve strong in-domain performance through large-scale pretraining, their effectiveness often relies on broad data coverage and implicit pattern memorization, which can limit generalization when data are scarce or source and target domains are disjoint. In this work, we propose FSA, a feature-to-strategy framework for controlled zero-shot univariate forecasting. Instead of directly modeling raw sequences in the observation space, FSA learns a structured mapping from an interpretable feature space to an autoregressive strategy space. This design introduces explicit inductive biases that disentangle global trends, periodic components, and local temporal dynamics, enabling the model to capture transferable time-series structure with fewer data assumptions. Empirical results show that, under identical pretraining data, training protocol, and comparable parameter budgets, FSA outperforms Transformer-based architectures in our controlled zero-shot setting.

cs.LG↗
arXiv2026

DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories

Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where information is distributed across temporal sequences rather than confined to single snapshots. To bridge this gap, we introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task. Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues. We construct DISBench, a challenging benchmark built on interconnected visual data. To address the scalability challenge of creating context-dependent queries, we propose a human-model collaborative pipeline that employs vision-language models to mine latent spatiotemporal associations, effectively offloading intensive context discovery before human verification. Furthermore, we build a robust baseline using a modular agent framework equipped with fine-grained tools and a dual-memory system for long-horizon navigation. Extensive experiments demonstrate that DISBench poses significant challenges to state-of-the-art models, highlighting the necessity of incorporating agentic reasoning into next-generation retrieval systems.

cs.CV↗
arXiv2026

Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding

Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning.

cs.CL↗
arXiv2026

SN 2023fyq: direct detection of a Type Ibn supernova progenitor and its multi-wavelength environmental constraints

Context. Type Ibn supernovae (SNe) are characterized by narrow helium emission lines arising from ejecta-circumstellar medium interaction, yet their progenitors remain debated, with both massive Wolf-Rayet stars and low-mass helium stars in binaries proposed. Aims. We aim to directly identify the progenitor of the Type Ibn SN 2023fyq and to characterize its environment in order to constrain the progenitor's nature and evolutionary channel. Methods. We search for the SN progenitor based on pre-explosion and late-time HST and JWST images and derive its properties by fitting the spectral energy distribution. We investigate the SN environment by probing the stars, dust, ionized gas and molecular gas with a multi-wavelength dataset including HST and JWST imaging, VLT/MUSE integral-field-unit spectroscopy and ALMA CO (2--1) radio interferometry. Results. We discover a pre-explosion source at the SN position, which is consistent with a hot ($T>$15000 K) and luminous (log($L$/$L_\odot$) $\gtrsim$ 5.5) SN progenitor and a possible host star cluster. The progenitor is confirmed to have disappeared after explosion. Analysis of the SN environment implies that the progenitor likely has an age of log($t$/yr) = 7.1--7.2. These phenomena disfavor a very massive single-star progenitor and instead support a binary scenario involving a low-mass helium star and a compact object; the observed progenitor emission likely arises from binary interaction that began at least $\sim$12 yr before the explosion. Conclusions. SN 2023fyq is the first Type Ibn SN with a directly detected progenitor and a possible host star cluster. It adds to the diversity of Type Ibn SNe in terms of their progenitor channels and mass-loss mechanisms.

astro-ph.SR↗
arXiv2026

Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle spatio-temporal dynamics. In this paper, we focus on fine-grained TAL in professional badminton videos and introduce a new benchmark dataset, Fine-Badminton, which consists of 31 matches with 29 fine-grained stroke categories, covering 2104 rallies and 27597 annotated actions. To effectively capture the intricate motion patterns in such scenarios, we propose a Decoupling Spatio-Temporal Adapter (DSTA), which enables efficient modeling of spatio-temporal features within a parameter-efficient framework. Specifically, DSTA decomposes motion representation into three parallel branches, capturing temporal dynamics as well as vertical and horizontal spatial variations. The design allows the model to better distinguish subtle differences among fine-grained actions. Extensive experiments on both the Fine-Badminton dataset and the ShuttleSet benchmark demonstrate that the proposed method achieves state-of-the-art performance while introducing only a marginal increase in computational and parameter cost. These results validate the effectiveness and efficiency of the proposed approach for fine-grained temporal action localization.

cs.CV↗
arXiv2026

LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation

Temporal Action Detection (TAD) requires precise localization of action boundaries within long, untrimmed video sequences. While current high-performing methods achieve strong accuracy, they are often characterized by excessive parameter counts, substantial computational overhead, and a reliance on specialized operators that hinder deployment across diverse hardware platforms. This paper presents LiquidTAD, a framework that distills the exponential relaxation prior of liquid neural dynamics into a parallel temporal operator, rather than reproducing full Liquid Neural Network (LNN) dynamics. By introducing a Parallel Liquid-inspired Relaxation mechanism, sequential ODE solving is avoided through a fully vectorized, non-recursive formulation built entirely upon standard neural operations, enabling hardware-agnostic deployment with linear complexity with respect to the temporal length. A complementary Hierarchical Decay-Rate Sharing Strategy further adapts this relaxation prior across feature pyramid levels, stabilizing optimization and implicitly compensating for temporal compression in deeper layers. Experimental evaluations on THUMOS-14 and ActivityNet-1.3 demonstrate that LiquidTAD achieves accuracy competitive with strong baselines while substantially lowering the model footprint. Specifically, on THUMOS-14, LiquidTAD achieves 69.46\% average mAP with only 10.82M parameters and 27.17G FLOPs, reducing the parameter count by over 60\% compared with ActionFormer.

cs.CV↗
arXiv2026

SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is often essential for accurately interpreting each chunk. To address this, prior work has explored encoding longer context windows to produce embeddings for longer chunks. Despite these efforts, gains in retrieval and downstream tasks remain limited. This is because (1) longer chunks strain the capacity of embedding models due to the increased amount of information they must encode, and (2) many real-world applications still require returning localized evidence due to constraints on model or human bandwidth. We propose an alternative approach to this challenge by representing short chunks in a way that is conditioned on a broader context window to enhance retrieval performance -- i.e., situating a chunk's meaning within its context. We further show that existing embedding models are not well-equipped to encode such situated context effectively, and thus introduce a new training paradigm and develop the situated embedding models (SitEmb). To evaluate our method, we curate a book-plot retrieval dataset specifically designed to assess situated retrieval capabilities. On this benchmark, our SitEmb-v1 model based on BGE-M3 substantially outperforms state-of-the-art embedding models, including several with up to 7-8B parameters, with only 1B parameters. Our 8B SitEmb-v1.5 model further improves performance by over 10% and shows strong results across different languages and several downstream applications.

cs.CL↗
arXiv2026

Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge

Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across various visual tasks. However, most existing judge models are optimized for single-task scenarios and struggle to generalize to diverse contexts, which is a critical requirement for reliable evaluation. To address this limitation, we propose Multi-Task Reinforcement Learning for MLLM-as-a-Judge (MT-RL-Judge), a framework that jointly optimizes the judge model across multiple tasks, leveraging the generalization capabilities of RL. Experimental results against several strong baselines demonstrate that MT-RL-Judge outperforms strong baselines in both judgment consistency and correlation with human preferences. Furthermore, our approach exhibits robust generalization on out-of-distribution tasks, further validating its effectiveness.

cs.CL↗
arXiv2026

Non-linear associations of amyloid-$β$ with resting-state functional networks and their cognitive relevance in a large community-based cohort of cognitively normal older adults

Background: Non-linear alterations in brain network connectivity may represent early neural signatures of Alzheimer's disease (AD) pathology in cognitively normal older adults. Understanding these changes and their cognitive relevance may help clarify early network vulnerability associated with AD pathology. Most prior studies recruited participants from memory clinics, often with subjective memory concerns, limiting generalizability. Methods: We examined 14 large-scale functional brain networks in 968 cognitively normal older adults recruited from the community using resting-state functional MRI, cerebrospinal fluid (CSF) biomarkers (amyloid-$β$ 1-42 [A$β$], total tau, phosphorylated tau 181), and neuropsychological assessments. Functional networks were identified using group independent component analysis. Results: Inverted U-shaped associations between CSF A$β$ and functional connectivity were observed in the precuneus network and ventral default mode network (DMN), but not in the dorsal DMN, indicating network-specific vulnerability to early amyloid pathology. Higher connectivity in A$β$-related networks, including dorsal and ventral DMN, precuneus, and posterior salience networks, was associated with better visual memory, visuospatial, and executive performance. No significant relationships were observed between CSF tau and functional connectivity. Conclusions: Using a large, community-based cohort, we demonstrate that non-linear alterations in functional connectivity occur in specific networks even during the asymptomatic phase of AD. Moreover, A$β$-related network connectivity is cognitively relevant, highlighting early network vulnerability and its functional consequences in amyloid pathology.

q-bio.NC↗