arXiv subjects

Can Chen

Publications and source records attributed to Can Chen.

At least 19 recordsLinked to original sources

arXiv2026

MemT-1.0: Towards Memory-Native Evolution

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.

cs.CL↗

arXiv2026

Stability and Stabilization of Kronecker-Sum-Coupled Multilinear Systems

Coupled dynamical systems with multi-dimensional state structures arise in many applications such as spatiotemporal processes and large-scale interconnected systems. However, existing studies primarily focus on matrix-based coupled systems or tensor-based dynamical systems without couplings. The properties of coupled tensor-based systems remain largely unexplored. In this article, we study Kronecker-sum-coupled multilinear systems under the transform-based tensor product framework. We establish fundamental tensor spectral properties showing that stability can be characterized through lower-dimensional subsystem dynamics together with slice-wise matrix stability in the transform domain. We further develop optimization conditions for state-feedback stabilization and show that the stabilization problem can be decomposed into independent subsystem problems. Finally, we analyze the computational complexity of the proposed framework and demonstrate its substantial computational advantages over unfolding-based approaches using both synthetic systems and multi-inertia motor systems.

math.OC↗

arXiv2026

From Inference to Control: Structure-Guided Control of Hypergraph Dynamics

Controllability determines whether a system's state can be guided toward any desired configuration, making it a fundamental prerequisite for designing effective control strategies. In the context of networked systems, controllability is a well-established concept. However, many real-world systems, from biological collectives to engineered infrastructures, exhibit higher-order interactions that cannot be captured by simple graphs. Moreover, the interaction structures might be unknown and difficult to measure directly. Here, we close this gap by combining hypergraph inference with the identification of controllable nodes. Building on the inferred structure, we design a controller that, given a set of controllable nodes, steers the system toward a desired configuration. We formulate analytical controllability guarantees for polynomial systems. For non-polynomial dynamics on hypergraphs, we propose a heuristic method for identifying controllable nodes and validate the proposed approach using Kuramoto oscillators.

eess.SY↗

arXiv2026

Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs

Clinical questions often depend on linking a patient's multimodal evidence to external biomedical knowledge, yet existing predictive systems rarely represent such links explicitly, so they can neither be traced to their evidence sources nor removed to measure their contributions. We present MM-KG (Multimodal Knowledge Graph), which represents heterogeneous, multimodal patient observations and biomedical concepts as separate layers in one typed graph, joined by explicit alignment edges. First, modality-specific harmonizers convert EHR text, imaging, genomic, and biospecimen data into typed observations mapped to UMLS concepts, which a route-prioritized aligner links to a biomedical knowledge graph. Query-conditioned retrieval then selects a compact subgraph for downstream use by a large language model or a graph neural network. We build MM-KGs for MIMIC-IV and ADNI, and evaluate them with a 2x2 design that separates patient evidence, biomedical knowledge, and their interaction. On questions that require both sources, neither source alone performs far above chance, whereas their combination yields a drug-controlled AUROC interaction of +0.194 on MIMIC and +0.299 on ADNI. On held-out five-candidate ranking, MM-KG outperforms MindMap by +0.131 Hits@1 and leads an adapted GraphCare on the items that require consulting the patient, and deleting the single answer-bearing relation from the retrieved packet returns Hits@1 to the no-knowledge baseline. Finally, query-conditioned retrieval reaches 0.731 AUROC with 6.8x less context than the strongest generic policy, whereas static knowledge graph context gives no consistent gain on ordinary outcome prediction. Knowledge graphs thus benefit clinical LLMs not as background context but as explicit links between multimodal patient evidence and the relation a question requires, and MM-KG makes these links retrievable, traceable, and testable.

cs.LG↗

arXiv2026

Interpretable Hypergraph Learning via Neural Additive Models

Hypergraphs offer a natural framework for modeling networked data, where dependencies among entities are governed by higher-order interactions. While hypergraph learning methods such as hypergraph neural networks have demonstrated remarkable predictive performance, most existing approaches rely on black-box message-passing architectures, making it difficult to disentangle the contributions of node attributes and higher-order structural information. To address this challenge, we introduce the hypergraph neural additive network (HGNAN), an inherently interpretable framework for learning on hypergraph-structured data. HGNAN extends classical neural additive models to higher-order relational data by integrating feature-wise nonlinear decomposition with hypergraph-aware structural aggregation, enabling transparent prediction for both node- and hyperedge-level tasks. Extensive experiments on benchmark datasets demonstrate that HGNAN achieves performance comparable with state-of-the-art hypergraph learning methods while providing intrinsic and meaningful interpretability.

cs.LG↗

arXiv2026

Maximum-Entropy Random Walks on Hypergraphs

Random walks are fundamental tools for analyzing complex networked systems, including social networks, biological systems, and communication infrastructures. While classical random walks focus on pairwise interactions, many real-world systems exhibit higher-order interactions naturally modeled by hypergraphs. Existing random walk models on hypergraphs often focus on undirected structures or do not incorporate entropy-based inference, limiting their ability to capture directional flows, uncertainty, or information diffusion in complex systems. In this article, we develop a maximum-entropy random walk framework on directed hypergraphs with two interaction mechanisms: broadcasting where a pivot node activates multiple receiver nodes and merging where multiple pivot nodes jointly influence a receiver node. We infer a transition kernel via a Kullback--Leibler divergence projection onto constraints enforcing stochasticity and stationarity. The resulting optimality conditions yield a multiplicative scaling form, implemented using Sinkhorn--Schrödinger-type iterations with tensor contractions. We further analyze ergodicity, including projected linear kernels for broadcasting and tensor spectral criteria for polynomial dynamics in merging. The effectiveness of our framework is demonstrated with both synthetic and real-world examples.

eess.SY↗

arXiv2026

Transform-Based Multilinear Algebra via Tensor Decomposition

Transform-based tensor products, including the T-product and its more general form, namely the higher-order tensor-tensor product, have become fundamental tools for multilinear data analysis in applications such as image processing, signal reconstruction, and robotics. While invertible transforms enable tensor computations to be carried out via matrix operations in the transform domain, the resulting storage and computational costs remain prohibitive for high-dimensional, higher-order tensors. To address this challenge, we integrate low-rank tensor decomposition techniques, specifically tensor train decomposition (TTD) and hierarchical Tucker decomposition (HTD), into transform-based multilinear algebra to improve computational and memory efficiency. In particular, we develop TTD- and HTD-based formulations for the T-product and its associated key algebra, such as block diagonalization and tensor singular value decomposition, by operating directly on the factor matrices or tensors of the decompositions. The framework is further generalized to the higher-order tensor-tensor product and applied to multilinear model order reduction problems. We demonstrate the effectiveness and efficiency of our framework with numerical examples.

math.NA↗

arXiv2026

Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding

Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination. Deviating from the prevailing attention intensity assumption, we reveal a deeper dynamic structural misalignment: hallucination is triggered at decision-critical steps where specific attention heads, acting as risky mediators, decouple from visual evidence to lock onto language priors. This establishes a pathological shortcut that bypasses visual grounding. To dismantle this, we propose Fox (Faithfulness and Observational-flow via eXpression-rectification), a training-free inference-time framework. Fox diagnoses structural misalignment using a visual attention entropy probe to localize risky mediators unsupervisedly. We then execute a targeted causal intervention via numerical logit saturation to physically sever the shortcut path. Finally, a conflict-gated cooperative decoding strategy reconciles interventional faithfulness with observational fluency. Extensive experiments demonstrate that Fox achieves SOTA performance, outperforming SID by 29.1% while preserving linguistic richness. Code is available at https://github.com/Cc2021start/Fox.

cs.CV↗

arXiv2026

Training Diffusion Language Models for Black-Box Optimization

We study offline black-box optimization (BBO), aiming to discover improved designs from an offline dataset of designs and labels, a problem common in robotics and DNA with limited labeled samples. While recent work applies autoregressive LLMs to BBO by formatting tasks as natural-language prompts, their left-to-right design generation struggles to capture the strong bidirectional dependencies inherent in design problems. To address this, we propose adapting diffusion LLMs to offline BBO to leverage their bidirectional modeling capabilities. However, a domain gap exists between the natural text pre-training of diffusion LLMs and the heterogeneous signals in BBO (prompts, designs, and labels). To bridge this gap, we construct a unified prompt--response corpus and introduce delimiter tokens to explicitly mark field boundaries for domain adaptation. We further propose a two-stage post-training framework to align the diffusion LLM generation with high-label designs. The first stage performs supervised fine-tuning on the unified dataset via masked-response prediction, and the second stage adopts reinforcement learning with rewards defined by label improvements. Our method achieves state-of-the-art results on Design-Bench under small-data settings with highly efficient training, requiring only $1.5$ H100 GPU hours for discrete tasks. Code for our work is available here: https://github.com/zpointS/DiBO.

cs.CE↗

arXiv2026

Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization

Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD) extrapolation problem. Existing approaches typically bifurcate into inverse methods, which struggle with the ill-posed nature of mapping scores to designs, and forward methods, which often lack the distributional expressivity to quantify uncertainty effectively. In this work, we propose SPADE (Support-Proximity Augmented Diffusion Estimation), a novel framework that reimagines forward surrogate modeling through the lens of conditional generative modeling. SPADE models the forward likelihood p(y|x) using a diffusion model, but with two critical enhancements to tailor it for optimization: (1) a Calibrated Diffusion Estimation module that enforces global consistency in statistical moments and pairwise rankings, and (2) a Support-Proximity Regularization mechanism that implicitly internalizes the data manifold constraint p(x) via kNN-based density estimation. Theoretically, we prove that our regularization is first-order equivalent to maximizing a Bayesian posterior with a valid design prior. Empirically, SPADE achieves state-of-the-art performance across Design-Bench tasks and an LLM data mixture optimization benchmark.

cs.LG↗

arXiv2026

Retrieval-Augmented Generation for Natural Language Processing: A Survey

Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that store knowledge. However, LLMs still suffer from several key issues, such as hallucination problems, knowledge update issues, and lacking domain-specific expertise. The appearance of retrieval-augmented generation (RAG), which leverages an external knowledge base to augment LLMs, mitigates these limitations. This paper presents a systematic review of RAG techniques for natural language processing (NLP), with a focus on retrievers and retrieval fusions. We introduce a novel taxonomy of retrieval fusions, such as query-based, logits-based, latent, and parametric fusion, and provide structured comparisons across accessibility, efficiency, and use cases. The paper further examines RAG applications across diverse NLP tasks, discusses evaluation methodologies and benchmark limitations, and analyzes training paradigms with and without knowledge base updates. Finally, we explore industrial deployment considerations and identify emerging challenges and future directions, including security, efficiency, and graph-based retrieval.

cs.CL↗

arXiv2026

MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks

Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover operations that destroy adversarial properties through discrete interpolation. We introduce Mode Connectivity Evolutionary Attack (MoCo-EA), which replaces traditional crossover with a novel Bézier crossover operator that optimizes perturbations along a continuous Bézier curve between parent perturbations. Our key insight is that adversarial examples lie on connected manifolds where intermediate points maintain and often enhance attack effectiveness. We demonstrate three findings: (1) Successful adversarial perturbations exhibit mode connectivity; (2) Intermediate points along optimized paths achieve higher transferability than endpoints; (3) Bézier crossover dramatically outperforms discrete genetic operations while reducing convergence time and query requirements. By exploiting the geometric structure of adversarial space through path optimization, MoCo-EA provides an efficient and reliable method. Our work challenges the traditional view of adversarial examples as isolated points and opens new directions for both attack generation and defense research.

cs.CR↗

arXiv2026

H3: A Healthcare Three-Hop Index for Physician Referral Network Prediction

Accurate prediction of physician referral links is essential for optimizing care coordination and reducing fragmentation in healthcare delivery. However, existing computational methods, ranging from triadic closure heuristics to graph neural networks, fail to capture the intrinsic properties of physician referral networks, including sparsity, disassortative degree mixing, and hub-dominated topology. Here, we propose H3, a healthcare three-hop index that addresses these limitations by modeling indirect referral pathways through intermediate physicians, with degree-based normalization and a redundancy penalty to mitigate hub-mediated noise. Using Medicare Physician Shared Patient Patterns data, we evaluate H3 under two complementary prediction regimes: within-period prediction, which assesses recovery of contemporaneous referral links under sparse conditions, and cross-period prediction, which tests robustness to temporal shift as referral windows expand. Across both regimes, H3 consistently outperforms classical heuristics and deep learning-based baselines. Unlike black-box neural network approaches, H3 produces fully decomposable predictions traceable to specific intermediary physicians, offering a transparent and deployable solution for referral network completion.

cs.SI↗

arXiv2026

Data-Driven Tensor Decomposition Identification of Homogeneous Polynomial Dynamical Systems

Homogeneous polynomial dynamical systems (HPDSs), which can be equivalently represented by tensors, are essential for modeling higher-order networked systems, including ecological networks, chemical reactions, and multi-agent robotic systems. However, identifying such systems from data is challenging due to the rapid growth in the number of parameters with increasing system dimension and polynomial degree. In this article, we adopt compact and scalable representations of HPDSs leveraging low-rank tensor decompositions, including tensor train, hierarchical Tucker, and canonical polyadic decompositions. These representations exploit the intrinsic multilinear structure of HPDSs and substantially reduce the dimensionality of the parameter space. Rather than identifying the full dynamic tensor, we develop a data-driven framework that directly learns the underlying factor tensors or matrices in the associated decompositions from time-series data. The resulting identification problem is solved using alternating least-squares algorithms tailored to each tensor decomposition, achieving both accuracy and computational efficiency. We further analyze the robustness of the proposed framework in the presence of measurement noise and characterize data informativity. Finally, we demonstrate the effectiveness of our framework with numerical examples.

eess.SY↗

arXiv2026

From Prediction to Diagnosis: Reasoning-Aware AI for Photovoltaic Defect Inspection

Reliable photovoltaic defect identification is essential for maintaining energy yield, ensuring warranty compliance, and enabling scalable inspection of rapidly expanding solar fleets. Although recent advances in computer vision have improved automated defect detection, most existing systems operate as opaque classifiers that provide limited diagnostic insight for high-stakes energy infrastructure. Here we introduce REVL-PV, a vision-language framework that embeds domain-specific diagnostic reasoning into multimodal learning across electroluminescence, thermal, and visible-light imagery. By requiring the model to link visual evidence to plausible defect mechanisms before classification, the framework produces structured diagnostic reports aligned with professional photovoltaic inspection practice. Evaluated on 1,927 real-world modules spanning eight defect categories, REVL-PV achieves 93\% classification accuracy while producing interpretable diagnostic rationales and maintaining strong robustness under realistic image corruptions. A blind concordance study with a certified solar inspection expert shows strong semantic alignment between model explanations and expert assessments across defect identification, root-cause attribution, and visual descriptions. These results demonstrate that reasoning-aware multimodal learning establishes a general paradigm for trustworthy AI-assisted inspection of photovoltaic energy infrastructure.

cs.CV↗

arXiv2026

SynCell: Contextualized Drug Synergy Prediction

Drug synergy is profoundly influenced by cellular context, as variations in protein interaction landscapes and pathway activities across cell types reshape how drugs act in combination. Most existing models overlook this heterogeneity, relying on static or bulk-level protein-protein interaction (PPI) networks that ignore cell-specific molecular wiring. The availability of large-scale transcriptomic data now enables the reconstruction of cell-line-resolved interactomes, offering a new foundation for contextualized drug synergy modeling. Here we present SynCell, a Contextualized Drug Synergy framework that integrates drug-protein, protein-protein, and protein-cell line relations within a unified graph architecture. SynCell leverages cell-line-specific PPI networks to embed the molecular context in which drugs act, and employs graph convolutional learning to model how pharmacological effects propagate through cell-specific signaling networks. This formulation treats synergy prediction as a cell-line-contextualized drug-drug interaction problem. Across the large-scale DrugCombDB benchmark, SynCell consistently outperforms state-of-the-art baselines - including DeepSynergy, HypergraphSynergy, HERMES, BAITSAO, DTF, and NHP - particularly in predicting synergies involving unseen drugs or novel cell lines. When benchmarked against these seven methods, SynCell demonstrates substantial gains in generalization and biological interpretability, confirming that contextualizing PPIs with cell-line resolution is indispensable for accurate synergy prediction.

q-bio.QM↗

arXiv2026

Structural Controllability of Large-Scale Hypergraphs

Controlling real-world networked systems, including ecological, biomedical, and engineered networks that exhibit higher-order interactions, remains challenging due to inherent nonlinearities and large system scales. Despite extensive studies on graph controllability, the controllability properties of hypergraphs remain largely underdeveloped. Existing results focus primarily on exact controllability, which is often impractical for large-scale hypergraphs. In this article, we develop a structural controllability framework for hypergraphs by modeling hypergraph dynamics as polynomial dynamical systems. In particular, we extend classical notions of accessibility and dilation from linear graph-based systems to polynomial hypergraph dynamics and establish a hypergraph-based criterion under which the topology guarantees satisfaction of classical Lie-algebraic and Kalman-type rank conditions for almost all parameter choices. We further derive a topology-based lower bound on the minimum number of driver nodes required for structural controllability and leverage this bound to design a scalable driver node selection algorithm combining dilation-aware initialization via maximum matching with greedy accessibility expansion. We demonstrate the effectiveness and scalability of the proposed framework through numerical experiments on hypergraphs with tens to thousands of nodes and higher-order interactions.

math.OC↗

arXiv2026

Offline Model-Based Optimization: Comprehensive Review

Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is prohibitively expensive or infeasible, with applications spanning protein engineering, material discovery, neural architecture search, and beyond. The main difficulty lies in accurately estimating the objective landscape beyond the available data, where extrapolations are fraught with significant epistemic uncertainty. This uncertainty can lead to objective hacking(reward hacking), exploiting model inaccuracies in unseen regions, or other spurious optimizations that yield misleadingly high performance estimates outside the training distribution. Recent advances in model-based optimization(MBO) have harnessed the generalization capabilities of deep neural networks to develop offline-specific surrogate and generative models. Trained with carefully designed strategies, these models are more robust against out-of-distribution issues, facilitating the discovery of improved designs. Despite its growing impact in accelerating scientific discovery, the field lacks a comprehensive review. To bridge this gap, we present the first thorough review of offline MBO. We begin by formalizing the problem for both single-objective and multi-objective settings and by reviewing recent benchmarks and evaluation metrics. We then categorize existing approaches into two key areas: surrogate modeling, which emphasizes accurate function approximation in out-of-distribution regions, and generative modeling, which explores high-dimensional design spaces to identify high-performing designs. Finally, we examine the key challenges and propose promising directions for advancement in this rapidly evolving field including safe control of superintelligent systems.

cs.LG↗