Searcharxiv⌕ Search

arXiv subjects

Jun Hu

Publications and source records attributed to Jun Hu.

At least 19 recordsLinked to original sources
arXiv2026

HyScale: Scaling Long-Context Training for Learned Sparse Attention

We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however, grows into the training bottleneck. For each query, it scores every previous token whereas sparse attention reads only $k$; worse, current systems materialize a full score table and repeat selection during recomputation. Our key insight is that the output of selection is not an activation, but rather a set of indices. Building on it, HyScale introduces HyTopK and selection replay. HyTopK finds each query's exact top-$k$ on the fly without a score table, while selection replay reuses forward-pass selection in recomputation. Together with holistic system optimizations tackling end-to-end training challenges, HyScale speeds up GLM-5.1 training on 1M-token sequences by 2.07$\times$ over Megatron-LM on 512 H20 GPUs. It also speeds up the CSA layers of DeepSeek-V4-Flash and the QSA layers of Qwen3.8-Flash-Next by 2.01$\times$ and 1.57$\times$ at 1M tokens on 32 H800 GPUs.

cs.AI↗
arXiv2026

The center conjecture for cyclotomic Hecke algebras and cohomology of quiver varieties

For a quiver without edge loops, we construct an isomorphism from the cohomology of a Nakajima quiver variety with coefficients in an arbitrary field to the Jucys--Murphy center of the corresponding cyclotomic KLR algebra over that field. In affine type $A^{(1)}_{e-1}$, combining this with a dimension count shows that this Jucys--Murphy center coincides with the full center in characteristic $0$, when the characteristic does not divide $e$, and when the characteristic equals $e$. This follows from a geometric theorem showing that the sum of these cohomology rings is cocyclic as a module over an integral form of a loop algebra. As a consequence, we prove that the center of a cyclotomic Hecke algebra of type $G(r,1,n)$ with $q\neq 1$ over any field is generated by symmetric polynomials in its Jucys--Murphy elements, and the same holds over any commutative domain in which $q-1$ is invertible. We also prove a generalization to the integral case of the conjecture of Krylov, Paegelow and Shlykov identifying the equivariant $K$-theory of the core of a Gieseker variety with the cocenter of the generic cyclotomic Hecke algebra, including the natural extension of this conjecture to positive characteristic.

math.RT↗
arXiv2026

A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation

A few well-annotated datasets for land-cover semantic segmentation have recently been introduced to advance the field of earth observation technologies. However, these datasets overlook the significant diversity among geographic areas with different climates, which can greatly impact and diversify land cover. Consequently, this leads to a domain gap in remote sensing images and severe performance degradation of the segmentation models. To enhance land-cover semantic segmentation with improved generalization ability, we conducted the first investigation into the impact of climate on this task. In this paper, we present a unique large-scale Climate-Aware Satellite Images Dataset (CASID) specifically designed for domain adaptive land-cover semantic segmentation. It consists of 980 satellite images with a size of 5000 x 5000 pixels, collected from 30 different regions around Asia, covering over 24,500 square kilometers. These images are gathered from four distinct climate zones, namely temperate monsoon, subtropical monsoon, tropical monsoon, and tropical rainforest. It includes four sub-datasets/domains, each representing one of the aforementioned climate zones. This characteristic makes CASID the first climate-aware land-cover semantic segmentation dataset with multiple domains. Additionally, we provide a comprehensive analysis of the samples from the four climate zones, emphasizing differences in global image features, image texture, category distribution, spectral value, and object shape. These analyses offer valuable insights for subsequent research in this field. Moreover, we conduct extensive experiments to evaluate the latest semantic segmentation and unsupervised domain adaptation methods on the CASID dataset. These results serve as a robust baseline for future research endeavors. Our dataset will be made publicly available at https://github.com/Linwei-Chen/CASID.

cs.CV↗
arXiv2026

A Pressure-Free Virtual Element Method for the Surface Stokes Problem

We develop a pressure-free virtual element method for the surface Stokes problem on polygonal approximations of closed surfaces of arbitrary genus. The method extends the planar VEM Stokes complex to discrete surfaces, yielding a nonconforming complex with an exactly tangential, $H(\operatorname{div})$-conforming velocity space, commuting interpolation, and the correct discrete cohomology. To obtain the weak consistency needed for optimal convergence, we introduce an edge correction that preserves the complex without adding degrees of freedom; the resulting construction reduces to the original complex in the planar setting. The virtual formulation requires no penalties, and a local divergence-preserving reconstruction provides a computable pressure-robust load. We also construct explicit macroelement representatives whose energy and load induce an alternative formulation on the VEM space, algebraically equivalent to a direct macroelement Galerkin method. The original virtual formulation and the macroelement method are stable and attain optimal first-order convergence in the broken $H^1$ norm and second-order convergence in the $L^2$ norm for the velocity. Numerical experiments illustrate these convergence rates, the role of the edge correction, and pressure robustness.

math.NA↗
arXiv2026

FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation

Graph fraud explanation generation emerges as an important task, which requires jointly leveraging graph structure and content information to produce human-readable explanations for a given risk label. An intuitive approach is to adapt existing graph-enhanced large language models (LLMs), which inject graph structure into LLMs via graph-conditioned instruction tuning or structure-aware embeddings. However, existing methods face two key challenges in graph fraud explanation generation: a lack of evaluation protocols tailored to explanation quality, and a mismatch between the granularity of graph information they provide and what explanation generation requires. In this paper, we propose FRaud Explanation Generation via Agentic Graph Context NavigaTION (FRACTION), a framework for graph fraud explanation generation. To evaluate explanation quality, we introduce a task-specific rubric that assesses faithfulness, graph grounding, helpfulness, consistency, and conciseness, and validate it against human judgments. To focus on fine-grained details of relevant neighbors without reading the entire neighborhood, we equip a language model with graph tools that progressively disclose neighbor records. To train our graph agent, we propose a rubric-guided trajectory distillation strategy through which the agent learns both tool-use behavior and structured explanation generation. Experimental results on three fraud datasets demonstrate consistent improvements over state-of-the-art baselines under a human-aligned rubric.

cs.LG↗
arXiv2026

Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis

Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRISM (Population-Retrieved Inference for Structured Multimodal Prognosis), a multimodal language model that combines per-feature numerical tokenization, recency-weighted aggregation of longitudinal ECGs, and a dual-modality population memory bank. Retrieval operates in representation space: the model receives mean-pooled embeddings of similar training-cohort encounters, while no individual retrieved record enters the prompt. On the 1,443-task MDS-ED benchmark, PRISM achieves AUROCs of 86.2% for diagnosis, 93.1% for deterioration, 91.8% for ICU admission, and 92.8% for mortality. These results use a 96-hour pre-arrival window unavailable to reported baselines. With benchmark-window inputs only, PRISM reaches 0.8895 AUROC, compared with 0.8937 for UniPACT and 0.8889 for MDS-ED. A matched-input compact fusion model using the same five evidence streams and frozen encoders reaches 0.7652 AUROC, versus 0.9092 for PRISM. Replacing numerical EHR encoding with text serialization reduces AUROC by 3.66 points; removing pre-arrival history reduces it by 1.97 points; and zeroing retrieval reduces it by 0.99 points. Genuine retrieval outperforms random-neighbor retrieval by 0.97 macro-average points, although a paired task-level sign test does not establish a uniform advantage (p=0.067). On the external MC-MED cohort, supervised fine-tuning reaches 0.8611 AUROC, compared with 0.8227 for locally trained gradient boosting and 0.7841 for source-only PRISM. These results support structure-aware multimodal integration and supervised external adaptation.

cs.AI↗
arXiv2026

Exact Representation of Piecewise Polynomial Finite Element Functions by Two-Hidden-Layer Multilayer Perceptrons

We construct exact representations of finite element functions of arbitrary polynomial degree on simplicial meshes in any spatial dimension by two-hidden-layer multilayer perceptrons (MLPs). The first hidden layer uses $\mathrm{ReLU}^0+\mathrm{ReLU}$, and the second uses the degree-dependent activation $\mathrm{ReLU}^k$. The neural networks can realize both zero-skeleton and prescribed-skeleton representatives of discontinuous finite element functions, where the former vanish on the mesh skeleton and the latter admit independently prescribed polynomial data on each relatively open lower-dimensional mesh subsimplex; in particular, continuous finite element functions can be represented pointwise on the closed domain. In the continuous case, a half-open decomposition reduces the second-hidden-layer width by assigning each subsimplex to a single incident element. The number of nonzero parameters grows linearly with the number of elements for fixed spatial dimension, polynomial degree, and output dimension, and it is of the same order as the number of global degrees of freedom of the finite element space in the continuous case, provided that the mesh is shape-regular. All parameters in the neural network can be explicitly computed via the information of the mesh and finite element function without training.

math.NA↗
arXiv2026

Can a Robot Read Braille? - Learning to Adapt Contact via Imitation Learning for Tactile Braille Recognition

For people who are blind, touch provides an essen-tial channel for accessing written information through Braille. Bringing a similar capability to robots requires them not only to recognize tactile patterns, but also to actively establish physical contact that makes those patterns readable. Yet existing robotic Braille readers largely focus on recognition after contact, leaving contact establishment itself insufficiently addressed. We present an adaptive-contact framework for robotic tactile Braille reading that assesses contact quality and physically corrects unsuitable contact before recognition and reconstruc-tion. Multi-Head Policy Learning uses expert-guided contact-adjustment demonstrations to jointly learn contact acceptability and pose corrections. During deployment, the robot iteratively evaluates and re-establishes contact, retaining reliable tactile observations for pose-aware fusion and Braille reconstruction. Across 20 physical Braille plates used for learning and eval-uation, the proposed approach achieves 94.0% tactile quality and 88.6% tactile reconstruction on the ten online-evaluation plates. These results demonstrate the importance of actively establishing readable contact, rather than relying solely on recognition under imperfect tactile observations, for reliable robotic Braille reading.

cs.RO↗
arXiv2026

CALM: Current Aligned Link Manipulation for Single Arm Oversized Object Lifting

Most robots manipulate objects solely with their end effectors, whereas humans flexibly leverage different body parts, such as the forearm and elbow, especially when handling oversized objects. Learning such whole-arm manipulation is chal-lenging due to long-horizon sparse rewards, limited contact sens-ing, and the sim-to-real gap in contact and actuator dynamics. To address these challenges, we propose Current-Aligned Link Manipulation, a framework for learning long-horizon contact-rich manipulation using motor current as joint load related feedback. Three stage-specific policies first learn repositioning, grasping, and lifting using privileged simulation information, and a stage router sequences them to generate complete task demonstrations. For sim-to-real transfer, a causal current mapper predicts physical motor current from simulated joint histories, aligning the actuator current observation between simulation and hardware. A unified student policy then learns from these demonstrations using only deployable sensor observations and is further refined with DAgger. The task policies are trained entirely in simulation, and the final student is deployed on hardware. Experiments demonstrate 76.2% (762/1000 trials) complete-task success in simulation and 73.3% success (22/30 trials) on the physical robot for sequential oversized-object lifting.

cs.RO↗
arXiv2026

MENO: Memory-Efficient Neural Operator

We propose the Memory-Efficient Neural Operator (MENO) as a high-performance PDE neural solver based on the Manifold Function Encoder (MFE). MENO features three primary advantages: (1) MENO has a significantly smaller memory footprint and much faster training speed than other popular architectures, with the memory footprint being independent of the data resolution, and therefore holds the potential for scaling up to large-scale models. (2) MENO can accept PDE inputs of arbitrary form, including arbitrary geometric domains and arbitrary discretizations. In particular, it is capable of handling cross-geometry scenarios, i.e., where the input functions and the output solutions are defined on different manifolds. (3) MENO exhibits strong generalization capability, and achieves the best accuracy on most of the benchmarks we tested, compared with the results reported in the literature. The code is available on GitHub at https://github.com/jpzxshi/MENO, and all numerical examples in this paper can be run with a single command to reproduce the reported results.

cs.LG↗
arXiv2026

Error Analysis for Solving Elliptic Interface Problems with Randomized Neural Networks

This paper presents a unified error analysis of randomized neural networks (RaNNs) for elliptic interface problems. We first derive an integral representation of Barron functions using the standard $\tanh$ activation, which yields a $C^2$-approximation bound valid for any hidden-parameter distribution supported on a cube with strictly positive density. We then establish a quantitative $\mathcal{O}(n^{-1})$ generalization bound for the composite loss that enforces the partial differential equation, boundary, and interface conditions simultaneously, where $n$ denotes the number of training samples. Combining these results with the optimization guarantees for RaNNs, we obtain an a priori $L^2$ error estimate for the neural network solution in the presence of interface discontinuities. Numerical experiments are presented to validate the theoretical results.

math.NA↗
arXiv2026

New runner removal theorems for the cyclotomic Hecke algebras of type $G(r,1,n)$

For the Iwahori-Hecke algebras $\mathcal H_q(\mathfrak S_n)$ of the symmetric group $\mathfrak S_n$ at a primitive $e$-th root of unity, James and Mathas proved a theorem which relates $v$-decomposition numbers $d_{λμ}^{e}(v)$ for different values of $e$, by adding ``empty runners'' to the abacus display for the labelling partitions $λ,μ$. Fayers proved a similar theorem, which involves adding ``full'' runners to these abacus displays. In this paper we use Uglov's map from the set of $r$-abaci for $r$-partitions to the set of $e$-abaci for partitions to extend these theorems to the cyclotomic Hecke algebras of type $G(r,1,n)$.

math.RT↗
arXiv2026

Affine quantum Schur--Weyl duality

Let $\mathpzc K$ be an arbitrary commutative ring containing an invertible element $\varepsilon$. Let ${\mathcal H}_{\!\vartriangle\!}(r)_{\mathpzc K}$ be the extended affine Hecke algebra of type $A$ with Hecke parameter $\varepsilon$, let $Ω_{\mathpzc K}^{\otimes r}$ be the affine tensor space, and let ${\mathcal S}_{\!\vartriangle\!}(n,r)_{\mathpzc K}$ be the corresponding affine quantum Schur algebra. We first prove that the natural right action of ${\mathcal H}_{\!\vartriangle\!}(r)_{\mathpzc K}$ on $Ω_{\mathpzc K}^{\otimes r}$ is always faithful. Assume further that $\mathpzc K$ is a field of characteristic $0$ and that $\varepsilon$ is not a root of unity. We prove that, for any $n\geq 2$, the natural algebra homomorphism $ξ_r:{\mathcal H}_{\!\vartriangle\!}(r)_{\mathpzc K}\rightarrow\operatorname{End}_{{\mathcal S}_{\!\vartriangle\!}(n,r)_{\mathpzc K}}(Ω_{\mathpzc K}^{\otimes r})^{\mathrm{op}}$ is an isomorphism. This proves Conjecture~3.8.8 of \cite{DDF}. As an application, we prove the conjecture formulated in \cite[5.2.4]{DDF} concerning the center of the affine quantum Schur algebra. We also prove that ${\mathcal S}_{\!\vartriangle\!}(n,r)_{\mathpzc K}$ is left and right Noetherian whenever $\mathpzc K$ is a Noetherian commutative ring, which verify a conjecture in \cite[Rem. 1.7]{DY}.

math.QA↗
arXiv2026

CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation

Electrocardiography (ECG), photoplethysmography (PPG), and phonocardiography (PCG) provide complementary views of the same cardiac cycle, yet existing cardiac foundation models are trained for a single sensing modality, leaving the shared physiology across sensors unexploited. We introduce CardioState-JEPA, a cardiac foundation model to learn a single shared representation jointly across ECG, PPG, and PCG, built on a physiology-aware joint-embedding predictive architecture. The model maps heterogeneous waveforms into a common token space, processes them with a single shared Transformer encoder, and learns by predicting masked latent cardiac states, placing the pretraining target on shared physiology rather than sensor-specific waveform appearance. To handle the temporal offsets between electrical, mechanical, and hemodynamic events, cross-modal prediction uses a learned delay aligner that matches signals at the corresponding cardiac time. Because synchronized multi-sensor recordings are scarce, CardioState-JEPA first learns within-modality structure from abundant unimodal data and then uses paired data to align modalities in latent cardiac time. Evaluated as a frozen encoder across 25 downstream tasks spanning ECG, PPG, and PCG, our encoder improves average PPG classification by 8.2 AUROC points, PCG murmur detection by 18.8 AUROC points, and ECG classification by 15.5 AUROC points over the best self-supervised signal baseline and matches or exceeds cardiac models trained with privileged clinical text or supervised labels on several ECG benchmarks. These results establish that heterogeneous cardiac signals can mutually supervise a single foundation model of cardiac physiology.

cs.LG↗
arXiv2026

Symmetric Taylor--Hood elements for the linear stress gradient problem

We develop mixed finite element methods for the linear stress-gradient elasticity problem based on symmetric Taylor--Hood elements. We establish the stability of the symmetric Taylor--Hood pair on simplicial meshes in both two and three dimensions, thereby resolving the stability left open by Brezzi, Fortin, and Marini in 1993. Combing the Nitsche's method, we further construct finite element schemes for linear stress problem in general boundary condition. Numerical experiments confirm the theoretical results.

math.NA↗
arXiv2026

Vision-Based Tactile Intelligence for Robotics: Sensing, Learning, and Embodied Manipulation

Tactile sensing is essential for robots in contact-rich tasks, yet many tactile sensors still provide sparse, low-dimensional signals that do not capture sufficient information for complex robotic perception and interaction. Vision-based tactile sensors (VBTSs) offer a powerful alternative by con-verting contact-induced deformation of a soft interface into im-ages. The image-based formulation gives VBTSs high-resolution, information-rich tactile observations that enable complex robotic tasks. This review surveys the full VBTS pipeline and treats sensing hardware, learning methods, simulation, and datasets as an integrated sensing-and-learning system. We 1) organize representative VBTSs into a hardware taxonomy structured by deformable elastomer design, sensor size and shape, and optical system design to guide future sensor development; 2) present a hierarchical view of learning-based tactile intelligence from low-level signal understanding to task-level policies and foundation models; and 3) examine simulation platforms and tactile datasets as a scaling layer, together with sim-to-real transfer and cross-sensor adaptation for training, benchmarking, and deployment. Finally, we identify open challenges and future directions for VBTSs in robotics. By providing a holistic view of how hardware, AI architectures, simulation, and datasets interact, this review aims to advance tactile intelligence for contact-rich robotic tasks.

cs.RO↗
arXiv2026

Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification

Feature reconstruction techniques are widely applied for few-shot fine-grained image classification (FSFGIC). Our research indicates that one of the main challenges facing existing feature-based FSFGIC methods is how to choose the size of the receptive field to extract feature descriptors (including spatial and frequency feature descriptors) from different category input images, thereby better performing the FSFGIC tasks. To address this, an adaptive receptive field-based spatial-frequency feature reconstruction network (ARF-SFR-Net) is proposed. The designed ARF-SFR-Net has the capability to adaptively determine receptive field sizes for obtaining spatial and frequency features, and effectively fuse them for reconstruction and FSFGIC tasks. The designed ARF-SFR-Net can be easily embedded into a given episodic training mechanism for end-to-end training from scratch. Extensive experiments on multiple FSFGIC benchmarks demonstrate the effectiveness and superiority of the proposed ARF-SFR-Net over state-of-the-art approaches. The code is available at: https://github.com/ICL-SUST/ARF-SFR-Net.

cs.CV↗
arXiv2026

NodeImport: Imbalanced Node Classification with Node Importance Assessment

In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional GNNs often struggle in such scenarios, as they tend to overfit to majority classes while underrepresenting minority classes. Existing solutions, which either prioritize nodes based on class size or synthesize new nodes for minority classes, often fall short of effectively addressing this imbalance issue. This paper introduces an approach to class-imbalanced node classification by utilizing a balanced meta-set for importance measurement, where a training node is considered significant if it enhances model performance under an unbiased setting. Our method identifies important nodes that can counteract class imbalance and utilizes them for model training, allowing for fine-grained and dynamic node selection throughout the training process. We theoretically derive a formula to directly assess node importance, reducing computational overhead and providing an intuitive threshold for node selection. Guided by this metric, we develop a novel framework that filters valuable labeled, unlabeled, and synthetic nodes that enhance model performance in an unbiased context. A key advantage of this framework is its separation of the synthetic node generation process from the filtering process, ensuring compatibility with various node generation methods. Furthermore, we introduce a strategy to construct a high-quality meta-set that closely approximates the overall feature distribution, ensuring robust representation of each class. We evaluate our framework, NodeImport, across multiple datasets using popular GNN architectures, demonstrating its superiority over existing baselines. Our results highlight the flexibility and effectiveness of the framework in mitigating class imbalance, leading to improved outcomes.

cs.LG↗