Searcharxiv⌕ Search

arXiv subjects

Hu Xu

Publications and source records attributed to Hu Xu.

At least 19 recordsLinked to original sources
arXiv2026

Hyperspin Altermagnets

The behavior of spin quantum in k-space is key to identifying altermagnets (AMs) as the third kind of fundamental collinear magnetism. In contrast, non-collinear magnets,though abundant in nature,lack well-defined spin quantum numbers, and the resulting spin textures are often highly complex, which limits their potential for next-generation spintronic applications. Here we propose hyperspin, which lives in a higher-dimensional space, to address these drawbacks. Through analyzing the commutation relations between spin and Hamiltonian for a class of non-collinear magnets, we reveal it is a hyperspin, rather than the usual spin, that commutes with Hamiltonian. Unexpectedly, these non-collinear magnets should also show collinear spin-split bands in k-space like collinear AMs. We therefore classify such non-collinear magnets as hyperspin altermagnets (HAMs), as opposed to the usual collinear AMs. Our theory elucidates the fundamental physics of AMs and HAMs and provides a framework for exploring the wide range of non-collinear magnets that may possess other kinds of conserved quantities.

cond-mat.mtrl-sci↗
arXiv2026

Competing Extended-$s$- and $d$-Wave Pairing from Distinct Spin-Fluctuation Channels in Stoichiometric $\mathrm{FeTe}$

The recent observation of superconductivity in stoichiometric $\mathrm{FeTe}$ raises the question of how pairing develops in this tetragonal 11-type chalcogenide once interstitial Fe is removed. We construct an experimentally constrained five-orbital tight-binding model from first-principles calculations and treat electronic correlations and pairing within the fluctuation-exchange approximation. The linearized Eliashberg equation yields competing extended-$s$- and $d_{x^2-y^2}$-wave spin-singlet pairing instabilities. Near stoichiometric filling, spin fluctuations near $(\pi,0)$ and $(0,\pi)$ in the unfolded one-Fe Brillouin zone connect the $\Gamma/M$ hole pockets with the $X/Y$ electron pockets and favor an extended-$s$ gap that changes sign between the hole and electron sheets. Upon electron doping, depletion of the hole pockets shifts the dominant scattering toward the $X$--$Y$ channel near $(\pi,\pi)$, making the $d_{x^2-y^2}$-wave state the leading instability, with nodal lines that avoid most of the Fermi surface. The relative strengths of the two pairing channels vary with filling and interaction strength as the dominant spin-fluctuation channel changes. Under matched interaction strength, temperature, and filling, the extended-$s$ eigenvalue is larger in $\mathrm{FeTe}$ than in $\mathrm{FeSe}$ throughout the range considered, while the $d_{x^2-y^2}$-wave eigenvalue is also generally larger, particularly under electron doping. These results give concrete gap structures against which spectroscopic measurements of stoichiometric $\mathrm{FeTe}$ can be compared.

cond-mat.supr-con↗
arXiv2026

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark

In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual diversity needed to handle open-ended visual inputs. We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs). We build a taxonomy of thousands of visual concepts across multiple domains (e.g., living things). Guided by this taxonomy, we curate a broad collection of images from search engines and existing datasets to comprehensively represent the visual world. Through structured trial-and-error, we manually design challenging questions that frontier MLLMs fail to answer. On quantitative and human evaluations, WorldBench achieves higher visual diversity than any existing diverse benchmark. Evaluating 15 MLLMs on WorldBench reveals weaknesses in visual understanding: even the strongest model reaches only 64.0% accuracy, while some models perform marginally above chance-level. We hope our work highlights the importance of visual diversity in building multimodal benchmarks.

cs.CV↗
arXiv2026

Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning

Calibration data are often treated as a minor implementation detail in post-training LLM pruning because averaged evaluations suggest only modest effects. We show that this conclusion is an averaging artifact: at 60\% SparseGPT sparsity, calibration strategies separated by only 2.85 points in averaged commonsense accuracy differ by 51.9 points in Code retention. Across 15 sources, capability-decomposed analysis reveals an opposing pattern: calibration perplexity is positively associated with General retention but negatively associated with Math or Code retention, leaving no evaluated single source uniformly strong across capabilities. This finding motivates capability-balanced multi-source calibration. Under the same calibration budget, a balanced real-data mixture outperforms every evaluated single source on LLaMA-3.1-8B, beating C4 by 18.8 points; the advantage grows with sparsity and persists on LLaMA-3.1-70B. Because the original pretraining data of advanced LLMs are often inaccessible, we further introduce Information-Guided Self-Calibration for Pruning (IGSP). Using only the base model and evaluation taxonomy, IGSP generates capability-stratified pools and selects low-redundancy samples within capability-specific perplexity ranges, outperforming Self-Cal and SGS by up to 4.8 points. Together, these results recast calibration as a capability-coverage problem and identify multi-source design as a practical principle for preserving capabilities in high-sparsity LLM pruning.

cs.LG↗
arXiv2026

Cambrian-P: Pose-Grounded Video Understanding

Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is largely absent from multimodal LLMs (MLLMs) for video understanding, which process frames as isolated 2D snapshots, instead of the persistent scene humans perceive. We revisit pose as a lightweight supervisory signal and introduce Cambrian-P, a video MLLM augmented with per-frame learnable camera tokens and a pose regression head. With a carefully designed sampling scheme, the model achieves substantial gains of 4.5-6.5% on spatial reasoning benchmarks such as VSI-Bench, generalizes across eight additional spatial and general video QA benchmarks, and, as a byproduct, achieves state of the art streaming pose estimation on ScanNet. Surprisingly, training on pseudo-annotated poses from in-the-wild video further improves general video QA benchmarks, showing pose helps beyond spatial reasoning. Together, these results position camera pose as a fundamental signal for video models that reason about the physical world.

cs.CV↗
arXiv2026

OceanBase Bacchus: a High-Performance and Scalable Cloud-Native Shared Storage Architecture for Multi-Cloud

Although an increasing number of databases now embrace shared-storage architectures, current storage-disaggregated systems have yet to strike an optimal balance between cost and performance. In high-concurrency read/write scenarios, B+-tree-based shared storage struggles to efficiently absorb frequent in-place updates. Existing LSM-tree-backed disaggregated storage designs are hindered by the intricate implementation of cross-node shared-log mechanisms, where no satisfactory solution yet exists. This paper presents OceanBase Bacchus, an LSM-tree architecture tailored for object storage provided by cloud vendors. The system sustains high-performance reads and writes while rendering compute nodes stateless through shared service-oriented PALF (Paxos-backed Append-only Log File system) logging and asynchronous background services. We employ a Shared Block Cache Service to flexibly utilize cache resources. Our design places log synchronization into a shared service, providing a novel solution for log sharing in storage-compute-separated databases. The architecture decouples functionality across modules, enabling elastic scaling where compute, cache, and storage resources can be resized rapidly and independently. Through experimental evaluation using multiple benchmark tests, including SysBench and TPC-H, we confirm that OceanBase Bacchus achieves performance comparable to or superior to that of HBase in OLTP scenarios and significantly outperforms StarRocks in OLAP workloads. Leveraging Bacchus's support for multi-cloud deployment and consistent performance, we not only retain high availability and competitive performance but also achieve substantial reductions in storage costs by 59% in OLTP scenarios and 89% in OLAP scenarios.

cs.DB↗
arXiv2026

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by ~3.3x, e.g., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.

cs.CV↗
arXiv2025

In Pursuit of Pixel Supervision for Visual Pre-training

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attributes to high-level concepts. Autoencoders represent a classical and long-standing paradigm for learning representations from pixels or other raw inputs. In this work, we demonstrate that autoencoder-based self-supervised learning remains competitive today and can produce strong representations for downstream tasks, while remaining simple, stable, and efficient. Our model, codenamed "Pixio", is an enhanced masked autoencoder (MAE) with more challenging pre-training tasks and more capable architectures. The model is trained on 2B web-crawled images with a self-curation strategy with minimal human curation. Pixio performs competitively across a wide range of downstream tasks in the wild, including monocular depth estimation (e.g., Depth Anything), feed-forward 3D reconstruction (i.e., MapAnything), semantic segmentation, and robot learning, outperforming or matching DINOv3 trained at similar scales. Our results suggest that pixel-space self-supervised learning can serve as a promising alternative and a complement to latent-space approaches.

cs.CV↗
arXiv2025

Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework

Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where specialized agents collaborate to produce data that is higher quality, more diverse, and structurally richer. However, existing frameworks for multi-agent synthesis often depend on a centralized orchestrator, creating scalability bottlenecks, or are hardcoded for specific domains, limiting flexibility. We present \textbf{Matrix}, a decentralized framework that represents both control and data flow as serialized messages passed through distributed queues. This peer-to-peer design eliminates the central orchestrator. Each task progresses independently through lightweight agents, while compute-intensive operations, such as LLM inference or containerized environments, are handled by distributed services. Built on Ray, Matrix scales to tens of thousands of concurrent agentic workflows and provides a modular, configurable design that enables easy adaptation to a wide range of data generation workflows. We evaluate Matrix across diverse synthesis scenarios, such as multi-agent collaborative dialogue, web-based reasoning data extraction, and tool-use trajectory generation in customer service environments. In all cases, Matrix achieves $2$--$15\times$ higher data generation throughput under identical hardware resources, without compromising output quality.

cs.CL↗
arXiv2025

DepthLM: Metric Depth From Vision Language Models

Vision language models (VLMs) can flexibly address various vision tasks through text interactions. Although successful in semantic understanding, state-of-the-art VLMs including GPT-5 still struggle in understanding 3D from 2D inputs. On the other hand, expert pure vision models achieve super-human accuracy in metric depth estimation, a key 3D understanding task. However, they require task-specific architectures and losses. Such difference motivates us to ask: Can VLMs reach expert-level accuracy without architecture or loss change? We take per-pixel metric depth estimation as the representative task and show that the answer is yes! Surprisingly, comprehensive analysis shows that text-based supervised-finetuning with sparse labels is sufficient for VLMs to unlock strong 3D understanding, no dense prediction head or complex regression/regularization loss is needed. The bottleneck for VLMs lies actually in pixel reference and cross-dataset camera ambiguity, which we address through visual prompting and intrinsic-conditioned augmentation. With much smaller models, our method DepthLM surpasses the accuracy of most advanced VLMs by over 2x, making VLMs for the first time comparable with pure vision models. Interestingly, without explicit enforcement during training, VLMs trained with DepthLM naturally avoids over-smoothing, having much fewer flying points at boundary regions than pure vision models. The simplicity of DepthLM also enables a single VLM to cover various 3D tasks beyond metric depth. Our code and model will be released at the link below.

cs.CV↗
arXiv2025

Meta CLIP 2: A Worldwide Scaling Recipe

Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (MLLMs). Although CLIP is successfully trained on billion-scale image-text pairs from the English world, scaling CLIP's training further to learning from the worldwide web data is still challenging: (1) no curation method is available to handle data points from non-English world; (2) the English performance from existing multilingual CLIP is worse than its English-only counterpart, i.e., "curse of multilinguality" that is common in LLMs. Here, we present Meta CLIP 2, the first recipe training CLIP from scratch on worldwide web-scale image-text pairs. To generalize our findings, we conduct rigorous ablations with minimal changes that are necessary to address the above challenges and present a recipe enabling mutual benefits from English and non-English world data. In zero-shot ImageNet classification, Meta CLIP 2 ViT-H/14 surpasses its English-only counterpart by 0.8% and mSigLIP by 0.7%, and surprisingly sets new state-of-the-art without system-level confounding factors (e.g., translation, bespoke architecture changes) on multilingual benchmarks, such as CVQA with 57.4%, Babel-ImageNet with 50.2% and XM3600 with 64.3% on image-to-text retrieval.

cs.CV↗
arXiv2025

Multicolor groups for molecules and solids

The local magnetic moments of atoms in a molecule or solid can be designated by different colors. Magnetic groups, or 2-color groups, or black-and-white groups have been applied in crystallography to classify different magnets. Despite its successes in the past decades, the recent advents of altermagnets and p-wave magnets raise new challenges to this long-standing framework, which urges for a new and unified one. Here we develop a multicolor group classification framework to classify all kinds of molecules and solids, including nonmagnetic materials and magnets with collinear or non-collinear magnetism, and with or without spin-orbit couplings (SOC). This new scheme can unify the classifications of matters into a single framework, including the recently identified altermagnets and p-wave magnets. Especially, altermagnetic topological matters and p-wave magnets with SOC, can also be diagnosed with multicolor groups, a task which can not be accomplished by magnetic space groups and spin space groups. Moreover, insufficiencies and misconceptions of conventional magnetic group classification can be supplemented through this new framework. Multicolor group will serve as a new stage in the symmetry classification of matters.

cond-mat.mtrl-sci↗
arXiv2025

GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis

Generative models based on deep learning have shown significant potential in medical imaging, particularly for modality transformation and multimodal fusion in MRI-based brain imaging. This study introduces GM-LDM, a novel framework that leverages the latent diffusion model (LDM) to enhance the efficiency and precision of MRI generation tasks. GM-LDM integrates a 3D autoencoder, pre-trained on the large-scale ABCD MRI dataset, achieving statistical consistency through KL divergence loss. We employ a Vision Transformer (ViT)-based encoder-decoder as the denoising network to optimize generation quality. The framework flexibly incorporates conditional data, such as functional network connectivity (FNC) data, enabling personalized brain imaging, biomarker identification, and functional-to-structural information translation for brain diseases like schizophrenia.

eess.IV↗
arXiv2025

Perception Encoder: The best visual embeddings are not at the output of the network

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each tailored to specific downstream tasks such as classification, captioning, or localization. Surprisingly, after scaling our carefully tuned image pretraining recipe and refining with our robust video data engine, we find that contrastive vision-language training alone can produce strong, general embeddings for all of these downstream tasks. There is only one caveat: these embeddings are hidden within the intermediate layers of the network. To draw them out, we introduce two alignment methods: language alignment for multimodal language modeling, and spatial alignment for dense prediction. Together, our PE family of models achieves best-in-class results on a wide variety of tasks, including (1) zero-shot image and video classification and retrieval, simultaneously obtaining 86.6 average zero-shot ImageNet robustness and 76.9 zero-shot Kinetics-400 video classification; (2) document, image, and video Q&A, enabling 94.6 DocVQA, 80.9 InfographicVQA, and 82.7 PerceptionTest with an 8B LLM; and (3) spatial tasks such as detection, tracking, and depth estimation, setting a new COCO state-of-the-art of 66.0 box mAP. To foster further research, we release our models, code, and novel dataset of synthetically and human-annotated videos: https://github.com/facebookresearch/perception_models

cs.CV↗
arXiv2025

Modeling and computation of the effective elastic behavior of parallelogram origami metamaterials

Origami metamaterials made of repeating unit cells of parallelogram panels joined at folds dramatically change their shape through a collective motion of their cells. Here we develop an effective elastic model and numerical method to study the large deformation response of these metamaterials under a broad class of loads. The model builds on an effective plate theory derived in our prior work [64]. The theory captures the overall shape change of all slightly stressed parallelogram origami deformations through nonlinear geometric compatibility constraints that couple the origami's (cell averaged) effective deformation to an auxiliary angle field quantifying its cell-by-cell actuation. It also assigns to each such origami deformation a plate energy associated to these effective fields. Seeking a constitutive model that is faithful to the theory but also practical to simulate, we relax the geometric constraints via corresponding elastic energy penalties; we also simplify the plate energy density to embrace its essential character as a regularization to the geometric penalties. The resulting model for parallelogram origami is a generalized elastic continuum that is nonlinear in the effective deformation gradient and angle field and regularized by high-order gradients thereof. We provide a finite element formulation of this model using the $C^0$ interior penalty method to handle second gradients of deformation, and implement it using the open source computing platform Firedrake. We end by using the model and numerical method to study two canonical parallelogram origami patterns, in Miura and Eggbox origami, under a variety of loading conditions.

cond-mat.soft↗
arXiv2025

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through context ablation: If a citation is necessary, removing the cited text from the context should prevent the same response; if sufficient, retaining the cited text alone should preserve the same response. This reward can guide the inference-time best-of-N sampling strategy to improve citation quality significantly, as well as be used in preference optimization to directly fine-tune the models for generating better citations. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks. The source code is available at https://github.com/facebookresearch/SelfCite

cs.CL↗
arXiv2025

General Information Metrics for Improving AI Model Training Efficiency

To address the growing size of AI model training data and the lack of a universal data selection methodology-factors that significantly drive up training costs -- this paper presents the General Information Metrics Evaluation (GIME) method. GIME leverages general information metrics from Objective Information Theory (OIT), including volume, delay, scope, granularity, variety, duration, sampling rate, aggregation, coverage, distortion, and mismatch to optimize dataset selection for training purposes. Comprehensive experiments conducted across diverse domains, such as CTR Prediction, Civil Case Prediction, and Weather Forecasting, demonstrate that GIME effectively preserves model performance while substantially reducing both training time and costs. Additionally, applying GIME within the Judicial AI Program led to a remarkable 39.56% reduction in total model training expenses, underscoring its potential to support efficient and sustainable AI development.

cs.LG↗
arXiv2024

Entropy-driven electron density and effective model Hamiltonian for boron systems

The unique electron deficiency of boron makes it challenging to determine the stable structures, leading to a wide variety of forms. In this work, we introduce a statistical model based on grand canonical ensemble theory that incorporates the octet rule to determine electron density in boron systems. This parameter-free model, referred to as the bonding free energy (BFE) model, aligns well with first-principles calculations and accurately predicts total energies. For borane clusters, the model successfully predicts isomer energies, hydrogen diffusion pathways, and optimal charge quantity for closo-boranes. In all-boron clusters, the absence of B-H bond constraints enables increased electron delocalization and flexibility. The BFE model systematically explains the geometric structures and chemical bonding in boron clusters, revealing variations in electron density that clarify their structural diversity. For borophene, the BFE model predicts that hexagonal vacancy distributions are influenced by bonding entropy, with uniform electron density enhancing stability. Notably, our model predicts borophenes with a vacancy concentration of 1 6 to exhibit increased stability with long-range periodicity. Therefore, the BFE model serves as a practical criterion for structure prediction, providing essential insights into the stability and physical properties of boron-based systems.

cond-mat.mtrl-sci↗