arXiv subjects

Di Zhang

Publications and source records attributed to Di Zhang.

At least 19 recordsLinked to original sources

arXiv2026

On the anisotropic mean curvature flow in the Gaussian space

In this paper, we study the anisotropic mean curvature flow in the Gaussian space endowed with a Finsler metric obtained from a Minkowski metric by a conformal deformation. We first derive the conformal transformation formulas for the fundamental tensor, the Cartan tensor, and the Chern connection of the conformally related Finsler metrics. Based on these formulas, we express the anisotropic mean curvature in the Gaussian space in terms of the corresponding anisotropic mean curvature with respect to the original Minkowski metric, and derive the associated evolution equation. Finally, we establish the short-time existence and uniqueness of smooth solutions by reformulating the geometric evolution equation as a strictly parabolic quasilinear partial differential equation.

math.DG↗

arXiv2026

Spin State versus Potential of Zero Charge as Predictors of Density-Dependent Oxygen Reduction in M-N-C Electrocatalysts

Metal-site density strongly influences oxygen reduction activity and selectivity in M-N-C electrocatalysts, but the descriptors that predict these trends remain under debate. Here, we compare spin state and the potential of zero charge (PZC) as predictors of density-dependent oxygen reduction behavior in Fe-N-C and Co-N-C catalysts. Using constrained-magnetization calculations combined with Landau analysis, we find that the ground-state magnetic moments vary only weakly across a broad range of metal-site densities, suggesting that magnetic descriptors alone cannot account for the pronounced performance changes. In contrast, explicit-solvent simulations reveal systematic density-dependent shifts in PZC, which alter the interfacial electric field and thereby modulate field-sensitive adsorption energetics of ORR intermediates. Incorporating these PZC shifts into a pH-field-coupled microkinetic model captures the density-dependent activity trends and reproduces the experimentally observed increase in two-electron selectivity at lower site densities under acidic conditions. Experimental PZC measurements further support the predicted trend. Within the investigated Co-N-C and Fe-N-C series, PZC-dependent electrostatics consistently rationalize the density-dependent ORR trends, whereas the examined magnetic descriptors show comparatively weak variation.

cond-mat.mtrl-sci↗

arXiv2026

Position: Next-Generation Game Engines Should Be Built on Interactive Generative Video

Modern game development faces significant challenges in creativity and cost due to predetermined content in traditional game engines. Recent breakthroughs in video generation models, capable of synthesizing realistic and interactive virtual environments, present an opportunity to revolutionize game creation. This position paper argues that next-generation game engines should be built on Interactive Generative Video (IGV). We term such engines Generative Game Engines (GGE), with IGV as the perceptual and world-generation core under designer control. We argue why IGV is uniquely suited for this role, identify what is missing, and examine progress across six functional modules to show how each supports our position, culminating in a five-level maturity roadmap (L0-L4). Drawing on discussions with researchers, game developers, and community participants, we present nine alternative views and ethical considerations to stimulate debate.

cs.CV↗

arXiv2026

GSHeadRelight: Fast Relightability for 3D Gaussian Head Synthesis

Relighting and novel view synthesis of human portraits are essential in applications such as portrait photography, virtual reality (VR), and augmented reality (AR). Despite recent progress, 3D-aware portrait relighting remains challenging due to the demands for photorealistic rendering, real-time performance, and generalization to unseen subjects. Existing works either rely on supervision from limited and expensive light stage captured data or produce suboptimal results. Moreover, many works are based on generative NeRFs, which suffer from poor 3D consistency and low real-time performance. We resort to recent progress on generative 3D Gaussians and design a lighting model based on a unified neural radiance transfer representation, which responds linearly to incident light. Using only in-the-wild images, our method achieves state-of-the-art relighting results and a significantly faster rendering speed ($\times12$) compared to previous 3D-aware portrait relighting research. Project page: http://www.geometrylearning.com/GSHeadRelight/.

cs.CV↗

arXiv2026

Robust Anomalous Hall Effect in Epitaxial Cubic D0$_3$-Fe$_3$Ge Nanoplates Grown by Chemical Vapor Deposition

The iron-based ferromagnetic materials have emerged as a promising system for spintronics due to their high Curie temperatures and significant anomalous Hall effect (AHE) driven by Berry curvature. While there have been investigations into the epitaxial growth of non-layered iron-based ferromagnetic materials, the realization of high-quality single crystal thin films continues to be a formidable obstacle. Meanwhile, the issues such as grain boundary scattering further hinder their characterization and application. Here, we report the first chemical vapor deposition (CVD) synthesis of single-crystalline cubic D0$_3$-Fe$_3$Ge nanoplates. This compound represents a substantial departure from the conventional hexagonal phases typically observed in the Fe-Ge system. Structural characterizations confirm the cubic lattice and stoichiometric purity of the crystals. Structural analysis identifies a strong epitaxial effect, resulting in a giant compressive strain of ~4.16% at the interface that relaxes gradually toward the surface. The second-harmonic generation (SHG) signals might further reveal that such interfacial strain disrupted the inherent centro-symmetry of the cubic phase. SQUID magnetometry shows robust room-temperature ferromagnetism and clear magnetic anisotropy. Magneto-transport measurements reveal a robust AHE that remains stable at temperatures far exceeding room temperature. The scaling observed between the anomalous Hall resistance and longitudinal resistance strongly suggests that this effect is dominated by the intrinsic Berry curvature mechanism. Furthermore, density functional theory (DFT) calculations reveal that the huge epitaxial strain induces band reconstructions and creates dense spin-orbit coupling gaps near the Fermi level, effectively doubling the anomalous Hall conductivity to match our experimental observations.

cond-mat.mtrl-sci↗

arXiv2026

RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer

A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answers to the same questions with records of how generation ends. Across five open-weight deployments and nine strategies, aggregate accuracy hides substantial question-level gains and harms; a common-budget MATH500 evaluation examines transfer on a separate sample. On 60 additional questions, concise reasoning improves Phi's automatic answer matching at a 2,048-token cap across three collections, but sharply reduces Qwen's. Author-reviewed final-answer commitments give a smaller, statistically unresolved Phi gain. Reserving an answer stage also improves matching, with additional input and call costs. These results show why a prompt benefit must be interpreted alongside its execution and evaluation: matching a reference answer need not mean delivering it, and an apparent compression benefit may admit another explanation. RCCM records this evidence for reproducible transfer comparisons.

cs.CL↗

arXiv2026

PlanPath: Exploration-Guided Orchestration for Patient-Level Pathology Reasoning

A patient's pathology case spans tens of slides from distinct specimens and anatomical sites, each carrying non-redundant, site-specific evidence. Forming a patient-level conclusion therefore requires locating the slides relevant to a given question and integrating complementary findings across them. However, existing pathology agents analyze one slide at a time and describe morphology rather than measure it, leaving evidence acquisition across a patient's specimens and patient-level quantification underexplored. To address this gap, we propose PlanPath, an agentic framework for patient-level pathology visual question answering (VQA). PlanPath turns the question into an exploration plan that specifies the evidence required, routes to the slides likely to carry it, and drives coarse-to-fine acquisition from tissue architecture down to individual cells. Tissue- and cell-level tools supply the counts, proportions, and extents, which PlanPath aggregates across slides into a traceable answer. To enable evaluation, we build two patient-level VQA datasets for renal and gastric cancer, averaging 15 WSIs per patient, with pathologist-verified question-answer pairs derived from diagnostic reports. Experimental results show that PlanPath outperforms the strongest baseline by 9.4% and 12.1% in overall accuracy on the two datasets and further improves existing slide-level agents when plugged into our framework. The dataset and code are available at: https://github.com/JSGe-AI/PlanPath_1.

cs.CV↗

arXiv2026

On the Multi-Weight Shift-Sum Iterative Decoding of Short BCH Codes

This paper investigates a shift-sum decoding algorithm that employs dual codewords. Existing dual codeword shift-sum decoding schemes mainly rely on minimum-weight dual codewords. However, the number of such codewords is often limited, which restricts the amount of reliability information available to the decoder. To address this issue, we extend the component counting mechanism from minimum-weight dual codewords to dual codewords whose Hamming weights lie within a prescribed upper bound. We further introduce a normalized component counting rule to suppress the overcounting bias caused by the much larger populations of higher-weight classes. Based on this framework, we develop a hard-decision iterative error reduction decoder and a soft information-aided iterative error reduction decoder. Numerical results show that the proposed method consistently outperforms existing minimum-weight shift-sum baselines especially for short codes where additional dual codeword information is particularly valuable.

cs.IT↗

arXiv2026

Visually Legible but Adversarial: Watermark-Constrained Attacks on End-to-End VLMs for Document Understanding

Visible watermarks convey document ownership, confidentiality, and status, but can also carry adversarial signals. We introduce Auto-Regional Adversarial Watermarking (AR-AWM), a model-aware white-box attack on end-to-end visual language models (VLMs) for document understanding. AR-AWM constructs a small, spatially distributed watermark-text support and optimizes only its pixels to disrupt visual representations. The attack is untargeted and question-agnostic: generation uses no questions, answers, parsing prompts, language-model gradients, or language-model outputs. Each attacked page is reused across downstream queries. On Qwen2.5-VL-7B, a watermark support covering 7.98% of page pixels under the reporting threshold reduces DocVQA exact match from 0.899 to 0.150 and average normalized Levenshtein similarity (ANLS) from 0.939 to 0.212. Selected qualitative cases retain visually legible source fields. The same support without optimization and with matched random perturbations retains ANLS of 0.932 and 0.933, respectively, identifying adversarial optimization as the primary cause of degradation. Layout-matched optimized rectangles yield ANLS of 0.276, showing an incremental benefit from text-shaped geometry. AR-AWM also degrades all reported text, formula, reading-order, and table metrics on OmniDocBench. Separate white-box optimization on InternVL2.5-8B reduces ANLS from 0.922 to 0.046, while weak cross-model transfer reveals strong encoder specificity. These results identify conventional watermark-shaped supports as an adversarial surface for document VLMs in the evaluated white-box setting.luated white-box setting.

cs.CV↗

arXiv2026

Associativity of discretized triangular norms

In this article, we mainly investigate when the binary operation $T^{[n]}:[0, 1]^2\rightarrow [0, 1]$ satisfies the associative law and thus becomes a triangular norm where \begin{equation*} T^{[n]}(x,y)=\left\{\begin{array}{ll} f_{n}(T(f_{n}(x),f_{n}(y))), &\text{if}\,\, (x,y)\in{[0,1)^{2}}, \\ \min\{x,y\}, &\text{otherwise,} \end{array}\right. \end{equation*} $f_{n}:[0,1]\rightarrow\left\{0, \frac{1}{n}, \frac{2}{n}, \dots, \frac{n-1}{n}, 1\right\}$ given by $f_{n}(x)=\frac{1}{n}{\lfloor nx \rfloor}$ with $n$ a positive integer and $T:[0, 1]^2\rightarrow [0, 1]$ is a triangular norm. We present some sufficient conditions for $T^{[n]}$ to be triangular norms, and for $T^{[n]}$ to be never associative when $T$ is strictly monotonic.

math.GM↗

arXiv2026

Diagonalizable modular derivations on bigraded Poisson spaces and Koszul duality

For two bigraded spaces $k^{m||n}$ and $k^{n\wedge m}$ equipped with appropriate quadratic Poisson structures, Koszul duality identifies the mixed Poisson differential calculi and, in the unimodular case, their Poisson cohomologies as Batalin--Vilkovisky algebras. In the current paper we prove that Koszul duality induces an isomorphism of Batalin--Vilkovisky algebras between their Poisson cohomologies when the modular derivation of one algebra is diagonalizable, including non-unimodular cases.

math.RA↗

arXiv2026

Topological Hall Effect Induced by Chiral Spin Textures at the Ferroelectric/Ferromagnetic Interface

Chiral spin textures, largely driven by the Dzyaloshinskii-Moriya interaction, offer significant potential for next-generation computing technologies due to their chirality and topological stability. Ferroelectric/ferromagnetic van der Waals heterostructures are particularly appealing because they can combine interfacial inversion-symmetry breaking and spin-orbit coupling to promote interfacial Dzyaloshinskii-Moriya interaction, while switchable ferroelectric polarization provides a nonvolatile tuning knob. This study investigates interfacial chiral spin textures in few-layer Fe$_3$GeTe$_2$/$α$-In$_2$Se$_3$ heterostructures. Two groups of topological Hall signals are identified just below and above the coercive field, and thickness-dependent transport reveals a notable reduction in critical temperature with increasing Fe$_3$GeTe$_2$ layer thickness. Low-temperature magnetic force microscopy images reveal two types of magnetic bubbles with opposite magnetic contrasts near the coercive field, each associated with distinct topological Hall signals. Together with atomistic spin-dynamics simulations and first-principles calculations, these results support the formation of interfacial DMI-stabilized chiral spin textures. Switching the ferroelectric polarization of the $α$-In$_2$Se$_3$ layer further enables nonvolatile modulation of both anomalous and topological Hall effects. The resulting ferroelectric and magnetic bistabilities generate four distinguishable Hall resistance states programmable by electric and magnetic fields. These findings highlight the potential of van der Waals interfaces for advanced device applications.

cond-mat.mtrl-sci↗

arXiv2026

Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics

In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rule update can be interpreted as an explicit Euler discretization of an underlying continuous-time system. EFLA replaces this first-order update with the exact closed-form flow. By exploiting the rank-1 structure of the dynamics matrix, both the matrix exponential and the input integral collapse to a simple update that preserves delta-rule linear attention's algebraic structure, parameter count, linear-time complexity, and chunkwise parallelism. This attention mechanism removes the Euler discretization error of the delta-rule dynamics without introducing additional parameters. Experiments on robustness tests, language modeling benchmarks, and the MAD synthetic benchmark show that EFLA improves stability under corrupted and high-energy inputs, reduces perplexity, and achieves stronger downstream performance compared to SSM and Euler-style baselines. These results establish exact-flow integration as a principled and scalable update mechanism for delta-rule linear attention.

cs.LG↗

arXiv2026

$δ$-mem: Efficient Online Memory for Large Language Models

Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization. We propose $δ$-mem, a lightweight memory mechanism that augments a frozen full-attention backbone with a compact online state of associative memory. $δ$-mem compresses past information into a fixed-size state matrix updated by delta-rule learning, and uses its readout to generate low-rank corrections to the backbone's attention computation during generation. With only an $8\times8$ online memory state, $δ$-mem improves the average score to $1.10\times$ that of the frozen backbone and $1.15\times$ that of the strongest non-$δ$-mem memory baseline. It achieves larger gains on memory-heavy benchmarks, reaching $1.31\times$ on MemoryAgentBench and $1.20\times$ on LoCoMo, while largely preserving general capabilities. These results show that effective memory can be realized through a compact online state directly coupled with attention computation, without full fine-tuning, backbone replacement, or explicit context extension.

cs.AI↗

arXiv2026

Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields

Due to the gigapixel-scale nature of whole-slide images (WSIs), weakly supervised WSI analysis is commonly formulated as a multiple instance learning (MIL) problem, where patch-level features are aggregated into slide-level representations. However, diagnostic and prognostic evidence often arises from spatially coherent tumor microenvironment regions and their interactions, rather than isolated patches alone. Existing patch-level or static region-based methods usually overlook how tissue regions should be adaptively formed and subsequently evolved through microenvironment interactions across heterogeneous boundaries. In this paper, we propose Concept-Guided Tumor Microenvironment Evolution (TMEvolve), a reaction-diffusion-inspired framework that models WSIs as latent tumor microenvironment fields over discrete patch graphs. TMEvolve instantiates this view as a learnable graph-discretized evolution process over patch neighborhoods. It first forms adaptive soft tissue regions as coherent microenvironment units, then performs pseudo-time evolution through two complementary local dynamics: intra-region diffusion, which stabilizes latent states within coherent tissue compartments, and concept-guided boundary flux, which propagates visual feature signals and language-derived concept signals across heterogeneous region interfaces. The evolved microenvironment regions are finally aggregated for slide-level prediction. We evaluate TMEvolve on six datasets across three weakly supervised WSI tasks: survival prediction, gene expression prediction, and histological subtype classification. TMEvolve consistently improves over representative MIL methods, pathology foundation models, and concept-guided baselines. Ablation studies and visualizations further support the effectiveness and interpretability of TMEvolve, highlighting the value of dynamic region modeling and boundary interaction.

cs.CV↗

arXiv2026

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost by pruning redundant visual tokens, but permanently discard visual evidence that may become useful in subsequent layers. We instead ask whether all visual tokens can be preserved while reducing the cost of repeatedly evolving the representations through the Transformer. To answer this question, we perform low-rank interventions on visual-to-text information flow. We find that, after visual-to-text attention is blocked, restoring only a few directions recovers most of the lost accuracy, suggesting the relevant visual influence is concentrated in a low-dimensional subspace. We further observe strong predictability in layer-specific visual states: lightweight MLPs approximate them with high cosine similarity and low reconstruction error. Motivated by these findings, we propose $δ$-Vision, which replaces repeated Transformer evolution of visual tokens with lightweight low-rank adapters that construct layer-wise visual memories while preserving all visual tokens for text retrieval. Across image and video benchmarks, $δ$-Vision achieves higher accuracy than visual token pruning baselines at comparable or lower computation, while delivering competitive inference efficiency without discarding visual tokens.

cs.CV↗

arXiv2026

Learning Geometrically-Grounded Amodal 3D Representations for View-Generalizable Robotic Manipulation

Real-world robotic manipulation requires visuomotor policies capable of robust 3D scene reasoning under varying camera viewpoints. While recent 3D-aware manipulation policies have shown promise, they still face several limitations: (i) reliance on multi-view observations during inference, which is impractical in camera-constrained deployments; (ii) insufficient geometric fidelity in learned representations, limiting precise and viewpoint-robust control; and (iii) the lack of effective mechanisms for transferring pretrained 3D representations to downstream visuomotor policies. To address these challenges, we present GEM3D (Geometrically-Grounded 3D Manipulation), a unified 3D representation and policy learning framework for view-generalizable robotic manipulation. GEM3D learns amodal 3D representations from single-view RGB-D observations by jointly enforcing point-cloud reconstruction and Gaussian-splatting-based novel-view consistency during pretraining. A multi-step distillation strategy then transfers the learned geometric understanding into a deployable single-view visuomotor policy for downstream manipulation control. Experiments on 12 RLBench tasks and three real-world tasks demonstrate strong manipulation performance. Further zero-shot evaluations on eight RLBench tasks and the real-world tasks show robust generalization to unseen camera poses and substantial gains over existing methods.

cs.RO↗

arXiv2026

Can Protein-Derived Knowledge Improve Pathology Foundation Models?

Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations, yet effectively leveraging large standalone molecular corpora remains challenging. First, existing molecular foundation models encode protein sequences or single-cell states, not the patient-level bulk expression profiles paired with WSIs. Second, because cross-modal supervision is restricted to paired WSI-omics samples, knowledge from standalone molecular corpora reaches the pathology encoder only indirectly, creating a paired-support bottleneck. To address these challenges, we propose a three-stage framework that decouples proteomic knowledge acquisition from cross-modal transfer, yielding ProSlide, a slide-level hierarchical pathology foundation model. First, to close the modality gap, we pretrain a Proteomic Foundation Encoder (PFE) on 12,695 sample-level bulk protein profiles using virtual profile generation and expression-space multi-view pretraining. Second, we pretrain ProSlide, a patch-region-slide encoder, to predict protein expression from paired WSI-protein samples. Third, to relax the paired-support bottleneck, we introduce Prot2Path, a cross-modal relational distillation objective. For each paired sample, it aligns the similarity distributions of the WSI and its protein profile over a shared, frozen bank of PFE-encoded paired and standalone profiles. We evaluate ProSlide on 12 downstream tasks across breast, lung, and renal cancers. Despite being pretrained with only 2,229 WSIs and 12,695 sample-level protein profiles, ProSlide achieves the highest mean accuracy and AUC within each cancer group.

cs.CV↗