Machine Learning
MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation
Pengfei Li and Mohammad Khalil
This paper proposes MIND, a marginal-invariant neural dependency
diffusion model for mixed-type tabular data. MIND does not directly learn the joint distribution in the original heterogeneous feature space. Instead, it first maps different variable types into a unified latent dependency space via column-wise marginal transport. A conditional
diffusion model then learns cross-column relationships. Copula-tangent denoising separates known marginal components from learnable dependency residuals. Rank projection during the sampling phase further mitigates marginal shift in reverse
diffusion. Experiments across nine diverse tabular
benchmarks show that MIND consistently improves marginal fidelity and dependency preservation over existing unified approaches. By explicitly isolating marginal modelling from dependency learning, MIND achieves a strong and stable balance among marginal fidelity, joint dependency preservation, and downstream prediction utility. This work supports separating marginal and dependency modelling as a principled and highly effective paradigm for complex mixed-type tabular generation.
Read the full abstract ▾
Computer Vision
Introduction to Computer Vision
Stan Birchfield
This book presents a code-first introduction to computer
vision, spanning classical 2D image processing, classical 3D
vision, and deep learning. Organized as 44 short chapters across three parts, the book builds each topic from first principles: image arithmetic and morphology; convolution, pyramids, and frequency-domain filtering; feature detection, optical flow, and stereo; projective geometry, camera calibration, and structure from motion; and the full arc of modern deep learning, from a single
neuron through convolutional networks, backpropagation, classic architectures, transfer learning, object detection, and semantic and instance
segmentation, concluding with engineering considerations like mixed-precision and parallel training. Every technique is implemented directly in Python and NumPy or PyTorch and checked numerically against the corresponding OpenCV or PyTorch library function, so readers see not just the mathematics but its concrete behavior on real and synthetic data. The material was distilled with AI assistance from freely available online course notes, condensing extensive working code into concise mathematical exposition while preserving verified, reproducible results throughout. It is intended as a self-contained reference for students and practitioners who want to understand computer
vision algorithms and their Python implementations.
Read the full abstract ▾
Machine Learning
Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
Marcio A. Sampaio, Paulo H. Ranazzi and Martin J. Blunt
Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions (non-Gaussian). In this way, for these methods, we need to apply efficient parameterization techniques. Currently, the most efficient methods for performing parameterization are deep learning models. However, given the variety of existing deep learning models, studies have not identified which is most suitable for use with ensemble-based methods, although some important models had already been evaluated. Based on a recent literature review, the most promising models selected were VAE-GAN, Latent
Diffusion, and StyleGAN models. As a novel aspect of this work, data assimilation with the second generation of StyleGAN (StyleGAN2) model was performed using the latent z-space and intermediate w-space, separately. They were applied in two 2D case studies: one categorical (three facies) and the other continuous. The results demonstrated that all three models are highly efficient, with the StyleGAN2 model standing out for generating samples with geological realism and achieving excellent data matching in the cases studied. Our findings show that performing data assimilation with StyleGAN2 using the intermediate space (w-space) yielded better results than the traditional application in the latent space (z-space). This is due to the fact that ESMDA uses linear updates and the w-space is much more linear and disentangled than the highly entangled z-space, thereby ensuring that the updated vectors remain close to realistic geological patterns. These results were validated using main geostatistical and history matching metrics.
Read the full abstract ▾
Computer Vision
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
Xinyue Xu, Jiahao Zhang, Lijie Hu et al. (+2 more)
Sparse autoencoders (SAEs) reveal visual structure in
diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (
Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence. D-Scope aggregates SigLIP~2
embeddings of highly activating image patches into visual centroids. Matching target text descriptions against these visual centroids in the shared image-text
embedding space then enables
retrieval of individual features without per-feature text annotations. The underlying patches provide evidence for inspecting each selection, while spatially masked interventions test the corresponding decoder direction at varying strengths under fixed generation conditions. We characterize 150 SAEs across two model families and five layers, and introduce a
benchmark of 100 target concepts with ten contexts each spanning under-specified and explicit-conflict conditions. Our empirical results show that high reconstruction fidelity can coexist with low dictionary utilization and limited visual-evidence coverage. Under per-case best-of-sweep strength selection, contrastive
retrieval yields larger mean regional SigLIP~2 gains than direct
retrieval across the tested steering configurations, without consistently improving outside-region preservation. D-Scope provides an inspectable framework for evaluating sparse DiT features through their visual evidence and the effects of their decoder directions on generation. The demo is available at https://jiahaozhang-public.github.io/d-scope/.
Read the full abstract ▾
All authors Xinyue Xu, Jiahao Zhang, Lijie Hu, Peter Hase, Hao Wang
Computer Vision
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction
Mehmet Emre And{\i}ran, Zhuoqian Yang, Liying Lu et al. (+2 more)
Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic range and exposure cause LDR images to lose varying amounts of information in shadows and highlights. We present ExpandDiff, a conditional
diffusion pipeline that jointly reconstructs clipped shadows and highlights. To account for this variation, we introduce Dynamic Clipping Synthesis (DCS), which randomly samples shadow and highlight clipping percentiles when constructing training inputs from HDR targets. A pixel-space
diffusion model guided by spatially-adaptive normalization then predicts perceptually encoded HDR through a bounded output head, reconstructing both clipping directions in one sampling trajectory. On the SI-HDR
benchmark, ExpandDiff variants improve HDR reconstruction accuracy by 3.43 dB in PU21-PSNR over the strongest evaluated competing method, and by 7.34 dB under two-sided clipping. The code and supplementary material are available at https://memreandiran.github.io/expanddiff/.
Read the full abstract ▾
All authors Mehmet Emre And{\i}ran, Zhuoqian Yang, Liying Lu, Mathieu Salzmann, Sabine Süsstrunk
Computer Vision
Semantic Watermarking for Malicious Image Manipulation Detection
Yoonseo Kim, Seungwoo Baek and Junyoung Park
The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images while preserving visual plausibility, with concrete consequences for public discourse and vulnerable populations. We propose a robust semantic watermarking framework that reframes the watermark as a recoverable semantic reference rather than an opaque identifier. Our framework combines a $\beta$-VAE-based binary watermark (CLIP-VAE) with explicit channel-aware training—random bit-flip noise is injected during training so that the decoder learns graceful degradation under the noisy watermarking channel. As a downstream application, a lightweight module SDA-Net uses the recovered semantic
embedding to expose not only whether but in which semantic direction an image has been altered. In a 5-way comparison against representative binary hashing baselines (SimHash, ITQ, HashNet, and their robust-MLP variants), CLIP-VAE achieves the highest reconstruction cosine similarity to the original CLIP
embedding under realistic InstructPix2Pix bit-error rates, and uniquely supports direction-of-drift detection—a forensic complement to existing content-moderation pipelines.
Read the full abstract ▾
Complex Variables
The sharp radius in Korenblum's maximum principle for the Fock space
Frank Wikström
Korenblum's maximum principle states that if $|f| \le |g|$ near the boundary, then $\| f \| \le \| g \|$. The optimal size of the region of domination has been studied in Bergman spaces since 1991 and in Fock spaces since 2006, but only bounds have been obtained. We determine the optimal size for the Fock space $F^2$ of entire functions that are square integrable with respect to $e^{-|z|^2}\,dA(z)$: if $f, g\in F^2$ and $|f(z) \le |g(z)|$ for all $|z|>1$, then $\| f \| \le \| g \|$. The radius $1$ is optimal and we determine all pairs for which equality holds. To our knowledge, this is the first space of Bergman or Fock type in which the optimal radius in Korenblum's principle has been determined. The proof combines a Schwarz-Pick estimate centred at infinity with a moment-duality argument, and requires no numerical computation. The same method gives a moment criterion for weighted Fock-type spaces. For every non-increasing radial weight, the optimal radius equals the upper bound given by the pairs $f\equiv c$, $g(z)=z$. In particular, the upper bounds of Wee and Le for such weighted Fock spaces are sharp in the
Hilbert space case. We also show that the optimal radius is $\sqrt{(\beta+1)/\alpha}$ for the weight $|z|^{2\beta}e^{-\alpha |z|^2}$, whenever $-1<\beta\le5.44$.
Read the full abstract ▾
Quantum Physics
Weakly Measured Loops for Quantum Amplitude Amplification: Oracle Savings and Adaptive Search with Unknown Target Probability
Wang Fang and Chris Heunen
We present a family of
quantum amplitude amplification
algorithms that interleave ordinary Grover rotations with tunable weak measurements in loops. A successful measurement yields the target state and stops the
algorithm, while after a failure, the loop resumes from the post-measurement state without restarting. We express the leading costs in expected Grover iterations as $p \to 0$. For a known target probability $p$, an exact weak measurement-conditioned loop for states near the angle $\pi/4$ uses $(\pi/8+1/4+o(1))/\sqrt{p}$ iterations, improving on the standard Grover constant $\pi/4$ and on optimised restart Grover, and matching the corresponding infimum in our continuous-angle analysis. When only a lower bound $0 < p_0 \leq p < 1/2$ is available, a discrete Lyapunov equation gives the exact expected oracle cost for every fixed measurement strength and a closed-form optimal strength. Using the strength selected from $p_0$, the expected number of Grover iterations is at most $\frac{1}{2\sqrt{2}}(\frac{1}{\sqrt{p}}+\frac{1}{\sqrt{p_0}})$, where the expected cost decreases as the actual $p$ increases, and gives the leading constant $1/\sqrt{2}$ at the promise boundary $p = p_0$. For completely unknown $p$, we identify measurement strength $\kappa(t)=\Theta(1/t)$ as the critical scale within the regular schedules considered here and analyse $\kappa_b(t)=\min\{1/2,b/t\}$. For each fixed $b > 2$, we rigorously derive a closed-form Gamma-function expression $C(b)$ giving $(C(b)/2+o(1))/\sqrt{p}$ expected iterations. Numerical minimisation of this explicit expression gives $b \approx 5.2$ and $C(b)/2 \approx 1.01$. The results show that weak measurements preserve the $\Theta(1/\sqrt{p})$ search scale while adding an explicit fixed-point control mechanism and provable oracle savings.
Read the full abstract ▾
Differential Geometry
Type I estimates for the Kahler-Ricci flow I
Wangjian Jian and Jian Song
We establish the Type I estimate for the scalar
curvature of the Kahler-
Ricci flow on compact Kahler
manifolds, for arbitrary smooth initial metrics, whenever the flow develops finite time singularities. This estimate is a building block for the analytic minimal model program with
Ricci flow.
Read the full abstract ▾
Combinatorics
Sub-quorum colorings of some infinite families of caterpillars
Rafik Sahbi, Youcef Belkina and Amar Bennadji
A partition $\pi=\{V_{1},V_{2},...,V_{k}\}$ of the vertex set $V$ of a graph $G$ into $k$ color classes $V_{i},$ with $i\in\{1,...,k\}$ is called a quorum coloring if for every vertex $v\in V,$ at least half of the vertices in the closed neighborhood $N[v]$ of $v$ have the same color as $v.$ The maximum cardinality of a quorum coloring of $G$ is called the quorum coloring number of $G$ and is denoted by $\psi_{q}(G).$ A sub-quorum coloring of $G$ is an onto partial function $f:V\rightarrow\left\{1,2,\ldots,\ell\right\}$ having the property that for every vertex $v\in V,$ if $f(v)$ is defined, then at least half of the vertices in $N[v]$ having an image by $f$, have the same color as $v.$ The sub-quorum coloring number $\psi_{sq}(G)$ equals the maximum value $\ell$ in a sub-quorum coloring of $G.$ In this paper, we determine the exact value of the sub-quorum coloring number for some infinite families of caterpillars including complete $n$-tuple caterpillars and complete caterpillars with minimum spine-vertex degree three.
Read the full abstract ▾
Robotics
TO-mdiSPAs: Topology Optimization of multi-directional Soft Pneumatic Actuators
Swagatam Islam Sarkar and Prabhat Kumar
Soft pneumatic actuators (SPAs) are highly promising and have been extensively explored within the field of soft robotics. Under pneumatic pressure loads, an SPA undergoes bending deformation to perform specific tasks. A multi- or omni-directional SPA can bend and move in any direction within a 3D space, leveraging its multiple degrees of freedom to realize various mechanical functions. This work presents a systematic methodology using
topology optimization (TO) to achieve an optimized design for a multi-directional SPAs. To ensure manufacturing robustness, a three-field TO formulation considering blueprint, dilated, and eroded designs is implemented. Additionally, Darcy's law, incorporating a drainage term, is used to model the design-dependent nature of the pneumatic loading. A min-max optimization problem is formulated based on the target output deformations of the SPA unit and solved using the Method of Moving Asymptotes. The optimization yields a high-performing, unconventional
geometric design. Finally, numerical simulations demonstrate that the optimized SPA successfully achieves versatile multi-directional movements.
Read the full abstract ▾
Data Structures and Algorithms
$(\alpha, \beta)$ Spanners and Hybrid Spanners with Nearly Tight Bounds
Shiri Chechik and Gur Lifshitz
For an $n$-vertex undirected, unweighted graph $G=(V,E)$ and a positive integer $k$, we present new spanner constructions with $O_k(n^{1+1/k})$ edges that achieve nearly optimal guarantees for all distances $d\le k$. Specifically, we construct a spanner $H\subseteq G$ with $O(n^{1+1/k}+(k+d\log d)n)$ edges, ensuring that any pair at original distance at most $d$ satisfies $\mathrm{dist}_H(u,v)\le 2k+O(d\log d)$. Equivalently, the multiplicative stretch for pairs at distance $d$ is $2k/d+O(\log d)$. In particular, setting $d=k/\log k$ yields an $(O(\log k),O(k))$-spanner with $O(n^{1+1/k}+kn)$ edges. For comparison, Ben-Levy and Parter (SODA'20) obtained, for every fixed $\varepsilon>0$ and sufficiently large $k$, an $(O(k^\varepsilon),O_\varepsilon(k))$-spanner with $O_{\varepsilon,k}(n^{1+1/k})$ edges. Our result improves the multiplicative stretch from $O(k^\varepsilon)$ to $O(\log k)$ while keeping the additive term linear in $k$, bringing us closer to the goal of $(O(1),O(k))$-spanners. Furthermore, Ben-Levy and Parter obtained multiplicative stretch $O_\varepsilon(k/d)$ for distances $d\le k^{1-\varepsilon}$, for every fixed $\varepsilon>0$, and an explicit bound of $7k/d$ for $d\le\sqrt{k}/2$. We achieve $2k/d+O(\log d)$, which is $(2+o(1))k/d$ whenever $d=o(k/\log k)$. Our second result is an improved construction of $k$-hybrid spanners, which guarantee stretch $2k-1$ for adjacent pairs and $k$ for non-adjacent pairs. Parter's original construction uses $O(k^2 n^{1+1/k})$ edges; we achieve the same guarantees with $O(n^{1+1/k}+kn)$ edges, removing the $k^2$ factor from the $n^{1+1/k}$ term. For every fixed $k$, our edge bound is optimal up to a constant factor under Erdős' girth
conjecture.
Read the full abstract ▾
Numerical Analysis
Deep Truncated FBSDE Method for High-Dimensional Nonlinear PDEs and Fully Coupled FBSDEs
Xinyu Cheng, Yunzhang Li and Weiran Xiong
In this paper, we introduce a deep truncated forward-backward
stochastic differential equation (FBSDE) method for high-dimensional partial differential equations (PDEs) and fully coupled FBSDEs. The proposed method combines gradient-truncated iterative decoupling with fictitious-play averaging to separate the forward and backward processes in a coupled framework. This preserves the coupled dynamics while reducing the unstable feedback induced by parameter-dependent forward paths during optimization. Furthermore, we incorporate a pathwise consistency term to create explicit local gradient shortcuts, thereby providing a structural mechanism that may mitigate gradient vanishing. We also derive a residual-based error estimate and establish conditional convergence of the fully discrete numerical approximations under suitable conditions, in which the pathwise consistency loss is not required. Our approach is particularly effective for convection-dominated equations, where the coupled formulation provides a stable representation of nonlinear transport without introducing singular terms into the BSDE. Numerical experiments demonstrate improved accuracy and stability in both low- and high-dimensional problems and robust performance for strongly coupled problems.
Read the full abstract ▾
Algebraic Topology
Weak, stable, and ordinary Lusternik-Schnirelmann category of finite spaces
David Mosquera-Lois and Kohei Tanaka
The weak, stable, and ordinary Lusternik–Schnirelmann categories of a finite $T_0$-space $X$ satisfy $\operatorname{cat}_w(X)\leq \operatorname{cat}_s(X)\leq \operatorname{cat}(X)$. We give a general construction answering the simultaneous-strictness question of Cárdenas, Flores, Quintero, and Villar-Liñán. If $P$ is weakly contractible but noncontractible and the deletion of one point makes $P$ contractible, then adjoining $m\geq 2$ incomparable maximal points produces a connected finite space with category triple $(1,2,m)$. Moreover, after any positive number of barycentric subdivisions its ordinary category is equal to $2$. Applying the construction to a nine-point space yields examples on $m+9$ points and, in particular, a twelve-point example for which both inequalities are strict. Using additivity under disjoint unions, we also realize every triple $(a,b,c)$ with $1\leq a<b\leq 2a$ and $c\geq b$, as well as every triple $(a,a,c)$ with $2\leq a\leq c$. We conclude with questions concerning connected realizations and the minimum cardinality of a finite space exhibiting simultaneous strictness.
Read the full abstract ▾
Statistics Theory
Improving the James-Stein estimator via q-number shrinkage
Yuzo Maruyama and Akimichi Takemura
For estimating the mean vector of a $p$-variate normal distribution ($p \ge 3$) under quadratic loss, the positive-part James-Stein
estimator dominates the original Jame-Stein
estimator though it suffers from a non-smooth thresholding boundary. In this paper, we first express the shrinkage factor of the positive-part
estimator using an infinite series. Truncating this series at a finite degree $m$ allows us to interpret the factor as a special case of $q$-numbers. Leveraging these $q$-numbers parameterized by a positive real index $m$, we propose a novel smooth
estimator. We prove that the proposed
estimator dominates the original James-Stein
estimator for any dimension $p \ge 3$, provided the truncation parameter satisfies $m \ge 0.95\sqrt{p-2}$.
Read the full abstract ▾
Machine Learning
Hybrid Methods for Robust Tabular Data Imputation
Jinwei Li, Michelle Bruch and Daniel Tenbrinck
Missing data are a fundamental challenge in statistical analysis and machine learning, as the choice of imputation method substantially impacts downstream inference. In this work, we propose two hybrid imputation methods called NuclearForest and SoftForest, which combine
nuclear-norm-based low-rank initialization using Singular Value Thresholding (SVT) and SoftImpute, respectively, with a non-iterative Random Forest refinement. For the SVT-based component, we further introduce an adaptive step-size rule, prove adaptive step-size bounds, and establish convergence for the corresponding zero-initialized iteration. The low-rank initialization provides a structured warm start that captures the global covariance patterns in the data, while the subsequent Random Forest step recovers residual nonlinear signals encoding local dependencies. We conduct an extensive
benchmark on diverse
datasets from different application domains, comparing the proposed methods with seven established imputation methods under the Missing Completely at Random (MCAR), Missing at Random (MAR), and Missing Not at Random (MNAR) mechanisms across varying missingness rates. Our results demonstrate that NuclearForest and SoftForest match or exceed the imputation fidelity of state-of-the-art iterative methods such as MissForest, while significantly reducing computational cost. In particular, they achieve speedups of approximately 5.81 times and 9.52 times over MissForest by replacing iterative cycles with a single refinement step. Our approach effectively exploits the low-rank structure of real-world tabular data and accommodates mixed-type variables, providing an efficient and robust solution for data imputation in bioinformatics, economics, and beyond.
Read the full abstract ▾
Mesoscale and Nanoscale Physics
Anisotropic wavevector-dependent damping of thickness-quantized magnons
Tamara Azevedo, Rostyslav O. Serha, Yannik Kunz et al. (+7 more)
Magnon damping is a key factor governing
spin-wave transport and nonlinear dynamics of multimode
magnon systems. However, many descriptions rely on the assumption of an effective mode-independent parameter, which can mask wavelength-dependent relaxation processes that depend on propagation geometry and mode profile. Here, we employ high-resolution parametric-instability spectroscopy to probe thickness-quantized
spin waves with wavelengths down to about a hundred nanometers in micrometer-thick yttrium iron garnet films. The instability threshold exhibits a regular sawtooth dependence on the
magnetic field, arising from switching between discrete thickness modes. Comparison with dipole–exchange theory reveals anisotropic wavevector-dependent damping that increases with mode number and depends differently on the in-plane and out-of-plane wavevector components.
Read the full abstract ▾
All authors Tamara Azevedo, Rostyslav O. Serha, Yannik Kunz, Matthias R. Schweizer, Vitaliy I. Vasyuchka, Mathias Weiler, Andrii V. Chumak, Burkard Hillebrands, Mikhail Kostylev, Alexander A. Serga
Robotics
Towards Agile Vision-Based Multi-UAV Flight: Revisiting State Estimation
Michal Pliska, Matouš Vrba, Ondřej Víta et al. (+3 more)
Agile multi-
UAV flight requires accurate and low-latency onboard estimation of the kinematic states of neighboring
UAVs for collision avoidance, motion coordination, etc. Most
vision-based approaches rely on position-only measurements, inferring velocity and acceleration indirectly from displacement. We show that this introduces a fixed structural delay in the estimation of higher-order states, which limits the achievable agility. To address this, we propose to integrate tilt measurements, provided by a state-of-the-art visual detector, which inform about the thrust direction of co-planar multirotor
UAVs. We
benchmark four position-only and five pose-aware
estimators, including a novel formulation of a linear thrust-constraining Kalman filter, on two real-world and one high-fidelity photorealistic simulated
dataset over different levels of agility (3-21 m/s^2). In our setup, pose-aware estimation consistently reduces the average velocity and acceleration estimation errors by 40% and 57% across the three
datasets with the proposed KF formulation outperforming the other
estimators. Position-only filters exhibit a constant ~300 ms delay in acceleration step response independent of agility, whereas the tilt-constrained
estimators operate near the physical response limit given by the camera frame-rate by observing the change in thrust direction before the displacement accumulates. In a closed-loop leader-follower simulated experiment with NMPC control, position-only estimation of the leader's state fails to facilitate stable hovering of the follower, while the proposed
estimator enables tracking of lateral maneuvers exceeding 2g of acceleration.
Read the full abstract ▾
All authors Michal Pliska, Matouš Vrba, Ondřej Víta, Martin Jiroušek, Viktor Walter, Martin Saska
Systems and Control
Circuit-Based Dispersion Analysis of Periodic Cross-Shaped Unit Cells with Dirac Characteristics
Mahyar Mehri Pashaki, Mohammad Hossein Koohi Ghamsari and Mohammad Memarian
In this paper, the dispersion behavior of periodic cross-shaped unit
cells is investigated with emphasis on Dirac-type dispersion using an equivalent
circuit modeling approach. Two unit-
cell geometries, including a simple cross structure and a modified configuration with a central patch, are analyzed using full-wave eigenmode simulations and scattering-parameter-based dispersion extraction. An equivalent
circuit model is developed to capture the dominant coupling mechanisms and accurately reproduce the dispersion characteristics near the $\Gamma$-point. The results demonstrate that the proposed
circuit model exhibits good agreement with full-wave simulations and provides a physically intuitive framework for analyzing stopband behavior and mode degeneracy. Furthermore, the limitations of S-parameter-based dispersion extraction in the presence of low-Q radiative modes are highlighted.
Read the full abstract ▾
General Relativity and Quantum Cosmology
Complete total-transmission modes of Kerr black holes
Changkai Chen, Xiaohua Zhang, Zhoujian Cao et al. (+2 more)
We construct the complete spectrum of gravitational total-transmission modes (TTMs) of Kerr black holes and find four globally continuous families, $n_\infty=1,2,3,4$, each with two complex-conjugate frequency branches. Compared with the three-family classification of Cook and Lu, our global continuation resolves the mirror-related sectors of their $n=2$ family into separate families without introducing additional
symmetry-unrelated roots. This organization distinguishes complex conjugation at fixed $m$ from the mirror
symmetry connecting the $m$ and $-m$ spectra. The $n_\infty=3$ family approaches the Schwarzschild algebraically special frequency, whereas the $n_\infty=1,2,$ and $4$ families diverge as $\omega\propto a^{-4/3}$ along lower-half-plane directions $-150^\circ$, $-90^\circ$, and $-30^\circ$, respectively. High-precision data up to $\ell=32$ confirm the Cook–Lu small-
spin asymptotics and reveal how the divergent branches are embedded in the global four-family spectrum, with a family-dependent relation between the spherical-limit angular labels and the large-$|a\omega|$ ordering. For axisymmetric perturbations, the $n_\infty=2$ and $n_\infty=3$ branches coalesce at genuine exceptional points, where the scattering spectral function develops a second-order zero and the TTM excitation factors are strongly enhanced, offering a different interpretation of the structure previously described by Cook and Lu as an overtone-multiplet splitting. Finally, we identify a previously unreported anomalous proximity between the $n_\infty=3$ TTM family and an unconventional Kerr quasinormal-mode sequence, with frequency separations reaching order $10^{-8}$ in the representative case studied.
Read the full abstract ▾
All authors Changkai Chen, Xiaohua Zhang, Zhoujian Cao, Jiliang Jing, Sheng Long
Computation and Language
Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions
Haoyang Zhang, Jianpeng Zhao, Qi Hao et al. (+1 more)
Rule-based
reasoning, as in eligibility checks and contract reviews, requires
language models to assess evidence against individual conditions and combine their judgments under explicit rules. Errors in evidence assessment can leave a decision unchanged, but misinterpreting or overlooking decision-critical evidence can reverse it. Identifying such evidence allows more capable models to focus on checking the corresponding condition judgments, supporting accurate and safe decisions. Recognizing the evidence's criticality requires understanding how evidence affects a condition judgment and how that judgment affects the decision. To achieve the goal, we propose a INTERvention-based imPACT learning framework (InterPact), which enables counterfactual verification of evidence criticality in rule-governed decisions. Specifically, its evidence intervention constructor generates training pairs for a propagation verifier by editing case facts with a frozen
language model while holding rules and non-target conditions fixed. Human-reviewed labels record the resulting condition and decision changes, while complete state-to-decision mappings supervise consequences beyond the observed edit. During training, the verifier weights learned conditional decision predictions by evidence-based condition probabilities through a fixed composition operation, propagating decision-change supervision into the base model. At inference, the trained base model directly judges criticality from the original case and target evidence, without human or stronger-model supervision. On single-case evidence criticality verification over adapted rule-governed decision cases, InterPact achieves 68.28% accuracy, outperforming all six baselines. These results support learned decision sensitivity as a basis for prioritizing evidence checks.
Read the full abstract ▾
All authors Haoyang Zhang, Jianpeng Zhao, Qi Hao, Pengyang Wang
Cryptography and Security
Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents
Tobias Kaiser and Aritra Dhar
Skills extend an
agent's capabilities by injecting instructions and information into the context, and are widely used by
agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's
agent. The emerging defense scans skills before installation, pairing deterministic static checks with an LLM-based semantic judge, as in NVIDIA's SkillSpector. We show that such defenses fall to an attacker who knows the detector. Our white-box LLM attacker, Pretext, iteratively crafts skills that evade detection while still delivering the payload and performing the benign task: moving the payload from code into natural
language leaves static analysis inert, while framing it as the skill's legitimate purpose and splitting instructions across files keeps the LLM stage below its blocking threshold. Across three open-source models, Pretext achieves up to 97% and 77% against a frozen detector and a co-adaptive one, respectively, revealing major gaps in current skill scanners.
Read the full abstract ▾
Analysis of PDEs
Regularity of critical immersions for scale-invariant curvature energies in even dimensions
Tian Lan
For immersions of a closed $2h$-dimensional
manifold $\Sigma$ into $\mathbb R^m$, we consider
curvature energies that are invariant under ambient isometries and dilations, with the principal term $\int_{\Sigma} \big|\nabla^{(h-1)} \vec{\mathrm{I\!I}}\big|_g^2\,d\text{vol}_g$ and lower-order submanifold invariants. Following the four-dimensional approach developed in joint work with Bernard, Martino, and Rivière, we prove that every weak critical immersion in the natural Sobolev class $W^{h+1,2}$, whose induced metric and its inverse have $L^\infty$ coefficients, is real-analytic in harmonic coordinates. The proof combines
geometric conservation laws, structural identities, and
elliptic estimates with critical Sobolev coefficients to obtain Morrey decay and bootstrap to full regularity.
Read the full abstract ▾
Computer Vision
FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning
Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk et al. (+1 more)
The rapid advancement of generative
video models has enabled the synthesis of increasingly realistic and temporally coherent
videos, while also raising concerns about the generation of harmful content. The reliance on large-scale web
datasets during training inevitably exposes these models to undesirable material, making concept unlearning an essential mitigation. Existing methods mainly target static visual concepts, such as objects, identities, or unsafe appearance, largely overlooking motion unlearning. Furthermore, these approaches often pay little
attention to preserving the surrounding scene. As a result, successful concept removal may unintentionally alter the background, composition, or overall
video dynamics. We argue that effective unlearning should ideally change only what is targeted, while minimizing unnecessary changes to the remaining scene. In this work, we introduce FOMO, to the best of our knowledge the first training-based selective
video unlearning method that directly treats preservation of the original scene as a priority. We formulate unlearning around two complementary objectives: what to change and what to preserve. Our method localizes concept-related representations and modifies them, while the preservation mechanism maintains non-target scene information without requiring auxiliary data. Beyond simply erasing unwanted concepts, FOMO explicitly redirects the generation toward a specified safe alternative. We further extend this formulation to motion unlearning, where the concept is defined by temporal behavior rather than a fixed spatial region. Our solution achieves effective unlearning across unsafe content, object, and motion concepts, while achieving the best trade-off between concept removal and scene preservation. Code: https://github.com/gmum/FOMO Project Page https://gmum.github.io/FOMO
Read the full abstract ▾
All authors Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk, Przemysław Spurek
Artificial Intelligence
Why Do Conventional World Models Fail to Learn Cellular Automata?
Shaoyang Guo and Ziming Liu
Although conventional world models - auto-regressive or
diffusion models based on
transformers or convolutional networks - may learn surface statistics of world dynamics, can they learn the exact world dynamics from its observed history? Leveraging cellular automata as a simple testbed, we find the answer to be no in many cases. Conventional architectures predict most pixels correctly yet rarely complete a rollout: a CNN predicts 96.3% of
cells but completes 18.9% of rollouts; a joint
diffusion model completes none. We trace the gap to three failure modes of these world models - namely, they fail to exactly capture spatial locality, temporal locality or temporal stability. Simple changes repair each: (1) for spatial locality, two-dimensional rotary positions lift a
transformer from 39.1% to 100% on the Game of Life; (2) for temporal locality, handing each
token its
cell's previous-frame neighbourhood lifts the same
transformer from 25.8% to 99.9% on unseen rules; (3) for temporal stability, causal freezing lifts the same
diffusion weights from 42.2% to 99.9%. None of the three changes touches the architectural backbone; each only modifies the information flow within it. We also compare joint and ordered sampling on billiards and, in an exploratory study, on a simulated Burgers equation.
Read the full abstract ▾
Cosmology and Nongalactic Astrophysics
An LSST-DESC Precursor Project: Hyper Suprime-Cam Year 1 $3\times2$pt in Harmonic Space
D. Sanchez-Cid, J. Sanchez, I. Sevilla-Noarbe et al. (+19 more)
We present the first fully photometric joint analysis of weak gravitational
lensing and
galaxy clustering (3$\times$2pt) in harmonic space with LSST-DESC analysis pipelines applied to Hyper Suprime-Cam Year 1 (HSC Y1) data. The HSC Y1
dataset, with imaging depth and
galaxy number density similar to those expected for the first year of LSST observations, is an ideal testbed for validating DESC measurement and inference tools. We measure the full set of angular power spectra -
cosmic shear,
galaxy clustering, and
galaxy-
galaxy lensing - perform null tests, and correct for the impact of observing conditions on both the
galaxy density and shear fields via mode deprojection. We validate our likelihood pipeline by reproducing the official HSC Y1
cosmic shear cosmological constraints with the DESC inference code. Jointly analysing all three two-point functions, we constrain $\Lambda$CDM and $w$CDM cosmologies, reporting results for
cosmic shear, the combination of
galaxy clustering and
galaxy-
galaxy lensing (2$\times$2pt), and the full 3$\times$2pt. From the joint 3$\times$2pt $\Lambda$CDM analysis we find $\Omega_m = 0.249^{+0.061}_{-0.051}$, $\sigma_8 = 0.904^{+0.098}_{-0.091}$, and $S_8 \equiv \sigma_8\sqrt{\Omega_m/0.3} = 0.821^{+0.018}_{-0.021}$. This analysis validates the complete DESC 3x2pt infrastructure on survey data, providing the foundation for the forthcoming LSST Year 1 cosmological analysis.
Read the full abstract ▾
All authors D. Sanchez-Cid, J. Sanchez, I. Sevilla-Noarbe, D. Alonso, F. Andrade-Oliveira, H. Awan, C. Chang, J. Ellison, C. García-García, M. Ishak, E. Longley-Phillips, R. Mandelbaum, A. Nicola, E. Pedersen, J. Prat, E. Rykoff, E. Sanchez, N. Šarčević, M. Soares-Santos, M. Yamamoto, J. Zuntz, the LSST Dark Energy Science Collaboration
Quantum Physics
Warm-Start Iterative QITE for Distribution Network Reconfiguration via Branch-Exchange Encoding
Noah Crum, Pete Pritchard, Tanner Rase et al. (+5 more)
We present a hybrid
quantum-classical
algorithm for distribution network reconfiguration, a combinatorial optimization problem on power distribution networks, that combines a radiality preserving branch-exchange encoding with iterative warm-start
quantum imaginary-time
evolution to minimize active line losses. The encoding uses a fixed-width binary representation of sequential branch-exchange actions, ensuring that every register outcome decodes to a radial configuration. The
quantum subroutine is informed by a surrogate model fit to classically-solved alternating current power flow (ACPF) labels. After a set budget of ACPF solves and
circuit samples is exhausted, the
algorithm returns the lowest-loss configuration seen. We employ our
algorithm on ten test cases, including seven commonly-used
benchmark cases and three cases we modified from these and similar standard systems. We include two methods to reduce problem size, which enable extensions of the
algorithm to larger networks. We successfully reach minimal-loss configurations for six cases and find configurations with losses from 0.2 percent to 2.18 percent above the reported reference minimal loss for the other four.
Read the full abstract ▾
All authors Noah Crum, Pete Pritchard, Tanner Rase, Phillip C. Lotshaw, Shaked Regev, Claudio Girotto, Ananth Kaushik, Paul Smith
Computer Vision
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
Qize Yu, Lianrui Fan, Boyu Chen et al. (+23 more)
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet
vision-
language-action (VLA) and world-action models (WAMs) take perception from general-purpose
vision-
language and
video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines
multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public
datasets and dedicated data engines. Against 44 baselines across 34 grounding
benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. On RoboTwin 2.0, it outperforms every mainstream backbone we evaluate in all four out-of-distribution settings, by up to 24.8% relative to the strongest backbone. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. On nuScenes, used as the visual backbone, GroundingPI attains an average open-loop L2 error of 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Downstream autonomous driving and robotic manipulation improve as the pretraining is scaled. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.
Read the full abstract ▾
All authors Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang, Yixiao Ge, Shuchang Zhou, Shilong Liu, Xianming Liu, Ping Luo, Shiyu Huang
Computer Vision
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Qize Yu, Lianrui Fan, Bowen Ping et al. (+19 more)
Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output
tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional
diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public
datasets and dedicated data engines, direct AR-to-
diffusion conversion with joint AR and
diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding
benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With
entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a $4.51\times$ speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These support efficient visual grounding in latency-sensitive real-world systems.
Read the full abstract ▾
All authors Qize Yu, Lianrui Fan, Bowen Ping, Xini Ding, Zetian Song, Junbo Niu, Kaixuan Wang, Tianxing Chen, Yue Chen, Minghua He, Yuran Wang, Jie Huang, Haojun Zhang, Min Chen, Hao Li, Wenxuan Song, Ruihai Wu, Xianming Liu, Shilong Liu, Shuchang Zhou, Ping Luo, Shiyu Huang
Robotics
Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
Xinhao Yang, Wenhao Wu, Ning Lv et al. (+5 more)
3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral specifications beyond those covered by demonstrations. We study this challenge as unseen specification generalization, where
language specifies behaviorally significant variations, such as target position, displacement, or articulated state, that are absent from policy training. We find that pretrained
language representations and conventional global behavior-
language alignment capture coarse task semantics but often blur nearby specifications that require distinct behaviors. We introduce T3DP, a Text-to-3D Policy framework for fine-grained
language-behavior
alignment. Rather than compressing each instruction and demonstration into a single global
embedding, T3DP preserves their local structures and establishes bidirectional
token-level correspondence between linguistic elements and behavioral segments. This directly grounds subtle linguistic variations in the behavior components they affect, preventing closely related specifications from collapsing in the representation space. The resulting specification-sensitive
language representation conditions a point-cloud-based 3D
diffusion policy, enabling more precise control over unseen behavioral specifications without modifying the underlying policy architecture. Across Meta-World, ManiSkill, and RoboTwin, T3DP improves average held-out-specification success over global
language-behavior
alignment by +11.0-14.2 points, with gains on all 15 task families; on real-
robot tasks, it further raises average success from 47.5% to 65.0% (+17.5 points). Representation and action-probe analyses show that fine-grained
alignment better preserves specification geometry and action-relevant variation, linking local behavior grounding to downstream control.
Read the full abstract ▾
All authors Xinhao Yang, Wenhao Wu, Ning Lv, Yanshen Ding, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang