Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Monday 7 September
In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely on offline inference with global temporal sampling, which violates causality and prevents deployment in live surveillance streams. Conversely, general streaming video models satisfy causal access but dilute rare transient anomalies during memory compression and often invoke heavyweight MLLMs uniformly over long normal intervals. React VAU addresses this gap with three synergistic components: a lightweight Fast Detection Module based on Spatial Grid Folding (SGF) for continuous anomaly filtering; an Anomaly-Aware Persistent Memory (AAPM) that protects critical visual cues from temporal decay; and a heavyweight Slow Reasoning Module that remains dormant during normal streams and is awakened only by suspicious events for semantic verification and causal description. Extensive experiments on multiple benchmarks demonstrate that ReactVAU operates under strict streaming constraints while simultaneously achieving competitive performance in both anomaly detection and causal reasoning, alongside significantly enhanced computational efficiency by minimizing heavyweight MLLM invocations. Project page is available at https://huiyuiui.github.io/ReactVAU/
High Energy Physics (Phenomenology)
Recent applications of the gradient flow
The gradient flow provides a gauge- and O(4)-invariant ultraviolet regulator for QCD. This opens new opportunities for combining non-perturbative lattice calculations with perturbative results, in particular in the context of an operator-product expansion (OPE). We review the concepts behind this and argue that, within the operator basis of a given OPE, the flow-time dependence of the conversion between flowed and regular Wilson coefficients is exact at each perturbative order. Recent applications to parton distribution functions, heavy-meson observables, quark masses, and gradient-flow definitions of the strong coupling are discussed. Finally, the perturbative formulation of the Ricci flow in quantum gravity and its application to the study of non-Gaussian fixed points is reviewed.
Read the full abstract
Computer Vision
Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis
We address the problem of discovering repeated elements from a single image. In contrast to existing approaches that depend on large annotated datasets, curated multi-image collections, or object segmentation masks, we show that a single image can suffice to learn a meaningful object model in a completely bottom-up fashion, without any prior knowledge beyond a coarse scale prior. Our method learns a tunable image-space prototype of the repeated elements through a reconstruction objective, enabling the model to identify and synthesize consistent object instances within the same image. Experiments on 116 real images from the FSC-147 dataset demonstrate that our method successfully learns coherent element models and captures intra-category variation on challenging images. Qualitative results reveal superior reconstructions and interpretable decompositions compared to classical decomposition, joint alignment, and 3D object modeling methods, while maintaining a simple 2D formulation. These results suggest that meaningful object discovery can emerge from single image learning alone.
Read the full abstract
Numerical Analysis
Threshold dynamics for subdiffusive grain growth
We propose a new fractional threshold-dynamics algorithm for subdiffusive interface motion and apply it to multiphase grain-growth simulations. The method combines the L1 discretization of the Caputo time derivative with a Helmholtz-resolvent thresholding step. At each time level, the L1 convolution produces a convex history average of the previously thresholded states; this history-dependent field is then propagated by a Helmholtz diffusion solve and projected back to pure phases by thresholding. For $\alpha=1$, the method reduces to a Helmholtz-resolvent analogue of the Merriman-Bence-Osher scheme, whereas for $0<\alpha<1$ it introduces a subdiffusive temporal memory. We establish a variational characterization, maximum and comparison principles, and stability for the continuous Helmholtz diffusion step. We also derive a memory-tail estimate and a finite-dimensional pinning criterion under an explicit resolvent-contraction hypothesis. The equal-tension multiphase scheme is implemented on periodic grids. The numerical experiments investigate the joint influence of the L1 history and the smoothing length. The fixed-step runs show faster coarsening for smaller fractional orders in the tested regime, while a comparison at fixed smoothing length examines the influence of the L1 history on successive updates.
Read the full abstract
Computer Vision
TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding
Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, which current Vision Language Models (VLMs) often lack. VLMs built on CLIP-based ViT backbones tend to trade fine-grained visual details for high-level semantics. We show that this deficit propagates downstream, affecting various vision and language tasks. To address this, we fuse DINOv3 and CleanDIFT representations into a perception encoder (DiffusedDINO), and align it with RoBERTa-L, yielding a text-aligned model (TDDN) that preserves this perceptual advantage: with frozen backbones and only ~590K alignment pairs, TDDN surpasses CLIP ViT-L/14 in image-text retrieval tasks: text-to-image on Flickr30K and both directions on MS-COCO-2014. TDDN more than triples CLIP's dense-prediction accuracy (ADE20K 5.20 -> 18.11 mIoU, COCO-Stuff 7.35 -> 24.44), despite CLIP's massive training corpus. TDDN leads on segmentation benchmarks among general-purpose contrastive encoders, including SigLIP 2. We further introduce PuzzlePerception, a segmentation and visual question answering dataset that probes fine-grained spatial understanding, on which TDDN doubles CLIP's segmentation accuracy (11.04 -> 22.51 mIoU). Our code and data are available at https://github.com/adityaSomak/TDDN.
Read the full abstract
Human-Computer Interaction
Designing for Healthy, Affordable, and Sustainable Human-HVAC Interactions for Heating in Smart Homes
As geopolitical tensions, energy crises, and energy-intensive AI infrastructure intensify concerns about demand, affordability, and resilience, communities increasingly encounter these challenges through everyday energy practices, particularly winter heating. Against this background, the doctoral exposé, "Designing Human-HVAC Interaction for Healthy, Affordable, and Sustainable Heating in Smart Homes", is structured around four chapters. First, a multidisciplinary literature review defines and positions Human-HVAC Interaction, focusing on heating in smart homes. Second, longitudinal living lab studies with design probes examine everyday heating practices, thermal comfort, and indoor environmental quality, with attention to thermally vulnerable groups such as older adults, pregnant or menopausal women, parents with infants, and people affected by allergies or airborne pollutants. Third, a VR-based smart home demonstrator explores how heating and IEQ scenarios can be prototyped and evaluated as a virtual living lab, while critically examining the limits of representing bodily indoor climate conditions through VR. Fourth, follow-up design studies examine how VR-based insights can be translated into physical-digital prototypes that combine digital fabrication, distributed environmental sensing, and diverse interface forms for critical heating and IEQ contexts. The thesis aims to contribute a design-oriented understanding of Human-HVAC Interaction by building from a multidisciplinary literature review to empirical living lab and co-design studies, VR-based prototyping, and physical system development, examining how smart home users make sense of, negotiate, and respond to smart HVAC system.
Read the full abstract
Functional Analysis
Weakly LUR norms and the Schur property
A separable real or complex Banach space fails the Schur property if and only if it admits an equivalent Gâteaux smooth, weakly locally uniformly rotund norm which is not midpoint locally uniformly rotund. The construction enlarges an LUR unit ball by a weakly compact set and adds a weighted Hilbert-space term. The resulting norms can be chosen arbitrarily close to any prescribed equivalent LUR norm, and are Gâteaux smooth whenever the prescribed norm is Gâteaux smooth; Fréchet smoothness is preserved as well. Weakly locally uniformly rotund norms which are not midpoint locally uniformly rotund are dense among all equivalent norms on each separable non-Schur space. For arbitrary real or complex Banach spaces, such a renorming exists exactly when the space is LUR-renormable and fails the Schur property. We give a direct construction for this last assertion.
Read the full abstract
Optics
Spectro-temporal shaping of broadband optical wavepackets via programmable on-chip photonics
The ability to precisely shape the properties of light over multiple degrees of freedom constitutes the foundation of modern photonic architectures. Broadband sources with addressable spectro-temporal content are for instance critical for applications spanning biomedical imaging, material processing, lidar, and ultrafast spectroscopy, but also key enabling technologies in quantum information processing, high-capacity communications, and optical computing. Yet, flexible and adjustable spectro-temporal shaping so far remains a significant challenge, as it requires the simultaneous manipulation of both frequency and temporal domains across broad spectral bandwidths and extended timescales, from femtoseconds to nanoseconds. Importantly, conventional approaches to spectro-temporal processing typically rely on bulky and complex optical systems that lack scalability and flexibility, ultimately hampering their utility for applications requiring addressable multiphotonic processes. Here, we present a framework for spectro-temporal wavepacket control over a broad bandwidth, merging programmable integrated photonics with high-speed optical characterization. Leveraging machine leaning for tailoring nonlinear pulse propagation, we experimentally report scalable and on-demand shaping of broadband ultrafast pulse patterns. We demonstrate the efficacy of our method through reconfigurable power across 400 nm bandwidth with picosecond resolution, with promises for applications where precise control over light is paramount, in particular those needing versatile and controllable multiphoton excitations.
Read the full abstract
Robotics
SPOT: Spatial Perception-Oriented Long-Horizon Humanoid Teleoperation
High-quality demonstration data is becoming a central bottleneck for training general-purpose humanoid robots. While recent humanoid teleoperation systems have made substantial progress in retargeting human motion to robot motion, long-horizon loco-manipulation requires another capability: operators must maintain task-relevant spatial awareness over time, e.g., object locations, surrounding environments, the robot's pose. We call the extent of this awareness the operator's perceptual horizon. However, existing methods often shorten this: narrow views miss peripheral events, robot-mounted cameras become unstable during locomotion, and coupled head-view control makes looking around interfere with robot motion. We present SPOT, a Spatial Perception-Oriented VR Teleoperation system for collecting long-horizon humanoid demonstration data by providing extended perceptual horizon. SPOT combines a robot-mounted binocular fisheye camera, a wide-field stereoscopic display, viewpoint-decoupled free-looking, and visual stabilization to provide a robot-centric view that is wide, stable, and actively inspectable. Unlike conventional egocentric interfaces, SPOT decouples visual exploration from robot actuation: the egocentric stereo observation is rendered on a virtual hemisphere around the operator, so natural head rotations change where the operator looks within the wide-field view rather than commanding the robot head, camera, or torso. We evaluate SPOT on perception-critical humanoid data-collection tasks spanning drop recovery, peripheral retrieval, large-workspace bimanual manipulation, fine alignment, and dynamic interaction. SPOT improves efficiency, accuracy, and recovery speed, demonstrating its effectiveness for user-friendly and scalable long-horizon humanoid data collection.
Read the full abstract
Commutative Algebra
Two Infinite Families of Regular Sequences of Power Sums in Three Variables
Let $$ S=\mathbb{C}[x,y,z],\qquad p_m=x^m+y^m+z^m. $$ For every $r\geq1$, we prove that $$ p_r,\ p_{r+1},\ p_{3r+1} \qquad\text{and}\qquad p_r,\ p_{r+1},\ p_{3r+2} $$ are regular sequences exactly when $r\not\equiv1\pmod3$. This proves the Conca–Krattenthaler–Watanabe prediction for two infinite families. The proof is elementary. Four simple reductions modulo $(p_r,p_{r+1})$ reduce the problem to the two equations $x+y+z=0$ and $xy+xz+yz=0$.
Read the full abstract
Solar and Stellar Astrophysics
SN 2024afyu interpreted as a Pair Instability Supernova
Pair-instability supernovae (PISNe) are the predicted explosions of very massive stars triggered by electron-positron pair production. Numerous transients have been proposed as PISN candidates, yet none has provided unambiguous confirmation of this explosion mechanism. The predicted strengths of nebular emission lines offer a powerful means of testing the PISN scenario. We investigate the nature of SN 2024afyu, a nearby (z = 0.0085), long-lived (trise = 85 +- 11.7 days) SN with peculiar spectral evolution, with the aim of identifying its powering mechanism. We analyse multi-band photometry and optical and near-infrared spectroscopy from shortly after explosion to the nebular phase (around 500 days past peak). Besides early appearance of [Ca II] features, we identify a number of sulfur and silicon emission lines, for which we estimate electron temperatures and elemental masses. SN 2024afyu has an inferred 56Ni mass of around 0.4 to 1.0 solar masses and an inferred sulfur mass of the order of 3 solar masses, substantially larger than expected for conventional core-collapse explosions. SN 2024afyu is photometrically similar (although fainter, M_Peak(r) = -18.9 +- 0.04 mag) but spectroscopically distinct to other proposed PISNe. Yet, existing PISN models broadly reproduce several key characteristics, including the overall spectral appearance and broad photometric evolution. SN 2024afyu is a strong PISN candidate, since alternative scenarios would struggle to explain the combination of broad light curve, large intermediate-mass-element abundance, and general spectroscopic evolution. The discrepancies between the observations and currently available theoretical models highlight the need for new PISN calculations spanning a wider range of progenitor masses, metallicities, mixing prescriptions, and circumstellar environments.
Read the full abstract
Robotics
A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series
Deep learning models have been increasingly applied to Time Series Forecasting (TSF) in recent years. Transformer-based and MLP-based models have both been used effectively on many real-world TSF regression benchmarks, and there is ongoing debate as to which family of methods is best. While these benchmarks have drawn much attention, it is also worth noting that many current datasets and methods assume approximate periodicity in the time series. In this work, we focus on a new TSF task without periodicity: anticipating falls during humanoid locomotion, on the basis of egocentric vision and proprioception. When the locomotion trajectories are sufficiently diverse, periodicity is violated. We contribute two new benchmark datasets (one from simulation, one from real hardware), showing that periodicity is violated and recent deep TSF methods struggle on these benchmarks. We also propose a novel deep learning architecture that exploits both endogenous and exogenous variables and a training process that rigorously enforces i.i.d sampling of training examples. Our results show statistically significant improvement over prior art in multiple experimental conditions, by 12.73% or more on the real data and 10.40% or more on the simulation data. Code and datasets will be available upon acceptance.
Read the full abstract
Optimization and Control
Symmetry breaking in the polygonal Szegö-Weinberger inequality as $p\to1^+$: the longest shortest-fence quadrilateral
We consider Pólya's problem of finding, among convex sets of prescribed area, the one with the longest shortest fence, in the polygonal setting, namely when the class of competitors is restricted to polygons with a prescribed number of sides. While it is straightforward to show that, among triangles, the optimal shape is the equilateral one, we prove that symmetry breaking occurs in the case of quadrilaterals: the optimal quadrilateral is not the square. More precisely, we identify it as a specific isosceles trapezium, which is uniquely determined, up to homotheties and rigid motions, by an elementary equation for its base angle. The proof combines analytical arguments and rigorous interval-arithmetic computations.
Read the full abstract
High Energy Physics (Theory)
Wilson loops, M2-branes and strings
We establish a universal approach for studying the semiclassical quantization of both probe M2-branes and fundamental strings in asymptotically AdS$_{4}$ backgrounds. On the field theory side, their partition functions are dual to the vacuum expectation value of half-BPS Wilson loops of a class of three-dimensional $\mathcal{N}\geq 2$ Chern-Simons-matter theories. Utilizing this universal approach we arrive at novel predictions for the semiclassical behaviour of the Wilson loop or upon availability match our results with the previously obtained expressions via supersymmetric localization. We also show that the correct choice of holographic ensemble suggests that the semiclassical quantization of probe M2-branes yields the full perturbative answer in the rank of the gauge group $N$ for the dual Wilson loop. This is a proceedings contribution to the ”Athens Workshop in Theoretical Physics: 10th Anniversary”, held at the National and Kapodistrian University of Athens on December 17-19 2025.
Read the full abstract
Distributed Computing
MicroIntent: Intent-Based Placement Strategy for Microservice Application in the Compute Continuum Using LLMs
The placement of microservices in the compute continuum plays a vital role in delivering services that comply with customers' needs, such as reduced latency, storage requirements, quality of service and availability. To achieve customers' needs in the geographically dispersed architecture of the compute continuum, Service Level Objectives (SLOs) have been largely used in decision-making to place microservices. However, because low-level SLOs increase the barrier to entry for continuum users, placement decisions based on high-level business vocabulary are required if the compute continuum is to be adopted at scale. This paper proposes an architecture for microservices placement decisions in the computing continuum utilizing high-level user intents described in natural language as input. The approach utilizes Generative Artificial Intelligence to translate the intents to low-level SLOs, which are used along with the infrastructure description to decide where different microservices that compose an application must be deployed so that SLOs are met. We implement and evaluate a prototype of the architecture to demonstrate the approach's feasibility.
Read the full abstract
Information Theory
Exact Degrees of Freedom of Spatially Sparse MIMO Channels Without Prior CSI
We characterize the degree of freedom (DoF) of a point-to-point blockwise memoryless channel without prior channel state information (CSI), with a fixed number $K$ of propagation paths, where the transmitter (Tx) and the receiver (Rx) are equipped with nonuniform linear arrays (NULAs) of $N_t$ and $N_r$ antennas, respectively. The positions of array elements are fixed, known, pairwise distinct, and need not be equally spaced. The uniform linear array (ULA) is a special case. In each block of length $T$, the continuous angles of arrival (AoAs), angles of departure (AoDs), and independent complex Gaussian path gains are redrawn. Both Tx and Rx know the state distributions but are not given the current realizations before transmission. The receiver may estimate the channel from reference signals or decode without explicit channel estimation, with reference symbols counted in $T$ and their energy counted against the power constraint. Under the aforementioned model, we show that the DoF is $1-\frac{1}{T}$ for $K=1$, and $K(1-\frac{3}{2T})$ for $K \geq 2$, when $N_r\ge K+1$, $N_t\ge\max\{K,2\}$, and $T\ge K$. The analytical results are further demonstrated by their applications to the DoF tradeoff analysis in integrated sensing and communication (ISAC). For more general array structures, an achievability result is established, while the converse remains open in general.
Read the full abstract
Artificial Intelligence
FrogNano: Training a 4B Coding Agent via Online Task Synthesis
We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks. A key ingredient for improving performance is an online task synthesis pipeline that creates tasks calibrated to the frontier of learnability for the current checkpoint. This report provides evidence that competitive small coding agents can be trained with synthetic tasks alone, without traditional distillation from larger models, and that generating tasks at the learnability frontier of the current agent is important. We report details on the training methodology, evaluations across diverse environments, and in-depth analyses, serving as a foundation for our ongoing exploration of lightweight yet capable coding agents that can run on minimal hardware.
Read the full abstract
Analysis of PDEs
Completion of DNA replication is constrained by the spatiotemporal organisation of origin firing
DNA replication requires the coordination of origin firing and fork progression to ensure the entire genome is timely duplicated before cell division. Yet origin firing is stochastic, giving rise to the classical random completion problem of how probabilistic local events can nevertheless ensure reliable genome duplication. Although several biological mechanisms have been proposed to resolve this problem, a quantitative account of how heterogeneous initiation and fork speed govern the persistence of the final unreplicated regions is still lacking. To address this gap, we introduce a population-level kinetic framework that extends KJMA nucleation-and-growth models by tracking unreplicated intervals over size, genomic position and time. We establish well-posedness of the resulting mean-field system and global existence for compatible data. Notably, by introducing a local initiation mass function, we quantify how the density and spatial organisation of origin firing constrain replication completion, yielding novel and sharp upper bounds on both the worst-locus unreplicated fraction and locuswise near-completion time. These results provide a rigorous and computable foundation for mapping vulnerabilities in replication completion and relating persistent unreplicated regions to replication stress and genome instability.
Read the full abstract
Strongly Correlated Electrons
Hysteretic Coherence Collapse Across the First Order CDW Transition in 1T-TaS2
The first order phase transition between the nearly commensurate (NC-CDW) and commensurate (C-CDW) charge density wave phases in 1T-TaS2 underpins its exotic electronic behavior, yet the spectroscopic evolution of the low energy electronic structure across this transition remains crucial to understand. Using angle resolved photoemission spectroscopy (ARPES), we investigate the low temperature C-CDW phase, characterized by a flat band commonly associated with the lower Hubbard band and a distinct in-gap state located closer to the Fermi level. Photon energy dependent measurements distinguish these two low energy features through their different spectral weight evolution. Temperature dependent ARPES across heating and cooling cycles reveals that the in-gap state undergoes an abrupt collapse upon heating into the NC-CDW phase and re-emerges sharply upon cooling back into the C-CDW phase. This pronounced thermal hysteresis provides direct spectroscopic evidence of the first order nature of the transition. Furthermore, the disappearance and recovery of the in-gap state closely track the corresponding changes in resistivity, highlighting its intimate connection to the electronic reconstruction across the C-CDW/NC-CDW phase transition.
Read the full abstract
Machine Learning
Prevalence calibration as shortcut mitigation
Shortcut learning denotes the widespread situation in which a classifier exploits spurious correlations rather than diagnostic features. Existing mitigation strategies mostly aim to learn shortcut-invariant representations; their empirical success is limited and they cannot be applied to classifiers using frozen foundation model encoders. We propose to reframe shortcut learning as fundamentally a calibration problem: unconstrained learning implicitly calibrates each shortcut group to its training set disease prevalence, rendering the resulting classifier necessarily over-confident in one group and under-confident in the other. Building on this insight, we prevalence-equalize calibration between shortcut groups through two encoder-agnostic methods, an in-processing regularizer and a post-hoc prevalence-equalized recalibration step. Across chest-drain-pneumothorax benchmarks on CheXpert and SIIM-ACR, spanning fine-tuned CNNs and frozen foundation-model backbones, both methods substantially outperform all baselines. Post-hoc recalibration of a standard ERM-trained DenseNet raises misaligned-group AUROC from 0.23 to 0.73, indicating that shortcut reliance degrades the classification head rather than the underlying representation. Besides two new state-of-the-art shortcut mitigation approaches, our findings more fundamentally connect shortcut learning to calibration theory and algorithmic fairness.
Read the full abstract
Functional Analysis
Some observations on transitivity of Lipschitz operators
The universal property of the Lipschitz-free spaces allows for the linearisation of a base point preserving Lipschitz map $f\colon M\to M$ to a bounded linear operator $T_f\colon \mathcal{F}(M) \to \mathcal{F}(M)$. While it is known that the operator $T_f$ is weakly mixing whenever $f$ has this property, it is open whether a similar inheritance result for topological transitivity holds. Motivated by this question we investigate properties of $T_f$ under the assumption that $f$ is topologically transitive. In particular we prove Kitai's theorem for Lipschitz operators, i.e. we show that every connected component of the complex variant of $T_f$ intersects the unit circle if $f$ is topologically transitive.
Read the full abstract
Human-Computer Interaction
Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-LLM Co-Writing
Human-LLM co-writing is increasingly used for open-ended text generation, but much prior work focuses on final outputs rather than the interactional dynamics through which stories are produced. We study turn-based collaborative storytelling across three matched conditions: Human-Human (HH), Human-LLM (HA), and LLM-LLM (AA). Using a shared storytelling paradigm, we measure how agents align, introduce novel material, and influence narrative development through turn-level measures of valence adaptation, semantic novelty, transience, and resonance. Our results show that HA co-writing is not intermediate between HH and AA collaboration. Instead, it displays a distinctive asymmetry where humans tend to introduce more novel and persistent narrative material, while LLMs tend to elaborate and stabilize the existing context. These findings suggest that, in this setting, LLMs function less as human co-authors and more as adaptive narrative amplifiers that reshape how agency is distributed in collaborative writing.
Read the full abstract
Software Engineering
You can contribute if you... An Empirical Framework of AI Contribution Policies in OSS
Artificial intelligence is reshaping open source software (OSS) contribution by lowering the cost of producing code, documentation, issue reports, and review interactions. This creates opportunities for broader participation, but also disrupts how maintainers assess contributor effort, competence, and accountability. In response, OSS projects are beginning to regulate AI-mediated contribution through contribution guidelines and other project documentation. This paper presents an empirical study of these emerging policies. We analyze project policies on AI-mediated contributions by evaluating their underlying rationales, rules, and expectations. Our analysis shows that these policies seek to protect scarce maintainer attention, preserve accountability, sustain meaningful review interactions, address legal and quality concerns, and maintain pathways for newcomer learning. Based on these findings, we introduce the AI Contribution Governance Framework, which organizes recurring concerns and governance mechanisms across projects. The framework helps OSS communities develop AI contribution policies and provides researchers with a vocabulary for studying how AI is changing collaborative software production.
Read the full abstract
Number Theory
Simple critical zeros and distinct zeros of the Riemann zeta function in short intervals
Recently, on the non-trivial zeros of the Riemann zeta function, it is obtained by Alpöge and Furman that more than 67.25% of the zeros are simple and on the critical line, and more than 83.62% are distinct. Later, Lamzouri gave a different and more direct proof. In this article, we will use the method of Lamzouri to give lower bounds on the number of the non-trivial zeros of the Riemann zeta function in short intervals. To prove the main result, we establish Montgomery's theorem on the pair correlation of zeros of the zeta function in short intervals by following the approach of Baluyot, Goldston, Suriajaya and Turnage-Butterbaugh, and then use Lamzouri's inequality on any finite multiset of complex numbers which is invariant under complex conjugation.
Read the full abstract
Machine Learning
AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions
Counterfactual explanations formalize "what-if" scenarios by identifying modifications to an input instance that obtain a desired alternative prediction. Traditionally, whether generated via instance-specific optimization or amortized single pass models, these approaches rely on a single, deterministic point-estimate predictor. However, this ignores predictive uncertainty and hypothesis variability, leading to brittle explanations that frequently become invalid if the underlying model is retrained or updated. To address this fragility, we propose the Amortized Variational Counterfactual Generator (AVCG), a generalized optimization framework that formulates counterfactual generation as optimization over an arbitrary distribution of plausible predictive hypotheses rather than a single deterministic predictor. This formulation naturally accommodates Bayesian posteriors, Rashomon-restricted hypothesis spaces, and other uncertainty representations within a unified optimization framework. Evaluation across multiple benchmark datasets demonstrates that the AVCG framework produces counterfactual explanations that remain highly valid under predictive uncertainty and model changes, while maintaining competitive plausibility and single-pass runtime performance.
Read the full abstract
Computer Vision
Poisson Image Denoising Using Minimax Concave and Reweighted $\ell_1$ Penalties: Nonblind and Blind Approaches
Images are important tools in various sciences. Despite the development of photo-taking tools, creating clear and image without noise remains challenging in practice. In particular, Poisson noise has an effect on medical and astronomical images, and reduces their quality. Additionally, blur is another factor that has an effect on image quality. The problem of image restoration becomes very complicated when we have no information about the Point Spread Function (PSF). These types of problems are known as blind case. However, in some images, such as some astronomical images, the type of PSF can be specified, and these types of problems are known as nonblind problems. Total Variation (TV) is a widely used method for solving such inverse problems, where the selection of the penalty function is the most critical factor that affects the method's performance. In this paper, to improve edge preservation, we employ a reweighted $\ell_1$-regularization of the fractional order derivative. Furthermore, we propose a nonblind and blind image deblurring approach under Poisson noise using the Minimax Concave Penalty (MCP), which is a continuous, sparsity promoting, and nearly unbiased regularizer. This formulation leads to a nonconvex optimization model. To solve the proposed model, we introduce an efficient numerical algorithm based on the Alternating Direction Method of Multipliers (ADMM) and provide an analysis of its convergence. Finally, the effectiveness of the proposed algorithm are demonstrated through extensive experiments on various images.
Read the full abstract
Computer Vision
JEDI: JEPA-to-Edge Distillation for Efficient Cropland Segmentation from Satellite Imagery
Large vision models provide useful representations for remote-sensing segmentation but are often too expensive for deployment at the satellite or field edge. Existing feature-level distillation methods also tend to assume similar teacher and student architectures and often stop feature alignment when task training begins. We introduce JEDI (JEPA-to-Edge Distillation), a two-stage framework that transfers representations from a large I-JEPA Vision Transformer teacher to a compact SegFormer student. First, JEDI aligns the student's terminal representation with the teacher's token space using cross-architecture projection and spatial alignment. It then jointly optimizes supervised segmentation, temperature-scaled response distillation, and persistent feature alignment throughout task adaptation. On CalCROP21, JEDI-B0 achieves 68.0 mean Intersection-over-Union (mIoU) with 4.04M parameters, improving over the standalone student by 16.0 points and coming within 2.0 points of the 70.0 mIoU achieved by the 639M-parameter teacher. We evaluate SegFormer B0, B1, and B2 students with 4.04M, 14.33M, and 28M parameters, respectively. Across all three variants, JEDI consistently outperforms response-, structure-, channel-, and relational-distillation baselines under the same teacher-student setting. These results show that persistent representation alignment is especially valuable under aggressive compression, substantially reducing model size and computation while preserving segmentation performance.
Read the full abstract
Systems and Control
Trajectory Optimization via Schrödinger Bridge Sampling
We take a new look at the relation between finite-horizon trajectory optimization and Schrödinger bridge sampling. Viewed as inference, KL-regularized trajectory optimization is solved by sampling from a Gibbs–Boltzmann distribution whose energy is the trajectory cost, and the adjoint Schrödinger bridge sampler (ASBS) is a simulation-free diffusion sampler designed for exactly such unnormalized targets. Hard equality path and terminal constraints, by contrast, confine the admissible decision variables to a measure-zero feasibility manifold, on which the target must be redefined intrinsically. In particular: $(a)$ we analyze two complementary parametrizations; a rollout parametrization, in which the dynamics are eliminated and only the remaining constraints shape the manifold, and a double-shooting parametrization, in which states and controls are sampled jointly and the dynamics themselves become part of the manifold; $(b)$ we establish regularity conditions under which both admissible sets are smooth embedded manifolds; $(c)$ under compactness and path-connectedness assumptions, we sample from the resulting intrinsic Gibbs measures via Riemannian ASBS, treating strict inequalities through exponential slack variables. Experiments, including contact-rich locomotion and manipulation, demonstrate the effectiveness of both regimes.
Read the full abstract
Data Structures and Algorithms
Improved Upper Bounds for Dynamic Bin Packing of General, Unit-Fraction, and Power-Fraction Squares
This paper presents significant upper-bound improvements for dynamic 2D square bin packing, where square items arrive and depart over time and the objective is to minimize the peak number of concurrent active unit bins. In our model, repacking is permitted only within a destination bin upon item arrival; migration between active bins is strictly forbidden. By introducing a streamlined two-list algorithm and proving a tight $5/16$ occupied-area bound for Next-Fit Decreasing Height, we reduce the upper bound on the asymptotic competitive ratio for arbitrary squares from 4.2154 down to 3.918, breaking a longstanding theoretical ceiling. For restricted variants, we establish asymptotic competitive ratios of at most 3.356 for unit-fraction side lengths and 2.211 for power-fraction side lengths.
Read the full abstract
Distributed Computing
Interactive Debugger for Performance Portable Python HPC Kernels
We propose PKDB, the first interactive debugger for GPU and multithreaded low-level kernels written in Python. Python is widely used in high performance computing (HPC), with frameworks such as PyKokkos translating Python-embedded domain-specific languages to native code that runs across OpenMP-threaded CPUs and various GPUs. Yet interactive debugging support for such code is absent: developers resort to print statements, framework-specific assertions, or CPU-only execution, the last of which requires altering the program or its data and can mask device-specific bugs. PKDB enables standard interactive debugging like breakpoints, stepping, and variable inspection while preserving actual on-device execution without source modification. Beyond these fundamentals, PKDB introduces two advanced capabilities that exploit the dynamic nature of Python and PyKokkos: (i) Live code evaluation, which lets developers execute arbitrary Python expressions or entire kernels in the middle of a paused kernel without restarting the process; (ii) Kernel call site substitution, which allows an actively running kernel to be updated and reloaded on the fly, so only the kernel is recompiled and re-executed without restarting the application. Our performance evaluation on Intel, AMD, and NVIDIA CPUs, and NVIDIA and AMD GPUs shows that PKDB introduces limited overhead and is practical for everyday use while introducing critical debugging features to the Python HPC ecosystem.