Computation and Language
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Tuesday 11 August
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions. Yet those actions are the product: they fix cost and latency, decide how the system fails, and are the only auditable part of its behaviour. We make the action policy the measured object across 8 models, 6 parallel benchmarks and 41 languages (2.38M rollouts). The naive measurement fails: five confounds sit between raw trace similarity and any defensible claim, each able to flip a conclusion. Short traces score higher, empty traces score perfectly, unrelated traces agree by chance over half the time, the gap is capped by each model's reproducibility, and a model asked the same question twice in one language answers differently, leaving no baseline. We remove all five, and every correction makes the effect larger. Divergence proves structural, not sampling noise: it survives greedy decoding in every cell and stays flat as temperature rises, even as models grow less self-consistent. Normalised by their own reproducibility, four very different frontier models converge under greedy decoding, each keeping 71-73% of its action policy across languages, with model identity explaining only 5.7% of the variance. Below roughly 10B parameters it breaks down, and the ordering among smaller models is largely an artifact of a chance floor we measure by permutation rather than assume. Agents route non-English tasks through English; this pivot is causally load-bearing, confirmed by a pre-registered prediction across four models, and models will not abandon it when told to. Finally, a single trace-extraction regex, not the model, manufactured a multilingual failure: two worked examples raise one model's measured accuracy twenty-sixfold while its accuracy on readable outputs barely moves.
Graphics
WildFireGS: Physics-Based Wildfire Simulation in Large-Scale Semantics-Enriched Gaussian Splatting Forest Scenes
Climate-driven environmental change is driving an increase in both the frequency and severity of wildfire events, making accurate simulation and prediction critical for effective risk mitigation and landscape management. While recent physics-based wildfire models achieve high realism by explicitly simulating combustion, heat transfer, and fuel dynamics, they remain largely restricted to synthetic environments with complete and idealized knowledge of forest structure, limiting their applicability to real-world environments captured via aerial imagery. To provide a pathway toward real-world wildfire digital twins derived directly from observational data, we present WildFireGS, a physics-based wildfire simulation framework operating directly on large-scale, semantics-enriched 3D Gaussian Splatting forest reconstructions. Our approach bridges learning-based scene reconstruction and environmental simulation by augmenting Gaussian primitives with semantics and material properties that encode vegetation type and fuel characteristics. We introduce a particle-based combustion model that operates natively on Gaussian representations, simulating ignition, heat transfer, combustion, and flame propagation across complex forest structures. This enables direct physics-based simulation of fire behavior on reconstructed real-world environments, without requiring conversion to explicit meshes or volumetric grids. We demonstrate the modularity of WildFireGS through a rain-driven cooling mechanism in terms of an energy-sink process to realistically model fire containment. Evaluations on synthetic scenes and real aerial forest captures show physically consistent wildfire behavior, reproducing characteristic dynamics including propagation scaling with vegetation density, wind velocity, and terrain slope. In addition, we validate our model through novel firebreak experiments and biomass loss estimation.
Read the full abstract
Computer Vision
Every Packet Counts: Dispersing Information for Loss-Resilient Learned Image Compression
Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss, a common challenge in satellite and emergency communications. This vulnerability stems from non-uniform information distribution at the packetization stage and sequential decoding dependencies at the entropy coding stage. We propose an end-to-end loss-resilient image compression scheme that addresses both. Before packetization, we introduce an Inter-Channel Redistribution (ICR) mechanism to redistribute channel energy, preventing critical information concentrating in a small subset of channels. Then, an Interleaved Channel Grouping (ICG) strategy partitions latent channels in a strided manner to disperse information across packets, with each packet kept within constrained sizes. To limit cascading errors from lost packets, we adopt a two-layer dual-branch autoregressive structure to shorten the dependency chain. Extensive experiments demonstrate that our method consistently outperforms existing approaches in both reconstruction quality and stability. At 20% packet loss, it achieves an average PSNR gain of 1.84 dB over LossResilientLIC while reducing PSNR variance by an order of magnitude. Notably, trained under uniform random loss only, our model generalizes to bursty loss modeled by the Gilbert-Elliott channel, outperforming methods explicitly trained for such conditions.
Read the full abstract
Artificial Intelligence
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correctness regression costs O(2^|D|) in a prompt of |D| instructions. We name the resulting divergence catastrophic remembering, the inverse of catastrophic forgetting around which continual learning is organized. First, we characterize this phenomenon across 247,694 instruction lifetimes in 1,867 repositories: agentic prompts grow without bound, more than tripling over their lifetime (+226%), gaining +4.9 net instructions every commit; further, the older an instruction gets, the less likely it is to be deleted (log-hazard -0.032/commit). Then, we show that prompt comments can halt the growth: inverting IFEval yields verifiable worlds whose optimal prompts are known, and there comments encoding latent reasoning remove 99.3% of excess instructions (+211.3% to +1.4%). Finally, applying the same inversion to WildIFEval, we show that prompt comments can improve real-world agentic instruction-following by up to 23.1%. If English is the new code, why don't we have comments yet?
Read the full abstract
Data Structures and Algorithms
A Linear-Time Approximation Scheme for the Densest Subgraph Problem
In the undirected Densest Subgraph Problem (DSG) the goal is to output a subset $S$ of vertices of a given graph $G$ that maximizes the quantity $|E(S)|/|S|$, where $E(S)$ is the set of edges in the subgraph induced by $S$. The problem is well studied in both theory and practice, and it admits natural efficient exact algorithms, as well as near-linear time algorithms with a $(1-\varepsilon)$ approximation ratio. However, all previously-known approximation schemes incur logarithmic factors in the size of the graph or other parameters of the graph. This raises the question of whether a linear time $(1-\varepsilon)$-approximation can be obtained for all $\varepsilon>0$. We answer this question affirmatively by providing a $(1-\varepsilon)$-approximation algorithm running in time $O\left(\frac{n+m}{\varepsilon^3}\log \frac{1}{\varepsilon}\right)$, where $m$ and $n$ are respectively the number of edges and vertices of $G$. To the best of our knowledge, this is the first truly linear-time approximation scheme for the problem (when $\varepsilon>0$ is a constant). Our algorithm uses assignments arising from a flow-based formulation together with a structural carving lemma. This lemma allows us to progressively carve "sparse" parts of the graph while nearly preserving the densest subgraph, allowing us to shift heavy computations to smaller instances, which eventually yields the mentioned runtime. Our framework also yields a $(1/2 -\varepsilon)$-approximation for the \emph{Densest At-Least-$k$ Subgraph Problem}, where in addition to maximizing the density, we require the subgraph to have at least $k$ vertices. Our algorithm runs in time $O\left( \frac{(n+m) \log^2 n \log \frac{1}{\varepsilon}}{\varepsilon} \right)$. This nearly matches the known $1/2$ approximation hardness while running in near-linear time.
Read the full abstract
Machine Learning
Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives
Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs). Despite these advances, existing studies remain highly diverse in their problem formulations, model architectures, training paradigms, and evaluation protocols, making it difficult to obtain a unified understanding of the field. In this survey, we present a unified review of cross-view feature matching. We first introduce a structured taxonomy covering feature extraction, single-type feature matcher, multi-type feature matcher, VFMs based methods, training strategy and robust estimation, providing a coherent framework for analysis and comparison. We further examine recent advances, distilling key design principles and highlighting the shift toward unified and generalizable correspondence models. We also provide a unified experimental benchmarking of representative state-of-the-art methods under consistent protocols, enabling fair and comprehensive performance comparisons. In addition, we discuss open challenges and future directions, including efficiency, robustness under extreme conditions, and cross-domain generalization. This survey aims to provide a comprehensive and structured reference for understanding the evolution, current landscape, and future development of cross-view feature matching in the era of vision foundation models.
Read the full abstract
Numerical Analysis
Randomized Tucker-Sketched GMRES
We address the problem of solving large-scale tensor-structured linear systems in the Tucker format. In this setting, standard iterative solvers such as GMRES face a fundamental bottleneck: the multilinear ranks of the Krylov basis vectors grow with the iteration count, leading to rapidly increasing tensor operation costs and memory requirements. To overcome these challenges, we propose two randomized algorithms within the sketched GMRES framework that replace full Arnoldi orthogonalization with short recurrences. The first, RHOSVD-Tucker sGMRES, uses randomized HOSVD with per-iteration rank selection, providing robustness across a wide range of problems. The second method, MLN-Tucker sGMRES, leverages the multilinear Nyström approximation with a fixed rank, enabling streaming computations; the streamability of the approximation further allows, at no additional cost, a memory-efficient reconstruction of the solution from a compact sketched representation of the Krylov basis. Both methods outperform standard low-rank Tucker solvers in symmetric and non-symmetric settings. Applied to inverse problems, the low-rank Tucker constraint acts as an implicit regularizer; combined with adaptive projected Tikhonov penalization and automatic regularization parameter selection, the methods yield stable reconstructions.
Read the full abstract
Computers and Society
Who Uses Open-Weight Models? China and the Shifting Geography of AI in Science
As LLMs have become a flashpoint for scientific research, computer scientists and STS scholars have advocated the use of open-weight models. Since LLM research has matured and more high-quality model families are available, have researchers adopted open-weight models? We present the first systematic study of model selection in scientific research, analyzing 21 million full-text articles through June 2026 from the Semantic Scholar Open Research Corpus (S2ORC). We employ a mixed NLP pipeline to extract model occurrences in article full text and determine whether they are used or merely mentioned by researchers. We divide our corpus into single- and multi-model family studies, which we take as a proxy for applied and foundational AI research. We find GPT-family models dominate both single- and multi-family research, but that both areas are becoming more diverse over time. In single-family papers, open-weight model use rises steadily, reaching 44.0% in 2026. However, we find that recent growth is driven by the availability of high-quality open-weight Chinese models. Further, a logistic regression model finds that open-weight adoption is heterogeneously distributed, estimating that researchers at Chinese institutions have 2.23 times the odds of using an open-weight model, accounting for 44.0% of the increase in open-weight adoption since 2023. A complementary multinomial model shows this association is concentrated in Chinese open-weight models: in 2026, their adjusted use is 37.1% among papers with Chinese affiliations, a 27.9 percentage-point over papers with no observed China link. These findings suggest that open-weight adoption in science is not a general turn toward open science, but part of a broader realignment of model ecosystems in which platforms and markets, and the sociocultural and geopolitical contexts which shape them, determine which AI systems become scientific instruments.
Read the full abstract
Networking
A Systematic Sample Size Analysis of ML-Based Path Loss Prediction for LPWAN
Low Power Wide Area Networks like LoRa are increasingly deployed for smart city applications, requiring accurate path loss prediction for effective network planning. Traditional (empirical) propagation models often exhibit limited accuracy in these scenarios. We investigate machine learning models for LoRa path loss prediction, systematically analyzing how prediction accuracy scales with training set size using real-world measurements from an urban deployment. Our approach employs a Random Forest with LiDAR-derived terrain features and k-Nearest Neighbors with coordinate data, comparing their performance against established empirical models and specialized LPWAN models. Under random pooled splits, both ML models consistently outperform the considered baseline models across the evaluated training-set sizes. At maximum training size, they achieve RMSE values below 6.5 dB compared to 9.7 dB for the best baseline, indicating accurate within-deployment interpolation. A leave-one-gateway-out check qualifies this result: RF shows placement-dependent transfer to held-out gateways, with moderate degradation for several gateways but larger errors for others, whereas coordinate-only k-NN degrades substantially when the gateway location is unseen
Read the full abstract
Artificial Intelligence
RTSKG: Building a Rail Transit Station Knowledge Graph Dataset
Rail transit systems play a vital role in urban mobility and economic development. As key components of such systems, rail transit stations function as critical transport hubs that enhance urban accessibility and stimulate development in surrounding areas. City-level rail transit station related tasks (e.g., ridership prediction) require large-scale urban data, but current studies often neglect complex interactions among various urban entities in terms of data organization. In this paper, to address the above issue, we build a Rail Transit Station Knowledge Graph (RTSKG) dataset which explicitly models the spatial and semantic interactions among different kinds of urban entities, to benefit city-level rail transit station related tasks. RTSKG integrates heterogeneous urban entities, such as rail transit stations, road segments, and points of interest, with a specially designed unified schema, and is accessible as Linked Data at https://w3id.org/rtskg/. Evaluations on station-area store recommendation and knowledge-enhanced ridership prediction demonstrate the effectiveness of RTSKG, highlighting its potential to support city-level rail transit station analysis.
Read the full abstract
Artificial Intelligence
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essential even when no sampled task activates them. Evaluation-guided compression can test these behaviors, but it introduces rollouts, cost, and dependence on the compression-time evaluation set. We present SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation. The intuition is explain once, reference many: state a repeated rule once at the scope where it applies, factor a repeated action sequence into a shared procedure, and keep only the differences as explicit exceptions. We formalize this intuition as a typed minimum description-length objective over a skill contract and a residual, subject to a hard coverage constraint for every extracted trigger, workflow edge, tool requirement, obligation, and output field. The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates. SkillZip has a one-shot mode with one structured extraction call and deterministic optimization, and a continual Zip-on-Write mode that integrates each self-evolution patch without replaying tasks or reparsing the full history. Through comprehensive experimental evaluations, we demonstrate the effectiveness and superiority of SkillZip in compression performance, generalizability, and cost overhead.
Read the full abstract
Computer Vision
Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction
Feed-forward Gaussian reconstruction has recently emerged as an efficient approach for driving scene reconstruction. However, prevailing LiDAR-based methods preserve the initial correspondence between observed points and Gaussian primitives, treating the initialized primitive set as the final representation. Unlike optimization-based 3DGS, these methods cannot accumulate gradients during training to determine how the scenes representation should be densified. Meanwhile, the shared sparse backbone only fuses observations from different timestamps implicitly, without explicitly aggregating cross-time evidence for individual primitives. In this paper, we present Learning Gaussian Structure (LGS), a framework that enhances both Gaussian structure and primitive attributes. Our key observation is that changes in local gradient responses induced by a prune or add intervention reveal whether the corresponding structural adjustment benefits reconstruction. Based on this observation, our Gaussian Densify Policy learns a Densify Map comprising Prune and Addition Scores from controlled interventions, and directly adjusts the Gaussian structure during inference. We further develop a compact Cross-Time Point Query that explicitly retrieves and aggregates neighboring features from Gaussian primitives at other timestamps for reliable attribute prediction. Extensive experiments on the Waymo Open Dataset and PandaSet demonstrate that LGS consistently outperforms existing methods.
Read the full abstract
Computer Vision
Foundation Model-Enabled Efficient Data Sampling (FEEDS): A label-efficient training strategy for pan-cancer, multi-tracer PET/CT datasets
Automated lesion segmentation in whole-body PET/CT imaging can assist clinicians with cancer detection, staging, and treatment planning across radiotracers and cancer types. However, training lesion segmentation models that capture variations in lesion size, distribution, and appearance requires large annotated datasets, whose creation is both time- and expertise-intensive. As a result, models trained on limited labeled PET/CT data often lack the accuracy and generalizability needed for clinical use. We present FEEDS (Foundation model-Enabled Efficient Data Sampling), a label- and compute-efficient learning strategy that uses vision foundation model embeddings to select the most informative and diverse unlabeled cases for expert annotation. Unlike unsupervised, semi-supervised, and active learning approaches, FEEDS is a one-step training paradigm requiring only a limited, representative training set, making it label- and compute-efficient. We train and validate FEEDS using the AutoPET-III dataset. We test its accuracy and generalizability on three held-out sets: AutoPET-III, DeepPSMA, and an internal Dartmouth-Hitchcock Medical Center dataset. We evaluate clinical utility at the voxel, lesion, and anatomic region level to assess performance in high-risk areas and treatment planning utility. FEEDS outperforms random-sampling-based labeling, pseudolabel-based semi-supervised learning, and training with limited labeled data alone. It generalizes across all three test sets, FDG and PSMA tracers, and multiple diseases, matching fully-labeled (100%) training performance with 70% less annotation burden. FEEDS addresses the challenge of label scarcity in an automatic lesion segmentation framework by providing a practical approach for constructing representative and diverse annotation queues from large, unannotated clinical repositories.
Read the full abstract
Computer Vision
Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues
Event cameras capture intensity changes asynchronously with high temporal resolution, requiring novel preprocessing methods for downstream tasks. Unlike static intensity snapshots, event data inherently encode information about scene dynamics and object motion, meaning that features derived from events can exhibit behaviors with no direct analogue in frame-based vision. In this paper, we analyze two features used in event-based corner detection—the eigenvalues of the structure tensor and the spatiotemporal density values—and show that they are motion cues. We hypothesize that these features, combined with local geometric information, can enhance motion estimation tasks. To validate this, we first theoretically analyze how the eigenvalues of the structure tensor at moving corner points relate to the direction of motion. We then design controlled experiments on a synthetic dataset, confirming that extending local geometric features with eigenvalues and density values provides complementary motion information and is robust to texture and shot noise. Finally, we integrate the proposed features into a state-of-the-art event-based optical flow network and evaluate on the real-world DSEC benchmark, where the added features consistently improve accuracy, with the largest gains in data-scarce scenarios and for lower-capacity models. The code for this paper can be found at: \href{https://github.com/hesamaraghi/static-in-frames-dynamic-in-events}{https://github.com/hesamaraghi/static-in-frames-dynamic-in-events}.
Read the full abstract
Computer Vision
CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering
Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics (e.g., CIDEr and SPICE) and LLM-as-scorer protocols struggle to verify dense factual claims, while existing QA-based alternatives generally offer lower probe density, narrower domain coverage, or no explicit alignment between individual questions and segmented image regions. We introduce CapProbe, a full-scene dense QA benchmark that turns detailed caption evaluation into region-aligned factual checking. Each image is decomposed into coarse semantic regions covering both foreground and background elements; for every retained region, we generate multiple-choice questions spanning 10 semantic categories, forming a dense checklist of probed visual facts. Guided by a two-tier taxonomy of 37 L1 domains and 219 L2 sub-domains, CapProbe comprises 346 images, 1,868 regions, and 25,650 questions, averaging 74 QA pairs per image. A language judge answers from the caption alone; an Uncertain option and Effective Accuracy provide a judge-dependent proxy for distinguishing unanswered probes from incorrectly resolved ones, while density-based metrics penalize verbose yet uninformative captions. The protocol is cost-effective: by converting unconstrained scalar scoring into structured MCQ reading, it reduces open-ended scoring bias while remaining judge-conditioned and yields relatively stable model rankings under a fixed reader. Experiments on 13 VLMs show large Coverage gaps across models, a clear competency-efficiency trade-off, and failure modes that sparse or overlap-based evaluation often misses. The benchmark data, annotations, and evaluation code will be released soon.
Read the full abstract
Multiagent Systems · Cross-listed from math.PR
Scaling Laws for Majority-based Opinion Dynamics in the Presence of Stubborn Agents
In a multi-agent system, there are often stubborn followers of specific opinions or beliefs. Motivated by this observation, in this paper, we aim to understand how stubborn agents affect the distribution of opinions in a network where both stubborn and non-stubborn agents interact with each other. To do so, we assume that all agents have an opinion in the set $\{0,1\}$ and each non-stubborn agent updates its opinion according to the $2k$-choices rule, where the agent samples $2k$ neighbours (including both stubborn and non-stubborn neighbours) uniformly at random and adopts the majority opinion among the sampled group of neighbours and itself. We assume that a proportion of agents, $\gamma_i$, are stubborn followers of opinion $i\in \{0,1\}$. It is natural to expect that the steady-state distribution of the opinions in the network will be dominated by the opinion with the larger proportion of stubborn followers. We show that while this is true, the time to reach steady-state depends heavily on the values of the parameters $\gamma_0$ and $\gamma_1$. When the individual values of these parameters, as well as their difference, are small, it can take an exponentially long time (in the network size) to reach the steady-state. In sharp contrast, when at least one of the parameters $\gamma_0$ and $\gamma_1$ is large, the network reaches the steady-state in a time that is only logarithmic in the network size. Hence, there exists a sharp phase transition in the network dynamics based on the proportions of stubborn agents. We also characterise the behaviour of the system when the parameters $\gamma_0$ and $\gamma_1$ lie on the boundary of the phase transition. In this boundary region, we show using Stein's method that the dynamics are driven by a diffusion process which takes polynomial time to mix.
Read the full abstract
Artificial Intelligence · Cross-listed from quant-ph
Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent Memory
We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-accessible boundary state and later answers a query. We count communication $B$, persistent instance-dependent memory $M$, and local work $D$; classical recurrence, caches, tools, and recomputation are allowed and charged. The central result is a boundary-preserving semantic-compilation theorem. It maps a finite one-way, streaming, or adaptive causal task into a semantic AI interface while preserving event order and access to past input. Classical boundary-state lower bounds and quantum-memory upper bounds transfer up to explicit compiler overhead, independently of the finite-precision recurrent architecture. Two applications have classical semantics. Matched-entity synopsis QA inherits the hidden-matching separation between $O(\log N)$ qubits and $\Omega(\sqrt{N})$ classical boundary bits. Continual requirements auditing inherits a Max-$k$SAT streaming separation: a recurrent solver uses $O(\log^5 n\log(1/\delta))$ qubits and polylogarithmic classical workspace to obtain a $0.7172$-approximation, whereas every classical one-pass finite-information solver attaining that ratio requires $\Omega(\sqrt{n})$ coordination width. As a quantum-native compiler test, a stabilizer latent-state dialogue uses $n$ qubits, while every exact finite-state classical causal online realization satisfies $B+M \ge \frac{1}{2}n^2+(\frac{3}{2}-\log_2 3)n+O(1)$. The source protocols, streaming algorithms, and stabilizer witness are imported; the new result is their architecture-independent semantic transfer. These are memory and coordination separations, not runtime or empirical advantages for present-day language models. The stabilizer result assumes exact simulation and ideal noiseless quantum memory.
Read the full abstract
Computer Vision
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains. Many concerns arise regarding the decision-making process of its models, mainly due to deep neural networks outperforming their peers at the cost of ambiguity in feature extraction and prediction. Consequently, in critical domains such as remote sensing, where high-resolution imagery must be analyzed using black-box models, the lack of transparency limits trust in these models and, thus, their adoption. In light of this reality, explaining and understanding the complex decision-making process of AI models has become essential. Explainable AI (XAI) aims to bridge this gap by providing insights into how and why certain decisions are made. While significant progress has been achieved in explaining image classification tasks, image segmentation still offers considerable room for improvement. In this context, this paper proposes an entropy-centric XAI method for semantic segmentation. Moreover, a new XAI evaluation methodology is proposed to efficiently measure the relevance of the regions highlighted by the proposed XAI method. Experimental results demonstrate the superiority of the proposed XAI method compared with recently adapted XAI methods for semantic segmentation.
Read the full abstract
Robotics
Deployment Is Not Destiny: Robot Recomposition in the Field with Unseen Software, Hardware, and Compute Payloads
The tight coupling of subsystems in most robots, though a natural consequence of their complexity, leads to monolithic designs that are time-consuming and difficult to adapt after initial deployment. To address this challenge, we present a framework and supporting abstractions for recomposition during runtime that enable robots to quickly integrate previously unseen modular software, hardware, and compute payloads. Our approach allows non-expert users to quickly add new capabilities in the field through a true plug-and-play process. Crucially, new resources are not only immediately available to a host robot but are also shared with distributed peers, enabling compute-constrained systems to access powerful new remote capabilities. Our framework reduces reconfiguration time to a matter of minutes with no developer intervention, in stark contrast to the hours of expert effort often required for traditional manual integration. We demonstrate our method in two disaster response scenarios, including radioactive source localization at an operational nuclear reactor facility and a thermal-guided search for people in dark, difficult-to-reach spaces. These demonstrations show how in-field recomposition provides timely, flexible, and accessible adaptation to dynamic requirements, representing a critical step toward creating robots that can quickly evolve alongside the tasks, technologies, and environments they support.
Read the full abstract
Machine Learning
Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training
Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to materialize for a batch of $n$ examples. Sampled softmax reduces this cost by restricting the objective to only $k \ll K$ candidate negative items, resulting in an $O(nk)$ memory. However, for a fixed budget $B = n k$, it remains unclear whether one should prioritize larger batches or the inclusion of more negative items. We address this question by analyzing sampled-softmax training under a fixed memory constraint. Under standard smoothness and variance assumptions, our theoretical evidence suggests that the fastest convergence arises from an $ n \sim B, k \sim 1$ allocation. So, an actionable rule is to include as many objects as possible given computational constraints. Our theory is supported by controlled synthetic and synthetic and four real sequential recommendation benchmarks, including MovieLens-20M. The suggested configuration achieve faster convergence and better final recommendation quality than imbalanced alternatives within the same memory constraint. These findings provide a theoretical and empirical foundation for configuring memory during the training of recommender systems. Code, reproducibility materials, and all scripts for generating figures are available at https://anonymous.4open.science/r/LimitedMemoryRule-BBFB
Read the full abstract
Data Structures and Algorithms
The Minimum-Weight Mixed Dominating Set on Threshold Graphs
We study the minimum-weight mixed dominating set problem on threshold graphs. In this problem, vertices and edges have weights, and the goal is to find a mixed set of minimum total weight that dominates every vertex and edge of the graph. We first show that arbitrary weights can be reduced to non-negative weights without changing the asymptotic running time. By adapting a reduction to the minimum-weight edge cover given in Ferrarini, Kober, Lancini, and Yuditsky, we obtain an $\mathcal{O}(n^5)$-time algorithm for the minimum weight mixed dominating set problem on threshold graphs.
Read the full abstract
Information Theory
Twisted Conjugacy and the Classification of Induced Centrosymmetric Alternant Codes
This paper presents a classification of induced centrosymmetric alternant codes through the study of the automorphism structures inherited from Generalized Reed–Solomon (GRS) codes. We introduce the twisted conjugation action naturally associated with projective semilinear transformations and establish its correspondence with ordinary conjugacy in the projective semilinear group. This correspondence enables the application of Shintani's theorem to classify the $\gamma_{p^j}$-similarity classes of involutions. As a consequence, we obtain necessary and sufficient conditions for an alternant code to admit a centrosymmetric structure induced by a projective semilinear automorphism. The resulting classification unifies the different families of induced centrosymmetric alternant codes within a common automorphism-based framework.
Read the full abstract
Numerical Analysis
Diffusion Quasi-Monte Carlo
We study high-dimensional numerical integration with respect to complex target measures using diffusion-based transport maps and randomized quasi-Monte Carlo (RQMC). Score-based diffusion models induce a deterministic probability flow ODE that transports a simple prior to the target, suggesting a principled way to transform low-discrepancy points on the unit cube into informative samples. We construct a cube-to-target map by composing a Gaussian base transformation (the component-wise inverse Gaussian CDF) with an Euler-discretized probability flow ODE. To retain unbiasedness under transport approximation, we formulate integration as importance sampling (IS) on the cube. Our main result provides verifiable conditions under which the resulting IS integrand satisfies the boundary growth condition, implying an $O(N^{-1+\epsilon})$ RMSE for scrambled nets. We then establish these conditions for diffusion probability-flow transport under mild bounded-derivative assumptions on the learned vector field, explicitly controlling the boundary singularities introduced by the inverse Gaussian CDF. Experiments range from a 2D mixture to 784D images and a 40,960D conditional vorticity-assimilation task; in the latter, blocked scrambled Sobol' sampling reduces the randomization standard deviation of nonlinear accuracy metrics at essentially unchanged online denoising cost. Together, these results give a theoretical and empirical foundation for combining diffusion generative modeling with high-precision RQMC integration.
Read the full abstract
Machine Learning
Uncertainty-Aware Deep Learning for Genomics Applications: Insights from an Empirical Study
Deep learning models have emerged as the standard computational tool for a wide range of applications in genomics. Yet, uncertainty quantification (UQ) — and more specifically, the reliability of different uncertainty estimates in this domain — has received little systematic attention. This work presents an empirical analysis of UQ in deep learning models, focusing on genomics applications. In a series of experiments, we contrast Deep Ensembles, Bayesian Neural Networks, and Monte Carlo-dropout methods. We assess their ability to quantify uncertainty in different scenarios, accounting for common dataset characteristics in two genomic application areas and modalities: sequence-to-activity models and single-cell expression analysis. Our systematic comparison framework provides guidelines for the applicability and reliability of UQ methods in genomics, highlighting their strengths and limitations in different scenarios. Our results indicate that Bayesian Neural Networks give the most consistent and directionally specific uncertainty response to class imbalance and out-of-distribution data in the tested settings, and mark the corrupted classes under label noise, at a higher computational and tuning cost. MC-dropout matches them on the sequence data, but is uncertain about every cell on the single-cell data, and deep ensembles respond less specifically. Moreover, we show how uncertainty scores can be used to select high-quality predictions in protein–RNA interactions.
Read the full abstract
Computer Vision
A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa
The application of computer vision in agriculture has shown significant potential for improving crop monitoring and precision farming. However, many existing approaches rely on controlled datasets that do not adequately represent realworld farming conditions, particularly in underrepresented regions such as Africa. This study presents a comparative evaluation of six object detection models YOLOv5, YOLOv8, YOLO11, YOLO26, Faster R-CNN, and RT-DETR using a real-world dataset, AgriAISeg 1 , collected manually from Nigerian farms. AgriAISeg comprises 3,382 images of sesame, cabbage, and tomato crops captured under varying environmental conditions, including changes in illumination, occlusion, and viewing perspectives. Models were trained, and performance was assessed using precision, recall, mAP@0.5, and mAP@0.5:0.95. The results show that RT-DETR achieved the highest overall performance with a precision of 0.768 and mAP@0.5:0.95 of 0.624, while YOLOv8 and YOLO11 also demonstrated strong and consistent performance. In contrast, Faster R-CNN recorded significantly lower accuracy, with an overall mAP@0.5 of 0.466, indicating reduced effectiveness under complex field conditions. In addition, YOLO-based models exhibited superior training efficiency compared to Faster R-CNN.These findings demonstrate that modern one-stage and transformer-based detectors provide more reliable and efficient solutions for plant detection in realworld agricultural environments.
Read the full abstract
Machine Learning
Efficient Hypergradient Descent for Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. We address this challenge by showing that, at the inner optimum, the Hessian of the inner objective is proportional to the Fisher information matrix of the policy, yielding a structured Fisher-based hypergradient closely related to Natural Hypergradient Descent. To address the resulting scalability bottleneck associated with large Fisher matrices, we approximate the required inverse-Fisher-vector product using a streaming spectral sketch, avoiding explicit construction of the Fisher matrix. We evaluate our approach against a first-order stochastic bilevel baseline across discrete- and continuous-control environments. The results demonstrate competitive policy performance and strong reward-ranking quality, while Fisher sketching reduces curvature-storage complexity and can improve computational efficiency relative to an explicit Fisher solver.
Read the full abstract
Computer Vision
HUI360: A 360{\deg} Egocentric Dataset and Baselines for Human-Robot Interaction Anticipation
As robots increasingly operate in human-populated environments, anticipating human intentions is essential for enabling proactive and socially aware behavior. Automatic anticipation of human-robot interactions is thus emerging as a crucial perception challenge for embodied agents. To this end, we introduce HUI360, the largest dataset for human-robot interaction anticipation in the wild and its set of baselines. The dataset was collected from a mobile robot, in the wild, over multiple days within a 3-month period, and in several environments, capturing natural, spontaneous behaviors from both passersby and users, and encompassing a diverse range of individuals. This variety enables evaluating and improving the generalization capabilities of interaction anticipation models. We designed a pipeline and share code for automatic interaction annotation in arbitrary 360-degree equirectangular videos, along with interfaces for manual refinement. Using this pipeline, we release the HUI360 open set of 1M pre-processed annotations, including detailed 2D poses, facial keypoints, and segmentation masks, obtained using state-of-the-art computer vision methods and manually curated to ensure high-quality tracking and interaction annotation. Additionally, we release the raw panoptic 360-degree images captured from the robot's egocentric viewpoint (on demand, for research purpose only in compliance with GDPR). Finally, we establish benchmark baselines for interaction anticipation, including the first cross-dataset evaluations for this task: to this end, we also release 6M annotations for another existing in-the-wild outdoor dataset collected from a mobile robot (SSUP-HRI). Dataset and code can be found at https://hucebot.github.io/hui360.
Read the full abstract
Computer Vision
3D Weighted Geometric Graph Neural Networks for Sheep Facial Pain Assessment
Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of the 3D anatomy of sheep and cross-landmark spatial relationships that are intrinsic to the clinically proven Sheep Pain Facial Expression Scale (SPFES). This paper presents the 3D Sheep Pain Facial Expression System (3D-SPFES), a novel, monocular depth-aware geometric graph neural network system that integrates each SPFES facial landmark, such as the ears, eyes, and nose, into 3D Euclidean space estimated from a single RGB camera by using VideoDepthAnything, thus preventing the need for specialized depth hardware. Each landmark node includes a feature vector containing its 3D spatial coordinates, estimated surface normal, and facial attribute class embedding. Edges linked to nodes are assigned weights based on an aggregate metric that combines both Euclidean distance and surface co-planarity in a 3D space. A Weighted Geometric Graph Neural Network (WG-GNN) studies this graph using $\mathcal{K} = 3$ geometry-aware message-passing layers enhanced by a scaled dot-product attention method that selectively enhances anatomically relevant inter-landmark messages. The resultant node embeddings are combined into $\mathcal{O} = 3$ pain-level clusters and integrated into a Normalized Pain Score (NPS) within the range of $[0, 100%]$ a confidence-weighted, SPFES-derived scoring method.
Read the full abstract
Computation and Language
Multiclass Sentiment Analysis for Identifying Political Viewpoints
The rapid growth of social media has created vast amounts of political discourse, which provides valuable opportunities to analyze public opinions and identify different political perspectives. Sentiment Analysis (SA) is a core task in Natural Language Processing (NLP) that allows the computational study of attitudes and opinions in textual data, and has become increasingly important for understanding political discourse. In this work, we investigate multiclass sentiment analysis of political view- points on social media, that is to automatically discriminate multiple sentiment classes over political issues and figures. To solve this task we design and evaluate two machine-learning approaches based on XGBoost and BERT. We train and evaluate the models on a labeled dataset of political social media posts using standard classification metrics. The experimental results show that the XGBoost model reaches an F1-score of 0.2835 and the BERT- based model reaches an F1-score of 0.2806 on the test set. These results demonstrate the challenge of classifying complex and contextualized political discourse sentiment and provide a baseline for future research in multiclass political sentiment analysis.
Read the full abstract
Artificial Intelligence
V-FiLLM: Verified Financial LLM Reasoning Benchmark
While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less explored. We introduce V-FiLLM, a framework that generates financial reasoning benchmarks from executable computation trees grounded in real tables, yielding items whose answers are correct by construction. Trees are evaluated symbolically to obtain ground truth and rendered into natural-language questions, removing any model from the labeling loop, so items can be generated at arbitrary scale without annotation cost and without inheriting a generator's error rate. V-FiLLM exposes four independently controllable axes of difficulty including computation depth, expression breadth, financial concept complexity, and context size. By evaluating on open-source models, we find that accuracy falls up to 51% as reasoning depth increases, and up to 47% points under adversarial numerical perturbations, highlighting remaining challenges in robust financial reasoning over tables. We further show that lightweight LoRA fine-tuning on verified chain-of-thought traces improves accuracy from 81.1% to 85.6% on held-out problems and outperforms the base model by 5% points on FinQA (Chen et al., 2022a), s), suggesting that targeted, low-cost adaptation is a promising direction for compositional reasoning in financial QA.