Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Sunday 16 August

Computer Vision

ES3D: Embedding Semantics into 3D Space for Component-Aware Editing

Existing 3D editing methods have made notable progress in controllability, yet they remain limited in several important ways. Most approaches rely on text-driven editing, which struggles to express fine-grained visual changes intended by the user. Moreover, many methods require manually supplied 3D masks or introduce unintended changes to regions that should remain untouched. These limitations largely arise from the absence of fine-grained semantic understanding, making it difficult for existing models to retrieve or modify specific 3D components. We introduce ES3D, a framework that embeds semantics directly into 3D space, enabling component-aware retrieval and editing of a 3D asset conditioned on multiple local reference images and optional text queries. We first construct a 3D semantic embedding by projecting multi-view semantic features into the voxelized space of the asset. We then perform 3D component retrieval by computing feature similarity between the 3D semantic embedding and the semantic embeddings of image or text queries. For editing, we employ a pretrained 3D generative model with an inpainting mechanism to modify the retrieved components guided by user-provided images while preserving the rest of the asset. Overall, ES3D is a 3D editing framework that retrieves editable regions based on semantic cues and uses multiple images as conditions. Extensive experiments demonstrate that ES3D produces geometrically consistent and semantically coherent edits, enabling robust image-based and text-assisted control for 3D editing.
Read the full abstract

All authors Xuancheng Jin, Rengan Xie, Jiayuan Lu, Wenting Zheng, Rui Wang, Yuchi Huo, Lincheng Li, Yingfeng Chen

Robotics

Making two action heads agree: coordination mechanisms and a runtime collapse certificate for flow-matching policies

A dual-representation flow-matching policy decodes each predicted motion into joint and end-effector spaces, and the residual between the two kinematically equivalent decodings provides a physically interpretable runtime signal. On multimodal tasks, however, independently sampled branches may choose different valid modes, causing false alarms. We study how to coordinate the two branches and at what cost. Across two robot environments and a non-robotic testbed, the tested mechanisms fall into four classes. An auxiliary latent shared by both branches but absent from the flow-matching construction is erased at the population optimum, a provable dead end confirmed within a prespecified 2% equivalence band. Sharing source noise can coordinate or anti-coordinate: its effect changes sign with the representation map and tracks the alignment of decoder mode basins. Consistency regularization gives intermediate coordination but reduces the valid-pair rate, while training-supported discrete partitions achieve near-ceiling coordination robustly. We further derive a chance-corrected coordination bound based only on each branch's Gini-Simpson diversity, yielding an attainable region and a label-free certificate that separates coordination from collapse when zero mismatch is ambiguous. On LIBERO-Plus, benign multimodality adds 1.57 percentage points of false alarms to the residual, which remains the strongest evaluated failure signal; the preregistered token intervention does not meet its false-alarm criterion or produce a seed-robust detection change. Code, models, and per-run configurations are available at https://github.com/kimo423/dual-head-coordination.
Read the full abstract

All authors Jinhui Sun, Wei Zhou, Bowen Yang, Xinliang Xiao, Li Yang

Artificial Intelligence

Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign

We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign. We introduce PROPAGIA, a corpus of 2,646 propagandist French articles from the Storm-1516/CopyCop campaign disclosed by VIGINUM and INSIKT GROUP in 2025. For comparison, we rely on SIPA, a corpus of human-written French mainstream press from the same period. Using topic modeling, vagueness and sentiment analysis, we first isolate persuasion techniques characteristic of propaganda, with PROPAGIA far exceeding SIPA in vagueness, subjectivity and negativity, and citing fewer sources. We then find prompt instruction leaks on 50 of the 84 PROPAGIA websites, including a verbatim ten-point editorial specification accounting for several of these differences, together with high cross-article redundancy. Finally, we show that rewriting-based detection supports INSIKT GROUP's attribution to the Llama 3 family, but also suggests the involvement of Mistral-family models.
Read the full abstract

All authors Benjamin Icard, Elouan Vuichard, Louis Lefebvre, Lila Sainero, Thomas Girault, Alice Breton, Tanguy Launay, Gauvain Bourgne, Morgane Casanova, Guillaume Gadek, Victor Klötzer, Michel Le Nouy, Guillaume Gravier, Jean-Gabriel Ganascia, Paul Égré

Robotics

Some Modifications to Our End-to-End UAV Planner

The one-stage planner YOPO maps a single depth image and the robot state directly to a set of candidate trajectories, trained by backpropagating through differentiable trajectory costs. This yields dense, geometrically informative supervision, but inherits the pathologies of soft-constrained optimization: the safety cost competes with the smoothness and goal-reaching terms, is non-convex across homotopy classes, and the single-piece polynomial is limited in expressiveness. In this report, we summarize several effective modifications. We adopt a two-piece MINCO parameterization, trading time for smoothness without altering the trajectory's spatial profile. We further lift YOPO's multi-modal prediction to span distinct homotopy classes, treating each motion primitive as a homotopy anchor that confines the trajectory to a feasible basin - without explicit safe-flight-corridor construction or front-end search. For dynamic feasibility, we impose barrier penalties on velocity and acceleration together with a curvature-dependent speed limit whose gradient acts only on the velocity, producing an adaptive-speed behavior that decelerates in cluttered regions or sharp turns. We replace score regression with a ranking loss, preventing small score errors from reordering the candidate set. These yield richer trajectory representations, safer obstacle avoidance, and more direct flight paths.
Read the full abstract

Computers and Society

An AI-Based Adaptive Learning Platform for Multilingual and Low-Resource Educational Contexts: A Case Study on Nigeria

Educational platforms in under-resourced and multilingual contexts, such as Nigeria, often struggle with limited personalisation, inadequate language support, and weak curriculum internationalisation, leading to reduced learner engagement and inclusivity. This paper presents an AI-based adaptive learning platform designed for multilingual and low-resource educational contexts, with a case study on Nigerian Pidgin English. The system integrates fine-tuned large language models (LLMs) within a personalised and adaptive learning (PAL) framework, addressing linguistic inclusivity and computational constraints in resource-limited environments. To enhance linguistic alignment, a curated Nigerian Pidgin corpus was developed and used to fine-tune an instruction-tuned LLM. The study further investigates model optimisation through multi-level quantisation (4-bit, 5-bit, and 8-bit), enabling systematic analysis of trade-offs between semantic fidelity and computational efficiency. Experimental evaluation combines automatic semantic metrics (BLEU, ROUGE-L, BERTScore, perplexity, lexical diversity) with human-centred cultural assessment conducted by native speakers. Results demonstrate that higher-bit quantisation improves semantic preservation and structural coherence, while lower-bit models offer reduced inference latency with minimal degradation in instructional quality. The findings establish a deployable, resource-aware intelligent learning system that balances semantic robustness, cultural relevance, and computational efficiency. This work contributes an experimentally validated framework for adapting large language models to low-resource languages while maintaining practical feasibility for scalable educational deployment.
Read the full abstract

All authors Everistus Ugochukwu Nwogo, Isibor Kennedy Ihianle, Pedro Machado, Jordan J. Bird, Ahmad Lotfi, Ahmad Abdulnasir Shuaib, Isaac Ibukun Akinwumi, Jonathan Oluranti

Artificial Intelligence

Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps

Foundation models (FMs) increasingly support multimodal and geospatial reasoning, yet it remains unclear whether cartographic principles designed for human perception are equally effective for machines. Focusing on sequential choropleth maps, we examine how hue palette, color ordering, and lightness contrast influence FM spatial reasoning. We construct a controlled benchmark of 5,760 maps and 28,800 questions spanning Attribute Identify, Spatial Recognition, Compare, Rank, and Pattern Delineate, and evaluate 21 open-source and proprietary multimodal FMs. Results show that hue choice has limited and inconsistent effects, whereas disrupting sequential color ordering substantially reduces performance, especially for comparison and ranking. Reduced lightness contrast also consistently impairs reasoning, while increasing contrast beyond sufficient separability provides only marginal gains. LoRA fine-tuning improves overall accuracy but preserves these relative sensitivities. Additional factorial experiments further indicate that errors arise from color-and-legend decoding, spatial reasoning, and the integration of thematic attributes with spatial structure. These findings show that conventional sequential ordering and sufficient contrast remain important for machine map understanding and provide empirical guidance for AI-friendly cartographic design.
Read the full abstract

All authors Yonghe Sun, Zhenjia Liu, Hua Liao, Wenjia Xu, Nai Yang, Weihua Dong, Zhiwei Wei

Multimedia · Cross-listed from eess.AS

CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects

Automatic video dubbing in the wild remains fundamentally limited by two competing constraints: hierarchical methods depend on brittle, multi-stage preprocessing pipelines that severely restrict data scalability and practical deployment, while holistic approaches operating on uncropped video suffer from weak temporal alignment and speaker-utterance ambiguity in multi-speaker settings. To overcome these limitations, we propose CineDub, a unified diffusion-based model that achieves precise multi-speaker dialogue dubbing directly from uncropped videos, without face cropping or speaker diarization. Central to our approach is the Implicitly-Coupled Holistic Conditioning (ICHC) paradigm, where holistic visual representations and a semantic-bundled transcription format are encoded independently, yet implicitly coupled through cross-modal training to resolve speaker ambiguity and enable precise multi-speaker multi-turn dialogue dubbing. Building on the unified temporal cues captured by holistic visual features, we further extend CineDub to joint speech and audio generation. We introduce an Ambient-to-Linguistic Curriculum Learning (ALC) to mitigate sub-task degradation, and a decoupled textual branch control mechanism to resolve cross-prompt interference during simultaneous generation. We also release two in-the-wild benchmarks, CineDub-Multi for multi-speaker dialogue dubbing and CineDub-SA for video-to-speech-and-audio (V2SA) generation, to enable evaluation under realistic conditions. Experiments show that CineDub achieves state-of-the-art results on established single-speaker dubbing and video-to-audio benchmarks while excelling in multi-speaker dialogue dubbing and acoustically coherent joint generation.
Read the full abstract

All authors Yusheng Dai, Kangdi Wang, Baolong Gao, Yuxuan Jiang, Weiqiang Wang, Qiuhong Ke, Jianfei Cai

Computer Vision

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust. In real-world computer vision tasks, these models often operate on complex images containing background noise and are heavily annotated. To make such models explainable, Concept-based Explainable AI (CXAI) methods need to be assessed for their applicability and problem-solving capacity. In this work, we explore CXAI use cases in multi-label classification by training two DNNs, VGG16 and ResNet50, on the 20 most annotated labels in the MS-COCO dataset (Microsoft Common Objects in Context). We apply two CXAI methods, CRP (Concept Relevance Propagation) and CRAFT (Concept Recursive Activation FacTorization), to generate concept-level explanations and investigate the overall evaluations. Our analysis reveals three key findings: (1) CXAI highlights learning weaknesses in DNNs, (2) higher concept distinctiveness reduces label and concept confusion, and (3) environmental concepts expose dataset-induced biases. Our results demonstrate the potential of CXAI to enhance the understanding of model generalizability and to diagnose bias instigated by the dataset.
Read the full abstract

Networking

WiFiSpectralJam: A Large-Scale Open Wi-Fi Spectral Scan Dataset with Controlled RF Jamming

WiFiSpectralJam is a Wi-Fi spectral-scan dataset comprising 14.52 GB, 96,090 CSV files, and 522,771,130 ordered spectral observations using commodity Wi-Fi sensing hardware. Measurements were acquired with a Raspberry Pi Compute Module 4 equipped with a Qualcomm Atheros QCA9880 802.11ac network interface and the Linux ath10k spectral-scan interface. The dataset spans active and passive scan modalities across the 2.4 and 5 GHz bands and includes real-world benign background captures, benign RF-chamber floor captures, and controlled RF-jamming captures generated with a HackRF One. Jamming conditions vary by transmit power, target channel, and, in the active subset, waveform type. The release provides the raw spectral-scan records together with a file-level metadata manifest, derived spectral-summary features, validation outputs, and reproducible benchmark protocols. These resources support reuse in RF interference characterisation, jamming detection, spectrum monitoring, distribution-shift evaluation, and machine-learning studies using commodity-NIC spectral measurements. The dataset is publicly available at: https://www.kaggle.com/datasets/daniaherzalla/radio-frequency-jamming/data.
Read the full abstract

All authors Dania Herzalla, Govind Singh, Willian T. Lunardi, Martin Andreoni

Machine Learning

FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction

Diffusion models have recently shown strong potential for multivariate time-series anomaly detection by learning the distribution of normal data through iterative denoising. Existing diffusion-based approaches, however, typically perform anomaly detection after completing the reverse diffusion process, relying primarily on the final reconstructed signal and overlooking informative representations produced during denoising. This design incurs substantial computational cost and limits the use of intermediate diffusion information for anomaly detection. In this paper, we propose FirstDiff, a diffusion-based anomaly detection framework based on the observation that the predicted diffusion noise at the initial reverse-diffusion evaluation already contains sufficient information for accurate anomaly detection. FirstDiff models the statistical distribution of predicted diffusion noise under normal behavior using validation data, enabling anomaly inference from a single denoising-network evaluation rather than completing the reverse diffusion trajectory. To model complex temporal and inter-sensor dependencies, FirstDiff employs a Diffusion Transformer as the denoising backbone. Extensive experiments on five public benchmark datasets demonstrate that FirstDiff achieves state-of-the-art performance while reducing diffusion inference from the full reverse trajectory to a single denoising-network evaluation.
Read the full abstract

Software Engineering

An Empirical Study on the Impact of Normalized Use-Case Specifications on Traceability

Traceability link recovery between requirements and source code is vital for software quality assurance and evolution analysis. Although automated traceability techniques have advanced greatly, the large semantic gap between vague natural-language requirements and precise source code still hinders accurate link recovery. Most existing approaches optimize traceability algorithms yet ignore the inherent quality of requirement descriptions, which prevents fundamental reduction of the semantic gap. This work proposes a requirement-oriented normalization method. Using controlled natural language and large-language-model-based prompt engineering, raw requirements are decomposed and converted into standardized use-case specifications to strengthen semantic representation and mitigate semantic divergence. Evaluated on four public datasets under two typical traceability frameworks, the normalized specifications improve tracing performance for semantically ambiguous raw requirements. However, over-normalization may degrade results for already high-quality requirements closely aligned with code semantics. The results validate source-side requirement normalization as a promising strategy for traceability improvement and reveal its applicable boundaries for practical usage.
Read the full abstract

All authors Luoyuan Shi, Yuanzhao Zhai, Dawei Feng, Jialin Zhao, Zhaoxie Xu, Bo Ding, Huaimin Wang

Machine Learning

Learning Auditable Classifier Models: Source-Disjoint Tree Ensembles

Predictive models in clinical and regulated settings must be accurate and fully auditable. Tree ensembles deliver strong accuracy on tabular data, but their sequential boosting couples structure discovery with coefficient estimation, making compact per-prediction auditing difficult. Interpretable alternatives impose structural constraints that limit expressiveness: generalized additive models typically restrict interactions to pairwise terms and post-hoc rule extractors produce overlapping rules that hinder compact interpretation. We introduce Residual Pattern Tree Ensemble (RPTE), a three-stage learning approach, that is built on three key principles: bounded feature budget, source disjointness, and separate coefficient estimation. Stage~1 builds a supervised symbolic feature vocabulary. Stage~2 grows shallow trees under a source-disjointness constraint, where each raw variable is allocated to at most one tree, and retains only the discovered tree structures. Stage~3 solves a single $\ell_1$-regularized logistic regression over leaf-region indicators, yielding jointly optimal sparse coefficients. This learning approach ensures that every prediction decomposes into an algebraic sum of named, non-overlapping rule contributions, enabling full auditability by design. Empirical evaluation on twelve clinical-domain binary classification benchmarks using repeated stratified 5-fold cross-validation shows that RPTE performs competitively against tuned opaque ensembles and interpretable baselines. RPTE reduces model inspection units by 9$\times$ to 87$\times$ relative to XGBoost and maintains lower audit complexity than EBM on all 12 datasets. RuleFit requires comparable or fewer inspection units on three datasets where its rule count is small, but without source-disjointness guarantees. The source code is available at \href{https://github.com/srikumar2050/hugiml-core}{this https URL}.
Read the full abstract

Discrete Mathematics · Cross-listed from math.CO

A method to identify the ordinary edges for symmetric traveling salesman problem based on frequency $K_i$s

The frequency $K_i$s ($i\in[4,n]$) are studied for symmetric traveling salesman problem ($TSP$) to characterize the structure properties of the edges inside and outside the optimal Hamiltonian cycle ($OHC$). Given a $K_i$ in $K_n$ where $i\in [4,n]$, the frequency $K_i$ is computed with the set of ${{i}\choose{2}}$ optimal $i$-vertex paths with fixed endpoints (optimal $i$-vertex paths) in the $K_i$. Given an $OHC$ edge in a $K_i$, it has a frequency bigger than $\frac{1}{2}{{i}\choose{2}}$ in the frequency $K_i$, and that of an ordinary edge outside the $OHC$ is smaller than $\frac{1}{2}{{i}\choose{2}}$. As the frequency of an edge is computed with the frequency $K_i$s, an $OHC$ edge of $K_n$ has an average frequency bigger than $\frac{1}{2}{{i}\choose{2}}$. It indicates an $OHC$ edge of $K_n$ is also one $OHC$ edge of a $K_i$ containing it. It also found that the probability that an $OHC$ edge has the frequency bigger than $\frac{1}{2}{{i}\choose{2}}$ increases according to $i\in [4, n]$ based on the frequency $K_i$s. For an ordinary edge outside the $OHC$, the probability that it has a frequency smaller than $\frac{1}{2}{{i}\choose{2}}$ increases according to $i$. Based on the findings, a method is given to identify the ordinary edges for $TSP$.
Read the full abstract

Computer Vision

Anatomical and Physical Supervision for CT-less PET Attenuation Correction: BIC-MAC 2026 Challenge

This report describes our submission to the Big Cross-Modal Attenuation Correction (BIC-MAC) 2026 Challenge for CT-less PET attenuation correction through multimodal pseudo-CT synthesis. We build upon a standard nnU-Net architecture and combine anatomical and physical supervision to improve both pseudo-CT quality and downstream PET reconstruction. Anatomical supervision is introduced through a frozen TotalSegmentator feature extractor, anatomy-guided structural constraints and patch sampling, while physical supervision is achieved using a differentiable attenuation correction factor projection loss based on multi-angle attenuation projections. Furthermore, the network is initialized with pretrained weights obtained from training on the SynthRAD Challenge MR-to-CT dataset. Minimal architectural modifications are applied, while performance improvements are pursued across the nnU-Net pipeline, including preprocessing, plans, and supervision design, among other components. Our final submission demonstrates the effectiveness of combining anatomical supervision, attenuation physics, and efficient nnU-Net scaling for CT-less PET attenuation correction.
Read the full abstract

Artificial Intelligence

PLeDO: Pain Level Detection for Osteoarthritis from EMR Data

Osteoarthritis (OA) is a progressive chronic joint disease resulting in a breakdown of articular cartilage and bone when damaged joint tissues are not able to normally repair themselves. The aim of this pilot research study is to understand the pain severity for OA from patients' primary care Electronic Medical Records (EMR), both from the structured medical data and the unstructured chart note data using information extraction, natural language processing and machine learning techniques. We propose SPaDe, a Synonym-based Pain level Detection tool to categorize patients into having mild or moderate-to-severe pain to understand diagnosis and treatment methods based on only the pain related expressions in the unstructured chart note. Expressions are subjective, objective, and influenced by cultural background and demography which poses a difficult challenge. Therefore, we improve the model by incorporating the medication information from the structured EMR data and pain scale related information from the chart note to propose an integrated pain level detection tool for OA called PLeDO. With the help of human labeled gold standard data, we demonstrate that both SPaDe and PLeDO can detect mild and moderate-to-severe pain from the EMR data to analyze and potentially improve the quality of care in primary care setting.
Read the full abstract

All authors Yuhao Chen, Jiahao Cai, Nafiz Sadman, Farhana Zulkernine, John Queenan, David Barber

Numerical Analysis

Maximal entropy dissipation numerical scheme for conservation law systems

This paper presents a numerical finite volume method for conservation law systems that are adapted to the principle of maximal dissipation. The general assumptions are the existence of a strictly convex entropy functional and the finite propagation speed property of a given system. The procedure is based on a numerical flux construction obtained by the minimization of the entropy functional in each time step. The scheme satisfies assumptions of the Lax-Wendroff theorem. A limiting solution obtained by this scheme is compared with the classical weak solutions obtained by the Glimm or the Wave Front Tracking algorithm for one-dimensional systems.
Read the full abstract

Machine Learning · Cross-listed from quant-ph

Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning

Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state. We propose Kraus-Parameterized Belief Reinforcement Learning, a pipeline in which a recurrent encoder, constrained to the Stiefel manifold, produces density-matrix estimates that are guaranteed positive-semidefinite and trace-normalized by construction, embedding quantum state geometry directly into the learning loop. A Proximal Policy Optimization (PPO) actor then maps these physically valid belief states to continuous control actions. On a simulated continuously monitored qubit, the resulting policy achieves stable feedback control, maintaining a measurement-conditioned belief fidelity of approximately 0.77-0.80 and exhibiting substantially lower return variance than a parameter-matched LSTM-history baseline across both nominal and out-of-distribution conditions. Although gains in raw target fidelity are modest, the geometric constraint guarantees a physically valid, interpretable belief representation and yields markedly more stable control under measurement inefficiency and abrupt dynamics switches. These results indicate that physics-informed neural memory is a practical inductive bias for reliable quantum feedback control.
Read the full abstract

Computer Vision

YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling

Pavement distress detectors are conventionally specialised for small objects, typically by adding a stride-4 detection head and replacing strided convolution with space-to-depth downsampling. This paper tests that premise against the annotation geometry of region level survey imagery and finds it fails: 1.28% of instances are small at 640 resolution while 70.37% are large, yet a stride-4 level would claim 75.3% of anchors, and complete misses rather than localisation errors dominate baseline failures. YOLO26-RD therefore reallocates the anchor budget, retaining the stride-4 branch as neck features but carrying no detection level there, and adds LearnableContrast, a 494 parameter per tile correction learned from the detection loss and active at inference, and EdgeSPD, a lossless space-to-depth downsampler gated by a fixed Sobel prior. Fifteen models were trained from scratch under one recipe, five scales each of YOLO26-RD and of matched YOLO26 and YOLOv12 families. Averaged over scales YOLO26-RD returns 0.790 mAP50 and 0.482 mAP50-95 against 0.776 and 0.471 for YOLO26 and 0.755 and 0.468 for YOLOv12; it exceeds both on mAP50 at every scale from s upward, and at m, l and x it leads on both metrics, twelve pairwise comparisons decided without exception. YOLO26-RD-l is the best of the fifteen at 0.809 mAP50 and 0.497 mAP50-95, improving on the YOLO26 reference by 0.031 and 0.030 and leading all six per class entries; every arm of a module ablation also exceeds that reference. The margin is thus a property of the architecture rather than of one tuned configuration, though three of the twelve margins lie inside the dataset 0.015 resolution limit and the held out split reproduces the ordering against YOLO26 but not YOLOv12 at scale x. As a TensorRT FP16 engine the released model sustains 98 frames per second on an entry level accelerator, against the 21 needed at 100 km/h.
Read the full abstract

All authors Sompote Youwai, Pawarotorn Chaipetch, Hathairat Samaikul, Theerayut Yonseng

Machine Learning · Cross-listed from eess.IV

Deep learning-based computed tomography (CT) derived body composition classifier for colorectal cancer patients

Background: Accurate body composition analysis using Computed Tomography (CT) scans is essential for assessing skeletal muscle area (SMA) and skeletal muscle density (SMD), key markers of nutritional status in cancer patients. Conventional manual methods are labour-intensive and require specialist expertise, limiting their routine clinical use. Therefore, this study serves as a feasibility and pilot investigation to explore the potential of deep learning-based automated regression for body composition analysis within a clinical workflow. Methods: Four deep learning architectures (AlexNet, UNet, GoogLeNet, and ResNet34) were trained to predict SMA, SMD, subcutaneous fat area (SFA), and visceral fat area (VFA) from CT scans of colorectal cancer patients. Systematic hyperparameter optimization identified the most accurate models, which were subsequently implemented in a web application for clinical use. Results: GoogLeNet achieved the best performance, with a mean percentage error (PE) of 4.96% for SMA prediction, while AlexNet reached 8.12% for SMD. Independent testing demonstrated robust accuracy, correctly classifying body composition metrics in 80% of cases. The web application delivered rapid and consistent outputs, supporting integration into clinical workflows. Conclusion: Optimized deep learning models, particularly GoogLeNet and AlexNet, can automate CT-derived body composition analysis with a Mean Percentage Error (PE) of 4.96% for SMA and 8.12% for SMD. These tools have the potential to streamline clinical practice by reducing the time and expertise required for manual segmentation. Further validation in larger, more diverse datasets is warranted.
Read the full abstract

All authors Eve Harling, Chattarin Pumtako, Bernd Porr, Donald C McMillan, Ross D Dolan

Computer Vision

Beyond Single Object: Learning 3D Relations with Large Language Models

We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison. We propose a framework for detailed object-level reasoning across multiple objects with three components: (1) MO3D (Multi-Object in 3D), an instruction dataset requiring fine-grained multi-object comparison; (2) Multi-3DLLM, using a minimal Patch-Interaction Transformer (PIT) that models inter-/intra-object relationships while preserving local geometry; (3) Mini-apps, two application-driven benchmarks (Shape Mating, Change Captioning) that probe geometric understanding for practical use. Recent 3D-LLMs and 2D-VLMs perform poorly on these tasks, lacking both comparison-centric design and geometric awareness. In contrast, Multi-3DLLM trained on our mixture data learns geometric reasoning, surpasses all baselines on MO3D, and provides positive transfer to single-object classification.
Read the full abstract

All authors Kohsuke Ide, Ryousuke Yamada, Yue Qiu, Xianzheng Ma, Yoshihiro Fukuhara, Hirokatsu Kataoka, Yutaka Satoh

Databases

Logos: Certified Order-Sensitive SQL Rewrites with Mechanized Semantics and LLM Guidance

SQL rewrite verification must account for duplicate rows, observable row order, and typed value semantics. Existing verifiers have yet to combine proofs over database instances of arbitrary finite cardinality with an ordered-list semantics for nested, tie-sensitive top-k. Unbounded systems reason primarily over bags or handle ordering through syntax-directed restrictions, whereas bounded systems either support only restricted top-k forms or impose a deterministic ordering rather than retain all legal tie-induced outcomes. Support for typed expression and aggregate semantics, observable runtime errors, and integrity constraints also remains partial. In Rocq, we mechanize a compositional logical semantics for a typed SQL core with order-sensitive operators, capturing all possible ordered lists and observable SQL failures in the supported fragment. To our knowledge, this is the first mechanized SQL semantics to combine nested, tie-sensitive top-k with a closure-based lifting from bag equivalence to ordered-list equivalence, enabling sound reuse of bag-theoretic reasoning while preserving compositionality across order-sensitive and correlated contexts. The formalization further provides executable semantics for PostgreSQL-oriented scalar and aggregate evaluation and an explicit account of integrity constraints. Building on this semantics, we present Logos, an LLM-guided Rocq verifier for unbounded SQL rewrite equivalence. Its agent uses a verified SQL-specific lemma library to construct query-specific Rocq proofs. Our evaluation covers 389 query pairs from Apache Calcite optimizer tests, TPC-H and TPC-DS rewrites, and WeTune's real-application workloads. Logos solves 86.9% of them, compared with 64.0% for SQLSolver, the strongest baseline.
Read the full abstract

Computer Vision

What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA

We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identical temporal segments for different questions about the same video. We trace this behavior to two structural limitations in prior common designs: (i) modality isolation that fixes video representations before they receive question semantics, and (ii) weak question injection inside the grounding module. To address this, we propose GroundFormer, which conditions video features on question intent before localization via learnable communication tokens that mediate directed visuo-lingual interaction. On top of the question-conditioned features, a factorized MIL cross-attention couples answer selection with temporal evidence under candidate-level supervision, while Gaussian smoothing converts peaked attention into temporally coherent segments. We further introduce a hierarchical multi-modal contrastive loss that aligns video, question, and answer embeddings across a two-pass training pipeline. GroundFormer achieves state-of-the-art grounded VideoQA performance on NExT-GQA and STAR, substantially improving question-discriminative temporal grounding.
Read the full abstract

All authors Jinhwan Seo, Kyubeom Han, Jumin Lee, Junhyug Noh, Sung-eui Yoon

Robotics

GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning

Correcting robot manipulation policies through human intervention holds great promise for real-world deployment, yet human operators are inherently imperfect in both the actions they provide and the timing of their intervention signals. While the former has been extensively discussed in reinforcement learning (RL), the latter remains underexplored. At high control frequencies, human intervention signals are often delayed and inconsistent across time and state space. In this work, we present GAINS, a framework for leveraging inconsistent human intervention signals in RL. At the core of GAINS, we employ distributional RL with quantile Q-networks to model the return variability induced by sparse task rewards and inconsistent human interventions. Building on this distributional representation, we introduce a pessimistic exploration strategy that promotes safe and sample-efficient learning under human corrections. We evaluate GAINS on four diverse simulated manipulation tasks and two challenging real-world scenarios against state-of-the-art intervention-based methods. GAINS achieves a 22% higher task success rate than RLIF and improves recovery success by up to 43% in failure scenarios. These results highlight the importance of modeling return variability induced by human imperfection for real-world deployment of intervention-based learning.
Read the full abstract

All authors Xinyi Zhang, Yinuo Zhao, Pei Ren, Lechun Jiang, Huiqian Jin, Lei Sun, Dapeng Wu, Zhengping Che, Chi Harold Liu, Jian Tang

Computer Vision

PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion

Controllable text-to-image diffusion models can often follow the global layout of spatial conditions, yet still violate fine-grained structures such as object boundaries, thin contours, and medium/small conditioned regions. This limitation is especially problematic for VAE-based latent diffusion, where spatial compression can weaken high-frequency and low-area condition signals. We propose PixelControl, a pixel-space controllable diffusion framework for fine-grained condition fidelity. Built on a PixelDiT-style backbone, PixelControl avoids the latent bottleneck and introduces two complementary designs. First, Structure-Aware Control Injection derives a condition structure map and uses it to strengthen injected control residuals around spatially sensitive regions. Second, Multi-Scale Pyramid Cycle Loss verifies generated images against condition-derived structures across multiple resolutions, balancing global layout consistency with local boundary and detail accuracy. PixelControl supports depth, segmentation, edge, and their combinations through modality-specific control branches with lightweight gated fusion. Experiments across depth, segmentation, and edge control show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions. The project page can be found at: https://linxin0.github.io/pixelcontrol_homepage/pixelcontrol-site/
Read the full abstract

All authors Xin Lin, Haodong Li, Zhifei Zhang, Yutong Yang, Haitian Zheng, Juanxi Tian, Zhe Lin, Truong Nguyen

Artificial Intelligence

HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation

Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As interactions accumulate, detailed execution traces and intermediate outputs dominate the context, making it difficult for the model to retain and use high-level planning information. Most existing methods address this issue through compression or retrieval applied to a single, flat context, which does not clearly separate different types of context information and often leads to degraded reasoning. To address this challenge, we propose HyMem, a hierarchical framework that explicitly separates the agent's context into distinct functional layers. HyMem organizes context by function to separate high-level planning from execution and complex analysis. Its isolated reasoning module handles complex subtasks without adding intermediate reasoning traces to the persistent planning context, while its memory management module preserves task progress across context refreshes through structured summaries. These components reduce redundant context accumulation, retain task-critical information, and support coherent long-horizon reasoning within a limited context window. Experiments on GAIA and Browsecomp-plus show that, with DeepSeek-V4, HyMem achieves average Pass@1 scores of 66.7% and 61.3%, outperforming the strongest baseline by 6.1 and 4.7 percentage points, respectively. Further analysis indicates that HyMem effectively controls the growth of the reasoning context, allowing the model to maintain focus and accuracy across complex, long-horizon tasks.
Read the full abstract

All authors XinQi Wang, Jinwei Xiao, Sijia Cui, Hongming Zhang, Yanna Wang, Qingyang Zhang, Bo Xu

Information Retrieval

The EMN Country Factsheets Structured Dataset

Each year, the European Migration Network (EMN) country factsheets deliver an overview of key migration and international protection developments within all EMN Member States and observer countries. The factsheets include both a textual component and a visual component. In this paper, we introduce a curated dataset of the textual component of these reports over 35 countries and 13 years (2012-2024.) The dataset was created to facilitate European-level research on migration policies and developments, and promote the use of reliable sources about migration in data science and media research, particularly at a time when the spread of online misinformation about migration constitutes a serious issue. The dataset transforms the original document texts into a tabular format, with columns corresponding to country, year, section, subsection, content, and harmonized title section. We illustrate the value of the dataset with concrete analyses and propose envisioned applications and uses of the dataset. The dataset is accessible through a DOI link.
Read the full abstract

Artificial Intelligence

Adaptive Mixing of Policies from Searching and Policies from Learning

Background: Distillation of training targets generated thru search/planning has proven useful in reinforcement learning, but search can take exceedingly long. Objectives: Rather than perform search to the same depth every time (typically at a fixed period of steps), reduce the search depth proportionally to the quality of the policy network priors. Methods: We describe Flexer, an architecture that, for each step, mixes the policy from a neural network and the policy from Monte Carlo tree search. The mixing factor favors the MCTS policy as the policy imitation error of the network and the environment models' variance increases. Results: Flexer outperforms a version of AlphaZero (and DQN and ADP) for some experiments on three toy symbolic problems.
Read the full abstract

Computer Vision

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across text, layout, charts, and visual structures. Recent efforts toward finer-grained supervision primarily rely on textual descriptions or localized visual regions as evidence proxies. However, such supervision signals may either overlook complex visual structures or provide incomplete and inaccurate representations of the underlying evidence. To address these limitations, we propose ConceptFormer, a latent concept representation learning framework for visual document retrieval. ConceptFormer models query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance, without requiring either textual intermediate representations or direct reliance on raw visual annotations. During training, ConceptFormer employs a strong vision-language model to dynamically determine the number of latent concept tokens and uses these concepts as an intermediate representation to bridge the semantic gap between queries and documents, thereby guiding the learning of the embedding space. Experiments on diverse visual document retrieval benchmarks demonstrate that ConceptFormer achieves 16.7% and 22.1% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively. Further analysis reveals that latent concepts effectively connect localized visual evidence with semantic relevance, enabling the retriever to capture both fine-grained textual cues and complex document-level visual structures while preserving strong retrieval alignment. Codes and data are available at https://github.com/Neuir/ConceptFormer.
Read the full abstract

All authors Chunyi Peng, Zhipeng Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Sen Mei, Yubo Sun, Yongheng Zhang, Jie Zhou, Yu Gu, Ge Yu, Maosong Sun

Digital Libraries · Cross-listed from math.CV

The Geometric Function Atlas: Using What We Know About Radius Problems to Solve New Ones

Usually, radius problems between Ma–Minda classes are solved one pair at a time, by fitting a disk inside the target region, providing a sufficient but not always the sharp radius. The same class appearing under different names makes comparison of results harder, with mistakes and duplication eluding detection. The Geometric Function Atlas catalogs radius problems using exact generators and a direction (source $\to$ target), ensuring unique identification. For each problem, we then compute the radius numerically, together with the point where the image first meets the target boundary. This helps us identify the sharp estimate which guides the proof we write. With this system, we were able to refine two earlier stated estimates, the disk radius for the sine $\to$ modified sigmoid and sine $\to$ rational cases from $\operatorname{arsinh} c$ to $\arcsin c$, and correct earlier stated values for the crescent and exponential classes: the sharp radius is $\sin 1$ from crescent to exponential, and $\log(1+\sqrt2)$ from exponential to crescent. All four proofs follow a common strategy: an estimate that is exact at the contact point, followed by the standard extremal function. Applying the method, we derive fifteen further sharp radii, four of them known.
Read the full abstract

All authors Prasanna Devadiga, Kishan Gurumurthy, Arya Suneesh, Pushparaj Devadiga, Asha Sebastian

Computer Vision

Bitstream Action Recognition is Byte Modeling

Conventional action recognition typically relies on successful pixel decoding of the bitstream. However, bitstream corruption during storage or transmission may cause severe visual artifacts or even decoding failure, posing a significant challenge to reliable action recognition. Bitstream Action Recognition (BAR) aims to overcome the dependency on decoding and the vulnerability to corruption. In this paper, we propose a novel BAR framework, Bitstream Recognition via Anchoring Corrupted Embeddings (BRACE). BRACE is a dual-branch byte-modeling architecture that treats a corrupted bitstream and its intact counterpart as two byte realizations of the same action. This guides the generation of rich and stable representations for robustness to corruption through Intact-Anchored Representation Alignment (IARA). The intact representation serves as a stable anchor, and the corrupted one is aligned to it at the embedding and decision levels under Unreliable-Anchor Suppression (UAS), entirely in representation space and without repairing the bitstream. To address the scarcity of corrupted bitstreams in practice, we introduce the Real-world Bitstream Corruption Simulator (RBCS), a four-parameter simulator that reproduces bit-flip and byte-loss errors arising in transmission and storage. Building on RBCS, we construct the first large-scale BAR dataset (BAR-D), which comprises the BAR-Stanford40 and BAR-PPMI subsets and spans diverse corruption types and severity levels. Finally, we build a large benchmark on BAR-D involving 14 action recognition methods from the pixel, compressed, and bitstream domains. Extensive experiments demonstrate that BRACE has superior robustness to bitstream corruption than all comparison methods. Ablation studies further validate the effectiveness of the proposed RBCS augmentation and IARA.
Read the full abstract

All authors Fangcheng Li, Chaoran Huang, Tianyi Liu, Wenyang Liu, Kejun Wu, Qiong Liu, You Yang, Zhengguo Li