The paper introduces a benchmarking framework that evaluates open-weight Vision‑Language Models (VLMs) for face recognition by treating explanation quality as a core metric. It defines two key criteria for explanations—relevance, meaning reliance on identity‑stable facial features, and faithfulness, meaning alignment with the visible image content without hallucinations. Using this framework, the authors benchmark several VLM families, jointly assessing face verification accuracy and explanation quality, and find that current models still exhibit shortcomings in their explanations, underscoring the importance of explanation metrics for a complete performance assessment.
By Laurent Colbois, S\'ebastien Marcel
OpenMAS-GCom is a diagnostic benchmark designed to isolate the impact of communication structures, role assignments, and information flows in graph‑enhanced multi‑agent systems (G‑MAS). It evaluates systems by systematically modifying one component—such as rewiring communication edges, removing specialist or critic agents, or corrupting intermediate messages—while keeping tasks, models, prompts, and budget limits constant. The benchmark tests 17 configurations across 29 datasets in six domains, including 400 new G‑MAS‑Complex tasks that require agents to combine and reconcile information from multiple documents.
By Kairui Yang, Xunkai Li, Kaixiang Zhang, Minghao An, Zekai Chen, Yuxuan Ba, Rong-Hua Li
The paper presents the first large‑scale benchmark for uncertainty quantification (UQ) calibration in long‑form scientific question answering, evaluating four UQ methods on 685,000 responses from up to 20 large language models across seven datasets. It shows that instruction tuning leads to token‑level probability polarization, undermining token‑level uncertainty signals, while reasoning model families differ in how they handle this effect. Only semantic consistency—consistency of the final answer—provides well‑calibrated outputs, demonstrating that semantic calibration remains robust in multi‑step, dependency‑rich reasoning.
By Philip M\"uller, Nicholas Popovi\v{c}, Michael F\"arber, Peter Steinbach
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.
By Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Xiangtao Li, Mingming Gong, Ivor Tsang, Yanfeng Wang, Jiangchao Yao
PRIME introduces a perception feedback mechanism for Vision‑Language‑Action models in autonomous driving, conditioning perceptual queries on a Situational Memory that aggregates past perception, reasoning, navigation goals, and predicted behaviors via cross‑attention. This approach adds only 29.7 M parameters (0.41 % of a 7.3 B‑parameter base model) and enables intent‑driven perceptual attention at minimal computational cost. On the Bench2Drive closed‑loop benchmark, PRIME achieves a state‑of‑the‑art Driving Score of 82.47 and a Success Rate of 60.00 %, outperforming prior models such as ORION.
By Erik Deinzer, Naya Baslan, Luca Paparusso, Narunas Vaskevicius, Peter Knott, Luigi Palmieri
The paper introduces an end‑to‑end framework for personalized audio‑driven facial motion that operates in real time without look‑ahead. It combines a causal multi‑resolution motion tokenizer, which captures both global temporal context and fine articulatory details, with a multi‑modal style retriever that pulls stylistic priors from arbitrary reference footage using ongoing audio and motion queries. This approach allows high‑fidelity, identity‑consistent animation from just a few casually recorded clips, outperforming existing methods in lip‑sync accuracy, identity consistency, and perceived realism while maintaining real‑time streaming constraints.
By Xuangeng Chu, Yu Han, Wei Mao, Shih-En Wei
JudgeSense is a benchmark comprising 880 items from human‑labelled corpora, each presented under two differently worded instructions that ask the same question. The study evaluates 25 judges from six providers across four tasks, measuring how rewording affects agreement with the judge’s own verdicts. Results show that rewording reduces agreement on all tasks, with significant effects on two, and that stability varies across tasks and is not predicted by parameter count.
By Rohith Reddy Bellibatlu, Edward Raff, Wenbin Zhang
The paper introduces a multimodal reasoning framework for cross‑domain visual question answering in Printed Circuit Board Assembly (PCBA) inspection, converting diverse data sources into a unified instruction format and generating verified reasoning traces. It proposes Task‑Aware Group Relative Policy Optimization (GRPO) that uses semantic, distance‑aware, and format rewards to improve choice‑based and counting tasks beyond exact‑match supervision. During inference, the system applies semantic consistency correction, self‑consistency voting, and multi‑model arbitration, achieving an overall score of 83.24 on the PCBA Standard‑to‑Real Grand Challenge leaderboard.
By Jia Li, Li Dai, Peng Jia, Zhenzhen Hu, Chee Seng Chan, Bingkun Bao, Richang Hong
The paper compares Ultralytics YOLO27, YOLO26, YOLO11, and YOLOv8 for detecting and segmenting small fruit parts in orchard settings. It evaluates five model scales across 30 experiments, finding that YOLO11s-960 and YOLO26s-960 achieve the best mask and box mAP scores while maintaining efficient parameter counts. The study also highlights the difficulty of peduncle detection and provides publicly available code and models for reproducibility.
By Ranjan Sapkota, Manoj Karkee
MOSAIC‑SR is a new symbolic regression method that combines a pretrained Transformer with search‑based refinement. The Transformer generates multiple initial sketches, which seed searches that jointly recover equation structure and constants using scale‑aware optimization and symbolic repair. On the SRSD‑Feynman dataset and six other benchmarks, MOSAIC‑SR achieves the highest symbolic solution rate and ranks among the top two in predictive accuracy, even when irrelevant dummy variables are present.
By Peiyi Zheng, Yanming Kang, Hans De Sterck, Giang Tran
GraphSkillEvo introduces a graph-structured representation for agent skills, where each node encodes an execution step and edges capture context-dependent transitions. This structure offers clearer workflow guidance and reduces redundancy compared to unstructured natural-language skills. The authors then present a population-based evolutionary optimization framework that explores this structured skill space, achieving higher accuracy than the baseline SkillOpt across five agent benchmarks.
By Rui Sun, Zhi Zheng, Zhenkun Wang, Zhichao Lu
arXiv:2609. 20945v1 Announce Type: new Abstract: Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indirect cross-linguistic spread.
By Kyomin Hwang, Hyeonjin Kim, Hyunho Lee, Yearim Kim, Yeji Song, Nojun Kwak
The study compares temporal deep learning models—Bidirectional LSTM, Temporal Convolutional Network, and Transformer—for physiological emotion recognition using two multimodal wearable datasets, WESAD and EmoWear. Experiments evaluate wrist-only, chest-only, and multimodal sensor configurations with participant-independent leave-one-subject-out cross-validation, and also explore ensembles, sensor ablation, sampling frequency, and saliency analysis. Results show that the best architecture varies by dataset, multimodal sensing consistently outperforms single-site configurations, and a 4 Hz sampling rate offers a cost-effective operating point.
By Desta Haileselassie Hagos, Saurav Keshari Aryal, Legand L. Burge
SignGPT is a unified, pose‑based framework that performs gloss‑free sign language translation (SLT) and generation (SLG) by integrating part‑aware hierarchical representations of body, hand, and facial motion into a shared language model. It uses asymmetric multi‑token prediction and progressive training for bidirectional modeling, and is evaluated on How2Sign (ASL) and Phoenix‑2014T (DGS) with benchmark comparisons, qualitative analyses, and component ablations. An exploratory study with 12 Deaf ASL signers demonstrates a sign‑to‑sign response pipeline, suggesting that unified modeling can support sign language conversation (SLC).
By Ronghui Li, Jun Dong, Zhongyuan Hu, Zunnan Xu, Jun Zhou, Liyuan Chen, Shuoling Liu, Jiangpeng Yan, Jie Guo, Xiu Li, Linchao Bao
The paper demonstrates that object detection benchmarks suffer from incomplete annotations, with re-annotation of COCO, Pascal VOC, Cityscapes, and KITTI revealing up to a 60% increase in detected objects, especially small, occluded, or densely packed instances. The authors propose a scalable annotation pipeline that uses multiple annotators per object to capture uncertainty and improve recall, and they introduce two new large-scale benchmarks: an uncertainty-aware detection benchmark and a label error detection benchmark based on real errors. Their findings show that benchmark performance is highly sensitive to annotation quality, yet model rankings remain largely unchanged, highlighting the need for uncertainty-aware evaluation to better reflect real-world ambiguity.
By Sarina Penquitt, Jonathan Klees, Antonia van Betteray, Parssa Jashnieh, Peter Stehr, Matthias Rottmann, Lars Schmarje
COMPLEX is a closed‑form, training‑free embedding for multiparameter persistence modules that provides both an upper and a lower Lipschitz bound, enabling faithful feature representations. By slicing modules along a near‑diagonal net and embedding each slice with the certified PLACE/PALACE landmark map, the method guarantees that separated modules remain separated in the embedding. On Orbit benchmarks and molecular graph tasks, COMPLEX achieves state‑of‑the‑art accuracy, outperforming existing landmark, transformer, and graph‑based approaches.
By Sushovan Majhi, Atish Mitra, \v{Z}iga Virk, Pramita Bagchi
The paper introduces a workflow that ranks competing geological interpretations by converting them into spatial priors and assessing their consistency with hydraulic‑head observations. Using a text‑to‑image model to generate 1600 geologic images per interpretation, a variational autoencoder encodes them, and a supervised inverse network maps head data into this latent space, producing log‑conductivity fields for flow simulation. The method is validated on a synthetic Johansen Formation benchmark and applied to two conceptual models of the Culebra Dolomite, yielding compatibility scores that align with independent evidence.
By Harun Ur Rashid, Daniel O'Malley
The study evaluates automatic tooth segmentation on panoramic radiographs using a large annotated corpus of 1,422 images and 42,142 tooth polygons. It finds that increasing input resolution improves boundary precision (mask mAP50‑95 rises from 0.656 to 0.717) while detection performance remains unchanged, and that architectural changes have minimal impact on in‑domain accuracy. Targeted interventions such as LoRA adaptation, promptable foundation models, and anatomical label assignment provide negligible gains, indicating that resolution and acquisition diversity should be prioritized over model novelty.
By Muhammad Rehan, Moaz Amjad, Syed Danial Ahmed, Mariam Adnan, Haider Ali
The study evaluates the robustness of medical vision‑language models for tuberculosis screening on chest X‑rays by testing them across multiple datasets, prompts, and evaluation settings. Three specialized models (BioMedCLIP, CheXficient, MedSigLIP) and a general OpenCLIP model were audited on 12,200 images, producing 244,000 model–image–prompt scores. Results show that no model consistently outperforms others across all cohorts and reliability criteria, with prompt changes and control group composition significantly affecting AUROC, and that high training‑set performance does not reliably transfer to external cohorts.
By Mushir Akhtar, M. Tanveer, Mohd. Arshad
The paper introduces a spectrally-aligned latent-flow model for time‑series generation that trains the latent space to preserve dynamical properties relevant to synthetic data quality. By incorporating fine‑tuning losses based on Fourier, wavelet, and signature transforms, the method mitigates spectral mismatches caused by latent compression and ensures alignment with true signals in terms of smoothness and targeted spectral content. Experiments on real‑world long‑range univariate and multivariate benchmarks show that the aligned model outperforms a base latent‑flow model and state‑of‑the‑art approaches in signal realism, computational efficiency, and local structure alignment.
By Camilo Carvajal Reyes, Felipe Tobar