The study introduces Smooth Net Benefit (σNB), a differentiable approximation of Net Benefit, as a training objective aimed at aligning predictive models with threshold‑specific clinical decisions. Experiments on the Framingham cardiovascular risk dataset and 44 TabZilla datasets show that σNB training yields modest improvements for logistic regression but little to no benefit for more flexible models such as GAMs and XGBoost. The authors conclude that σNB is not a universal replacement for negative log‑likelihood training, though it may be worth exploring in contexts where model flexibility is limited.
By Koen M. F. Gorgels, Lasai Barre\~nada, Maarten van Smeden, Ben Van Calster, Ewout W. Steyerberg, Wouter A. C. van Amsterdam
arXiv:2506. 13061v4 Announce Type: replace Abstract: Diffusion probabilistic models generate samples by learning to reverse a noise-injection process that transforms data into noise.
By Daniel Zhengyu Huang, Jiaoyang Huang, Zhengjiang Lin
HoliBench is a modular benchmarking and deployment toolkit that jointly measures accuracy, latency, and energy for foundation models across a wide range of devices, from single-board computers to GPU servers. It provides a platform abstraction layer that calibrates cross-device measurements and supports multiple model modalities, inference engines, and quantization levels. Using HoliBench, the authors evaluated 20 models on 7 device types, revealing tradeoffs such as limited latency gains from quantization on low‑precision hardware and diminishing accuracy returns relative to energy consumption, while also showing that single-model profiles can predict multi-model pipeline performance within a few percent.
By Inesh Chakrabarti, Zejun Xiong, Pragya Sharma, Mani Srivastava
The paper presents a zero‑shot model predictive control (MPC) approach for buildings that uses excitation‑based generalized transfer learning models. By pretraining on purposefully probed operational data from multiple source buildings, the authors demonstrate that these models achieve superior control performance in 32 simulated target buildings, outperforming both an online linear MPC and a PI controller. This method eliminates the need for target‑specific data, reducing setup cost and facilitating broader deployment of energy‑efficient MPC in the building sector.
By Fabian Raisch, Felix Koch, Zack Xuereb Conti, Christoph Goebel, Benjamin Tischler
The paper introduces Explanation-Driven Feature Acquisition (EDFA), a method that jointly optimizes algorithmic recourse and feature acquisition by selecting features based on explanatory value per unit cost. Using Markov Blanket theory, EDFA unifies various explanation types and provides distribution‑free validity guarantees for recourse derived from partial information. Experiments on seven datasets show that EDFA requires fewer features than existing active feature acquisition baselines while maintaining accuracy and producing more actionable recourse.
By Vinura Galwaduge, Jagath Samarabandu
The paper introduces a weakly supervised framework for extracting dataset mentions from forced displacement and Fragile, Conflict, and Violence (FCV) documents. It uses a lightweight model trained on general research literature to generate candidate mentions, which are then refined by a large language model that validates or rejects them and corrects boundaries. The refined annotations are augmented with synthetic and contrastive examples to fine‑tune the model, achieving 74.1% precision and 70.5% recall on a benchmark of 1,706 passages, with higher precision (89.5%) on passages that contain dataset references.
By Rafael Macalaba, Aivin V. Solatorio, Patrick Michael Brock, Olivier Dupriez
arXiv:2609. 12366v1 Announce Type: new Abstract: We present ORQA, a method for testing occupation-level knowledge in large language models.
By Shreyas Krishnan, Serina Chang, Abhishek Nagaraj
The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.
By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli
The paper introduces a certification framework for assessing concept unlearning in text-to-image diffusion models, offering high‑confidence guarantees with bounded error on residual concept leakage. Unlike prior methods that rely solely on attack success rates from automated prompt searches, this approach combines statistical certification with worst‑case analysis along concept‑relevant embedding directions to derive explicit upper bounds on leakage probability. Evaluations across NSFW content, artistic styles, and celebrity identities reveal that certified leakage bounds exceed standard attack success rates by 16.2%, highlighting significant residual risks overlooked by existing protocols.
By Mansi, Luca Marzari, Francesco Leofante
The paper presents a study on adaptive chemotherapy control using deep reinforcement learning (DRL) to address tumor heterogeneity and drug resistance. Closed‑loop DRL dosing policies—continuous (TD3) and discrete (DQN)—are trained on a high‑dimensional heterogeneous tumor model and benchmarked against a Pontryagin's Maximum Principle (PMP) open‑loop solution. Across a 100‑patient virtual cohort with ±10% parameter perturbations, TD3 achieves higher average tumor reduction, while DQN offers tighter inter‑patient dosing consistency, highlighting an efficacy‑consistency trade‑off. The work assumes full observation of tumor subpopulations, noting that clinical translation will require handling sparse, noisy measurements.
By Bereket Sitotaw Kidane, Md Samiul Haque Motayed, Shuo Wang
The paper introduces a new variational inference framework that uses tangent transformations to handle strongly super‑Gaussian likelihoods across a wide range of probability models. By constructing tangent minorants of the log‑likelihood through convex duality, the method achieves conjugacy with Gaussian priors, enabling tractable inference where traditional approaches struggle. The authors provide algorithmic convergence guarantees and near‑parametric risk bounds, and demonstrate superior scalability and accuracy on both simulated and real‑world datasets compared to existing variational algorithms.
By Somjit Roy, Pritam Dey, Debdeep Pati, Bani K. Mallick
The Vienna 4G/5G Drive-Test Dataset is a city‑scale open dataset of georeferenced LTE and 5G NR measurements collected across Vienna, Austria. It combines passive wideband scanner observations with active handset logs, offering complementary network‑side and user‑side views of deployed radio access networks. The dataset includes inferred base‑station deployment descriptors, high‑resolution building and terrain models, and is organized into scanner, handset, estimated cell information, and city‑model components to support reproducible benchmarking in environment‑aware learning, propagation modeling, coverage analysis, and ray‑tracing calibration workflows.
By Wilfried Wiedner, Lukas Eller, Mariam Mussbah, Dominik R\"ossler, Valerian Maresch, Philipp Svoboda, Markus Rupp
The paper introduces ASCIL, a post‑ASR correction framework that re‑evaluates wake‑up intent by combining acoustic embeddings, linguistic cues, device context, and past misclassifications. ASCIL interprets both implicit (hesitation, disengagement, silence) and explicit (cancellation, repetition) signals as noisy indicators of misclassification, enabling online pattern updates without manual annotation. On a proprietary dataset of 3,667 interactions, ASCIL reduces errors by up to 54.27% relative on a session‑disjoint subset and 24.39% at a 0.90 threshold, while adding less than 60 ms of latency and improving intentional acceptance rates.
By Preeti Saraswat, Divya Neelagiri, Anil Yadav
The paper introduces SWARM, a multilingual dataset of 2,183 search engine results in nine languages, annotated for support of Russian propaganda narratives. It evaluates a source-based blocklist, supervised classifiers, and zero‑shot large language models, finding that blocklists miss most propaganda and that content‑level models vary in performance, with the best LLM achieving an F1 of 0.73. The study highlights the need for per‑language, content‑level detection of search‑borne propaganda.
By Manuel Tonneau, Abhinav Dubey, Farhan Shaikh, Ilaria Vitulano, Martha Stolze, Hale Dedeoglu, Clara Riechert, Ella Kuka, Maryna Sydorova, Mykola Makhortykh, Elizaveta Kuznetsova
The study evaluates a multi‑agent large language model system for forecasting outcomes of the 2026 FIFA World Cup. Two specialist agents—one quantitative and one news‑focused—produce forecasts that are then reviewed by a critic and combined by a meta‑agent. Results show the news specialist performs best, matching betting market accuracy, while the meta‑agent adds little beyond the specialists’ predictions.
By Julian Varghese, Lucas Bickmann, Sarah Sandmann
SteerDuplex is a full‑duplex speech dialogue model that can be steered along attributes such as tone, persona, speaking rate, and voice style in response to user instructions. The authors introduce a taxonomy of text‑ and audio‑based steerability, identify gaps in existing models, and fine‑tune a Moshi‑based model with reinforcement learning to improve timing and response continuity. They also present SteerBench, a benchmark of 390 spoken prompts and 1,067 human‑authored rubrics, showing significant gains in audio‑steering pass rates and interruption handling compared to open baselines.
By Utkarsh Tyagi, Ramaneswaran Selvakumar, Advait Gosai, Sonal Kumar, Nikhil Barhate, Isabell Sagar, Steven Li, Miheer Bavare, Daniel Quigley, Fabiola Tapia Carrillo, Jose M Patron E, Diego Mac\'ias Guti\'errez, Paul Song, Ramani Duraiswami, Dinesh Manocha, Yunzhong He
UniMo introduces a unified point‑cloud based framework for generating 3D motion that works for both humans and animals, overcoming challenges posed by diverse skeletal topologies and limited animal datasets. It converts parametric skeletons into unparametric representations and uses dynamic sampling to focus on active joints. The authors also release UniML3D, a large motion‑language dataset with 145,907 sequences and 433,388 captions, and demonstrate state‑of‑the‑art performance on multiple benchmarks.
By Zeyu Zhang, Zhiyuan Zhang, Siheng Wang, Yiran Wang, Danning Li, Ian Reid, Richard Hartley
OphBiWSSD is a new framework for temporal action localization in ophthalmic surgeries that uses Bidirectional State Space Duality to avoid the quadratic memory cost of Transformers. It employs a weight‑tied selective scan that incorporates both past and future surgical context, enabling linear‑time global synthesis of non‑causal temporal cues. On the OphNet benchmark, OphBiWSSD achieves state‑of‑the‑art mean Average Precisions of 44.42 % for phases and 43.08 % for operations, outperforming baselines by 6.80 % and 6.66 % respectively.
By Yang Liu, Qionghong Ma, Joongwon Chae, Lihui Luo, Yibing Shen, Yulin Zhuo, Yingting Zhu, Jiashu Chang, Xiaoyun Zhong, Dongmei Yu, Peter E. Lobie, Peiwu Qin, Chengming Yang
CoralscapesV2 is an expanded dataset for coral reef visual scene understanding, increasing the number of fine‑grained classes from 39 to 95 and adding 65,000 exhaustive fish instance masks. It supports panoptic segmentation by providing high‑quality semantic and instance labels across diverse, unconstrained reef imagery. The dataset serves as a challenging benchmark for modern segmentation models and enables broader applications such as benthic cover mapping and automated fish‑reef interaction analysis.
By Jonathan Sauder, Thomas Ruckli, Gabriel\.e Strodomskyt\.e, Ibrahim Souleiman Abdallah, Rahma Hassan Abdi, Djama Goumaneh Awaleh, Mohamed Houssein Farah, Moustapha Nour, Osama Sharhubil Saad, Mustafa Mohammed Khalafallah Altaib, Maysoon Kteifan, Farah Alsoqi, Eyad Zgool, Jafar Al-Omari, Temesgen Gebremeskel Gebreluel, Zekaria Zekeria Abdulkerim, Meron Ghirmay, Teklehaimanot Beraki, Devis Tuia, Guilhem Banc-Prandi
The paper introduces a post‑training approach that enables a single inference process to transition from text reasoning to image synthesis, eliminating the need for explicit modality switching. Using the 14B BAGEL model, the authors demonstrate that targeted post‑training data and reward‑weighted training improve multimodal image generation across four independent T2I benchmarks. The study highlights the benefits of joint text‑image generation and strategic data selection for enhancing T2I performance.
By Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han, Yushi Hu, Emily Dinan, Amita Kamath, Michal Drozdzal, Reyhane Askari-Hemmat, Luke Zettlemoyer, Marjan Ghazvininejad