探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:ee582f8864c3bde5cc462953a38dbbae

How knowledge shapes community stigma and social support for women seeking abortion in the Democratic Republic of Congo: A cross-sectional study.

作者:

Etsou↗Kanda↗Ngwanza↗Mpoyi↗Bokamba↗Mulunda↗J.-C↗Lobo↗

Background The Democratic Republic of Congo (DRC) bears one of the highest maternal mortality ratios globally (746 per 100,000 live births), with nearly 11% of deaths attributable to complications of unsafe abortion. Despite ratification of the Maputo Protocol and related national policies, access to safe abortion remains limited, largely due to entrenched stigma. Social support, encompassing emotional, informational, and instrumental assistance, is critical in shaping womens abortion-seeking behaviors and health outcomes. This study examines the influence of community-level knowledge on stigma and social support for women seeking abortion care. Methods A cross-sectional survey was conducted from May 2024 to June 2024 among 1,715 adults in Kinshasa and North Kivu provinces. Analyses focused on a sub-sample of 574 respondents reporting familiarity with women who had undergone abortion. Structural Equation Modeling (SEM) was applied to estimate direct and indirect pathways linking community knowledge, stigma, and social support. Results Two core knowledge indicators, recognition of abortion as a safe medical procedure and awareness of legal conditions for access, were significantly associated with outcomes. A one-unit increase in knowledge corresponded to a 0.39-point increase in social support and a 0.19-point reduction in stigma. Enhanced knowledge promoted empathetic attitudes, reinforced practical support, and mitigated moralizing judgments toward women seeking abortion. Conclusions Strengthening community knowledge emerges as a strategic lever to reduce abortion-related stigma and enhance social support in the DRC. These findings underscore the importance of integrating stigma-reduction and knowledge-enhancement interventions into reproductive health programs to improve womens access to safe and dignified abortion care.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17824

Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows

作者:

Paul Julius K\"uhn↗Saptarshi Neil Sinha↗Jakob Hansen↗Robin Horst↗

Segmenting 3D assets into meaningful regions remains challenging, especially when segmentation criteria are application-dependent and require user control. We present a human-in-the-loop pipeline for generating a segmented 2D parameterized atlas from a 3D model for interactive media, game, and XR content workflows. Our method first selects a compact set of rendered views using a greedy set cover strategy over sampled surface points, and then supports interactive segmentation of these views with SAM~2 and Label Studio. The resulting masks are back-projected onto the model's UV parameterization to produce a unified segmented atlas that supports downstream production tasks such as segment-wise material assignment, style transfer, and semantic labeling. We assess the pipeline through a demonstration-based technical evaluation on eight cultural heritage objects. The results show that the approach can generate usable segmented atlases across diverse geometries while revealing recurring sources of manual correction, particularly fine structures, cavities, and weak appearance boundaries.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17846

Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

作者:

Haoqi Yuan↗Zhixuan Liang↗Anzhe Chen↗Ye Wang↗Haoyang Li↗Pei Lin↗Yiyang Huang↗Zixing Lei↗Tong Zhang↗Jiazhao Zhang↗Jie Zhang↗Jingyang Fan↗…

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $\pi$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2509.23982

Toward Preference-aligned Large Language Models via Residual-based Model Steering

作者:

Lucio La Cava↗Andrea Tagarelli↗

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically require curated data and expensive optimization over billions of parameters, and eventually lead to persistent task-specific models. In this work, we introduce Preference alignment of Large Language Models via Residual Steering (PaLRS), a training-free method that exploits preference signals encoded in the residual streams of LLMs. From as few as one hundred preference pairs, PaLRS extracts lightweight, plug-and-play steering vectors that can be applied at inference time to push models toward preferred behaviors. We evaluate PaLRS on various small-to-medium-scale open-source LLMs, showing that PaLRS-aligned models achieve consistent gains on mathematical reasoning and code generation benchmarks while preserving baseline general-purpose performance. Moreover, when compared to models aligned with DPO and SimPO, they perform better with great time-savings. Our findings highlight that PaLRS offers an effective, much more efficient and flexible alternative to standard preference optimization pipelines, offering a training-free, plug-and-play mechanism for alignment with minimal data.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13634

Operads for compositional reasoning in LLMs

作者:

Nathaniel Bottman↗Kyle Richardson↗

Question decomposition, i.e. breaking a complex query into simpler sub-queries whose answers are composed to produce a final answer, is a widely used strategy for improving LLM reasoning, yet it currently lacks a rigorous mathematical foundation. In this paper, we propose operads, mathematical structures that model many-in, one-out operations and compositions thereof, as a natural framework for describing question decomposition. We define the questions operad $Q$, in which operations correspond to question templates and composition corresponds to substitution of sub-answers, and show how QA models can be interpreted as algebras over $Q$. Beyond reframing existing practice, this operadic perspective points toward new methods, in particular a notion of operadic consistency, which measures whether a QA model's answers agree across the partial collapses of a question decomposition tree. Empirical evaluation of operadic consistency is reported in our companion paper (Bottman, Liu, and Richardson, 2026), which finds it strongly correlated with accuracy across twelve LLMs and four multi-hop QA datasets and outperforming standard temperature-based self-consistency baselines. We argue that operads are the natural mathematical home for question decomposition, and that invariants such as operadic consistency open new directions for analyzing and improving the reliability of multi-step reasoning.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2605.26759

Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining

作者:

Biao Ouyang↗Tengxue Zhang↗Zhihao Zhuang↗Yang Shu↗Chenjuan Guo↗Bin Yang↗

arXiv:2605.26759v2 Announce Type: replace Abstract: Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal discovery capabilities to new time series governed by diverse causal mechanisms. In this paper, we propose PTCD, a novel Pretraining framework for Time-series Causal Discovery, which improves cross-task generalization through context-conditioned modeling and transferable causal augmentation. To model complex temporal causal dependencies, PTCD employs a dual-scale iterative attention mechanism to capture window-level causal relationships, and a Gaussian mixture with a context-level routing mechanism to handle heterogeneous exogenous distributions. To further address distribution shifts across causal graphs, PTCD adopts a pretraining paradigm on synthetic datasets that integrates intervention-based learning and a causal mixup strategy, promoting stable causal discovery and stronger generalization. Extensive experiments on multiple real-world out-of-distribution (OOD) datasets demonstrate that PTCD excels in both causal discovery and root cause identification.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14598

Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0

作者:

Ali Asaria↗Tony Salomone↗Deep Gandhi↗

arXiv:2606.14598v1 Announce Type: new Abstract: Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat. We trace this to a software artifact: the production "INT8" forward quantizes weights and activations only to immediately dequantize them back to bf16 and run a bf16 matrix multiply, never engaging the GPU's INT8 tensor cores, so the hardware's compute advantage is left entirely unrealized. We close this gap with a single fused Triton INT8 GEMM (int8xint8->int32 on Ampere tensor cores, with per-token x per-channel dequantization and bias folded into the epilogue, autotuned per GEMM shape) dropped into the Ideogram 4.0 diffusion transformer's linear layers in place of the dequantize-to-bf16 path. In the kernel, the int8xint8->int32 accumulation is bit-exact against torch._int_mm and the dequantized output matches the reference at cosine similarity 1.0 with no NaNs, running 2.8-4.2x faster than bf16 per GEMM. End to end it delivers a ~1.1x (~9-10%) speedup at 768px, and at 1024px it generates an image in 156.5 s on a single RTX 3090, faster than the single-card NF4 (164.5 s) and FP8 (172.9 s) baselines, at no measurable quality cost on these point estimates (PickScore/CLIPScore). INT8 thus goes from the slowest variant to the fastest, and 1024px becomes single-GPU feasible. The primary speed criterion (beat FP8, by ~9.5%) is comfortably met; the NF4 margin (~4.9%, single-run n=4) is within run-to-run variance we did not quantify and is best read as consistent with meeting the stretch target. We close with an honest deployment map: the win is specific to consumer Ampere, and on A100 and B200 the same kernel loses to those cards' fast native bf16/FP8 paths.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16211

Weaving Multi-Source Evidence for Biomedical Reasoning: The BioMedHop Benchmark and BioWeave Framework

作者:

Xingyu Tan↗Shiyuan Liu↗Xiaoyang Wang↗Qing Liu↗Xiwei Xu↗Xin Yuan↗Liming Zhu↗Wenjie Zhang↗

Biomedical question answering (QA) increasingly requires reasoning over interacting entities, where supporting evidence is scattered across biomedical knowledge graphs, literature documents, and web-accessible resources. However, existing biomedical QA benchmarks mainly focus on exam-style knowledge, literature comprehension, or short-range multi-hop inference, leaving source-conditioned graph reasoning and evidence topology construction underexplored. To fill this gap, we introduce BioMedHop, a multi-source graph-grounded benchmark for evaluating biomedical reasoning over structured evidence topologies. BioMedHop contains 10,045 instances across KG, document, web, and hybrid evidence settings, covering shared-neighbor matching, intersection reasoning, path-based reasoning, and counting, with option-based, open-ended, and numeric count renderings. To support this benchmark, we further propose BioWeave, a source-aware reasoning framework that retrieves biomedical KG paths, gathers supporting clues from documents and web sources, assembles them into a unified evidence graph, and verifies answers through entity-level evidence support. Comprehensive experiments show that BioWeave achieves the best overall performance among compared methods on BioMedHop, outperforming the strong hybrid baseline ToG-2 by 10.5% in the overall average. Moreover, BioWeave consistently improves different LLM backbones and enables smaller models, such as Qwen3-4B, to achieve reasoning performance comparable to GPT-4-Turbo.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12744

GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models

作者:

Garvita Allabadi↗Matteo Sodano↗Roberto Estev\~ao↗Yuxiong Wang↗Vikram Adve↗Emre Kiciman↗Ranveer Chandra↗

In-Context Learning (ICL) has become a powerful mechanism for adapting Large Language Models (LLMs) to new tasks without fine-tuning. Extending this concept to Large Multimodal Models (LMMs), Multimodal In-Context Learning (M-ICL) relies on retrieving relevant examples, such as images, captions, or question-answer pairs, to guide predictions across tasks like classification, captioning, and visual question answering (VQA). Most existing approaches select in-context examples based on feature-space similarity, assuming that semantically similar samples provide the most useful context. However, our systematic analysis reveals that this assumption does not always hold: visually similar examples are not necessarily those that most effectively enhance in-context learning performance. To address this, we propose the Guided Retrieval of In-context Prompts (GRIP), a learnable vision-only retrieval framework that leverages feedback from LMMs to identify examples that truly improve model predictions. GRIP learns to distinguish beneficial from detrimental in-context examples through contrastive training, refining retrieval beyond pure similarity. Across three multimodal tasks, namely classification, captioning, and VQA, GRIP improves consistently over similarity-based retrieval on Qwen2.5-VL-7B, with its strongest gains in classification on Idefics2-8B. Moreover, we demonstrate that retrievers trained with feedback from one open LMM can be transferred to other models without retraining, including closed-source GPT-4o and Gemini, enabling scalable and cost-efficient deployment of M-ICL. Code will be published upon acceptance.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12623

Estimating Individualized Treatment Effects in Acute Ischemic Stroke with Causal Transformation Models (TRAM-DAG): A Multi-Centre Observational Study with External RCT Validation

作者:

Oliver D\"urr↗Lisa Herzog↗Pascal B\"uhler↗Susanne Wegener↗Beate Sick↗

arXiv:2606.12623v1 Announce Type: cross Abstract: Personalized medicine in acute ischemic stroke requires moving beyond average treatment effects (ATE) to individualized treatment effect (ITE) estimates to support treatment decisions. In acute ischemic stroke, mechanical thrombectomy has been shown to be more effective on average than lysis in randomized controlled trials (RCTs), such as the MR CLEAN study. We aim to identify which individual patients benefit most from mechanical thrombectomy compared to lysis. The outcome of interest is the modified Rankin Scale (mRS) at three months, an ordinal measure of functional disability (0: no symptoms, 6: death). We demonstrate that causal transformation models on directed acyclic graphs (TRAM-DAG) can be used for ITE estimation after being fitted on observational MAGIC multi-center stroke patient data. To ensure comparability with the MR CLEAN population, which we use for validation, we train the TRAM-DAG on a MAGIC sub-population with NIHSS at admission >= 6, corresponding to one inclusion criterion of MR CLEAN. The fitted model is then used to estimate ITEs for stroke patients in the MR CLEAN population. While these ITE estimates cannot be confirmed experimentally, we show that their average is consistent with the trial's reported ATE. Furthermore, the ITE estimates correctly rank trial patients by their observed frequency of a good outcome (mRS at three months

阅读与讨论 → 访问原文 →

11.

PLOS Medicine 2026-05-14 DOI: HASH:b91e8730b3acd6491ae6fa2924a91a91

First-trimester nonsteroidal anti-inflammatory drugs exposure and risk of major congenital malformations: A retrospective register-based cohort study

作者:

Ariel Avraham Hasidim↗

by Ariel Avraham Hasidim, Itamar Ben Shitrit, Daphna Idan, Tal Michael, Amalia Levy, Gali Pariente, Eitan Lunenfeld, Sharon Daniel Background Pain and fever are common in early pregnancy, yet their management poses a major clinical dilemma. Although not confirmed, recent studies have raised safety concerns regarding acetaminophen. Evidence on the use of nonsteroidal anti-inflammatory drugs (NSAID) in the first trimester remains inconclusive. This uncertainty has left clinicians with limited evidence to guide treatment decisions. This study evaluated the association between first-trimester NSAID exposure and the risk of major congenital malformations (MCMs) in a large, population-based cohort of pregnancies. Methods and findings We conducted a population-based retrospective cohort study within the Southern Israeli Pregnancy Registry (siPREG) project, including all singleton pregnancies of women aged 15–45 years resulting in live births, stillbirths, or elective terminations for fetal malformations at a Soroka University Medical Center between 1998 and 2018. Pregnancies exposed to established teratogens, multiple gestations, and those with documented genetic or chromosomal anomalies were excluded. First-trimester NSAID exposure was defined by pharmacy dispensations (overall and by specific agents). MCMs were identified from linked clinical, hospitalization, and termination records through the first postnatal year.Propensity scores were estimated using covariates selected via a directed acyclic graph, including maternal age, ethnicity, diabetes, medical indication for NSAID use, exposure to other antipyretics, obesity, smoking, folic-acid use, gravidity, perinatal care, and year of pregnancy. Generalized full matching was used to balance covariates. Adjusted risk ratios were derived using weighted Poisson regression with G-computation, and two-way cluster-robust standard errors, jointly clustering by maternal identifier and matching subclass. Sensitivity analyses included a dose–response assessment across defined-daily-dose (DDD) categories and a tipping-point analysis evaluating the impact of potential misclassification from unrecorded over-the-counter NSAID use.A total of 264,858 singleton pregnancies were included in the final cohort; 20,202 (7.6%) were exposed to NSAID, most commonly ibuprofen (5.1%), diclofenac (1.6%), and naproxen (1.2%). NSAID exposure, in total and as individual agents, was not associated with MCMs overall (8.2% versus 7.0%; matched-adjusted-Relative Risk (aRR) = 0.99 (95% CI [0.90,1.10])) or with organ-system-specific MCMs, including cardiovascular (matched-aRR = 1.05 (95% CI [0.92,1.20]), musculoskeletal (matched-aRR = 1.03 (95% CI [0.77,1.39])), central nervous system (matched-aRR = 0.77 (95% CI [0.53,1.11])), cleft palate (matched-aRR = 0.95 (95% CI [0.47–1.91])), gastrointestinal (matched-aRR = 1.03 (95% CI [0.64–1.63])), and genitourinary (matched-aRR = 0.99 (95% CI [0.72,1.35])) malformations. Dose–response analyses showed no significant association with MCMs across cumulative NSAID exposure: short-term (1–7 DDD, matched-aRR = 1.06 (95% CI [0.97,1.15]), medium-term (8–21 DDD, matched-aRR = 1.10 (95% CI [0.99,1.22]), and long-term (>21 DDD, matched-aRR = 1.24 (95% CI [0.94,1.63])). The main limitation was the potential for minor exposure misclassification due to over-the-counter availability of ibuprofen, although sensitivity analyses simulating such misclassification suggested minimal impact on the risk estimates. Conclusion In this large, population-based cohort, we found no evidence supporting an association between first-trimester exposure to NSAID and MCMs, providing reassuring evidence regarding their fetal safety in early pregnancy.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2603.08001

Amortizing Maximum Inner Product Search with Learned Support Functions

作者:

Theo X. Olausson↗Jo\~ao Monteiro↗Michal Klein↗Marco Cuturi↗

arXiv:2603.08001v2 Announce Type: replace Abstract: Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query. We propose amortized MIPS: a regression-based approach that trains neural networks to directly predict MIPS solutions, amortizing the cost of repeatedly solving MIPS for queries drawn from a known distribution over a fixed key database. Our key insight is that the MIPS value function is the support function of the set of keys, a well-studied convex function whose gradient yields the optimal key. This motivates two complementary amortized models: SupportNet, an input-convex neural network trained to regress the support function, and KeyNet, a vector-valued network that directly regresses the optimal key. SupportNet can serve as a cluster router, steering queries toward relevant database partitions, while KeyNet can be used as a drop-in replacement for the original query, fed directly to off-the-shelf indexing pipelines. Our experiments on the BEIR benchmark show that, for document embeddings, learned \SupportNet{}s and \KeyNet{}s significantly improve IVF match rates when accounting for compute effort, whether measured in FLOPs, number of probes, or wall-clock time. Our code is available at: https://github.com/apple/ml-amips.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2512.01241

First, do NOHARM: towards clinically safe large language models

作者:

David Wu↗Fateme Nateghi Haredasht↗Saloni Kumar Maharaj↗Priyank Jain↗Jessica Tran↗Matthew Gwiazdon↗Arjun Rustagi↗Jenelle Jindal↗Jacob M. Koshy↗Vinay Kadiyala↗Anup Agarwal↗Bassman Tappuni↗…

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18122

Embedded Machine Learning for Microcontroller-Class Edge Devices: Data, Feature, Evaluation, and Deployment Pipelines

作者:

Mostafa Darvishi↗

arXiv:2606.18122v1 Announce Type: cross Abstract: Embedded machine learning moves inference from cloud services to resource-constrained devices that must acquire data, preprocess signals, run a model, and act within tight limits on memory, energy, and latency. This paper presents a systems-oriented synthesis of an embedded machine-learning workflow for microcontroller-class platforms. The emphasis is placed on engineering decisions that are often hidden in generic machine-learning introductions: sampling and buffering, feature extraction as dimensionality reduction, validation under class imbalance, model/runtime co-design, and streaming deployment. Two representative signal families are used throughout the paper. The first is inertial motion recognition, where a two-second, three-axis accelerometer window is transformed from raw samples into root-mean-square and spectral features before classification. The second is keyword spotting, where audio is sampled, anti-aliased, transformed into mel-frequency cepstral coefficients, and processed by a compact one-dimensional convolutional network. The paper concludes with practical design rules for robust on-device inference, including data curation, quantization, thresholding, scheduling, and field monitoring.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19607

Which Pairs to Compare for LLM Post-Training?

作者:

Jiangze Han↗Vineet Goyal↗Will Ma↗

arXiv:2606.19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models. A common data-collection strategy is to generate a small set of completions for each prompt and label the resulting comparison pairs. However, human preference labels are often much more expensive than generating additional completions, suggesting a different use of the same labeling budget: generate a larger pool of completions, but label only the most informative comparison pairs. This paper studies which pairs should be compared in preference-based post-training. We formulate comparison curation as a sampling-design problem and evaluate designs by the quality of the final policy under the preference-based post-training objective. We instantiate this framework for Direct Preference Optimization (DPO), analyzing how the choice of labeled pairs propagates through DPO training to downstream policy performance. Our main results provide matching upper and lower bounds on the post-training optimality gap of the DPO-trained policy. The bounds show that comparison selection affects downstream performance through a single design-dependent information matrix, which links label allocation to parameter estimation error and policy suboptimality. This yields an explicit optimization criterion for budgeted comparison curation and motivates practical sampling designs for selecting informative pairs from large generated completion pools. Experiments on synthetic settings and language-model post-training benchmarks show that the proposed designs consistently improve sample efficiency over common comparison-selection heuristics.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18001

Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models

作者:

Cosimo Gregucci↗Obaidah Theeb↗Daniel Hernandez↗Antonio Vergari↗Steffen Staab↗

arXiv:2606.18001v1 Announce Type: new Abstract: Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and how they can robustly generalize across KGs is still an open question. In this paper, we shed some light on their generalization mechanisms highlighting how their performance on unseen KGs is not uniform when it comes to partially seen links, which we call half-links. In fact, we show that to predict a test triple $(h,r,t)$ it might suffice in practice to have observed the half-link $(h,r)$ or $(r,t)$ in the inference graph. This yields a taxonomy of four scenarios when combinations of these half-links are observed or not. In a rigorous stratified analysis over these scenarios, we reveal that SoTA KGFMs use seen half links for predictions, while unseen half-links pose different challenges. As such, our finer-grained taxonomy can be a diagnostic protocol for robust KGFM generalization and highlights where novel KGFMs can improve.

阅读与讨论 → 访问原文 →

17.

medRxiv (Medicine) 2026-06-11 DOI: HASH:542fadb543badbd4cfba6e04c59e27de

Foundation model-based tool for automated ulcerative colitis histology scoring demonstrates non-inferiority to pathologists across multiple scoring indices

作者:

Tahir↗Shamshoian↗Tauber↗Clinton↗L. K↗Griffin↗Shah↗Singh↗Fahy↗Sucipto↗Brosnan-Cashman↗Altepeter↗…

In clinical trials for ulcerative colitis (UC), pathologists assess disease severity through standardized histological indices, including the Geboes Score, Robarts Histopathology Index (RHI), and Nancy Histologic Index (NHI). Despite strong associations with clinical outcomes, histologic scoring suffers from inter- and intra-reader variability, and consensus criteria for histologic remission remain uncertain. Through a consortium approach, we developed an artificial intelligence-based measurement (AIM) tool for scoring histology in UC mucosal biopsies (AIM-HI UC). This model, trained on a large dataset of UC biopsies (N=10,230), utilizes additive multiple instance learning models leveraging PLUTO, a pathology foundation model, that predict each of the Geboes subgrades, from which the Geboes grade-level score, RHI, and NHI can be calculated. Evaluation of this model on a standalone verification set including clinical trial specimens established algorithm non-inferiority and/or superiority relative to standard qualified pathologists through comparison of algorithm-consensus and pathologist-consensus agreement metrics (non-inferior if difference >-0.1, superior if difference >0, inclusive of confidence intervals). AIM-HI UC was determined to be non-inferior to pathologists (N=3) for the prediction of all seven Geboes subgrades, grade-level Geboes, RHI, NHI, histologic improvement (GS

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19230

A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development

作者:

Samuel Stricker↗Claus Wirnsperger↗Alessandro Butt\'e↗Laura Helleckes↗Gonzalo Guill\'en Gos\'albez↗Antonio del Rio Chanona↗Mehmet Mercang\"oz↗

arXiv:2606.19230v1 Announce Type: new Abstract: This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian process (GP) surrogate-derived quantities are reformulated as objectives of a multi-objective optimization problem, and the resulting Pareto front is exposed to a domain expert for interactive candidate selection rather than returning a single automated recommendation. The framework is extended in two directions: constrained optimization is addressed by incorporating the posterior probability of satisfying output specification limits as an explicit Pareto objective, computed analytically from the GP posterior distribution; robust optimization is addressed by a Monte Carlo sampling strategy that estimates expected lower-confidence performance over a user-defined variability of input perturbations, capturing performance degradation under likely implementation deviations. The resulting multi-dimensional Pareto representation renders trade-offs between predicted performance, model uncertainty, probabilistic constraint satisfaction, and input robustness simultaneously visible through pairwise two-dimensional projections on an interactive dashboard, enabling selection criteria to be iteratively refined as the surrogate model improves and development objectives evolve. The framework is showcased on an eight-dimensional fed-batch Chinese Hamster Ovary (CHO) cell culture simulator demonstrating systematic identification of high-performing, feasibility-compliant, and perturbation-resilient operating conditions, and illustrating how expert-defined requirements provide a principled stopping criterion and support informed allocation of experimental resources.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2605.18817

Multi-Token Residual Prediction

作者:

Yufeng Xu↗Zishuo Bao↗Qian Wang↗Zeshen Zhang↗Haoqi Zhang↗Bowen Peng↗Ang Li↗Rahul Chalamala↗Yucheng Lu↗

arXiv:2605.18817v2 Announce Type: replace Abstract: Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K.

阅读与讨论 → 访问原文 →

20.

medRxiv (Medicine) 2026-06-22 DOI: HASH:c92e2011dba3f802ecab983d335d6548

Multisite Real-World Validation of an Electronic Health Record-Integrated Generative Artificial Intelligence Tool for Venous Thromboembolism Risk Stratification

作者:

Baughman↗D. J↗Liu↗Jee↗Young↗Knight↗A. M↗Davis↗Yegnasubramanian↗Najjar↗Whitbread↗J. J↗…

Background: Guiding risk-appropriate inpatient thromboprophylaxis requires venous thromboembolism (VTE) risk stratification; however, reliable risk determination remains inconsistent in routine care. Health systems increasingly pilot artificial intelligence (AI) tools, yet few studies demonstrate rigorous evaluation in the context of a learning health system (LHS). We evaluated the performance of a pilot electronic health record (EHR)-integrated generative AI (GenAI) system, inHealth General Reasoner (iHGR), for VTE risk stratification versus clinician order set classifications and physician-adjudicated chart review. Methods: This multisite retrospective validation study included adult inpatient admissions at Johns Hopkins Medicine between June 21, 2025, and Dec 18, 2025 (checklist-based order set from June 21, 2025 - November 19, 2025, and clinician judgement-based order set from November 29 - December 18, 2025). From 758 eligible admissions, we randomly sampled 500 balanced by site and order set periods. iHGR and clinician-selected order set classifications were compared with the reference standard (RS). Primary outcomes were iHGR sensitivity and specificity. Secondary analyses compared the order sets with the same RS to evaluate workflow comparators and error patterns. Results: iHGR achieved 81.8% sensitivity (95% CI 77.3-85.6) and 70.9% specificity (63.6-77.3). The checklist-based order set had 61.3% sensitivity (53.7-68.5) and 86.2% specificity (77.4-91.9). The clinician judgement-based order set had 78.1% sensitivity (71.3-83.7) and 65.4% specificity (54.3-75.0). False-negative iHGR classifications were associated with missed narrative risk factors. Conclusion: iHGR showed higher sensitivity for VTE risk than checklist-based order sets and clinician judgement without introducing systematic bias. In silico evaluation of pilot AI systems within LHSs can identify clinically important performance trade-offs and implementation targets before operational scale-up. Narrative clinical data abstraction remained a key limitation, supporting the use of GenAI to support rather than supplant clinician judgement.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18325

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

作者:

Raj Patel↗Shaswata Mitra↗Michele Guida↗Stefano Iannucci↗Sudip Mittal↗Shahram Rahimi↗

arXiv:2606.18325v1 Announce Type: cross Abstract: Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner–Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19899

Measuring Biological Capabilities and Risks of AI Agents

作者:

Patricia Paskov↗Jeffrey Lee↗Kyle Brady↗Alyssa Worland↗

arXiv:2606.19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations – drawing from our own evaluations – that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2505.23277

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression

作者:

Yong Zhang↗Heng Li↗Yanwen Huang↗Ning Cheng↗Yang Guo↗Yun Zhu↗Yanmeng Wang↗Shaojun Wang↗Jing Xiao↗

Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts. Existing context compression methods typically rely on heuristic relevance estimation or supervised compression models rather than on how LLMs utilize retrieved context during inference. We propose Sentinel, a lightweight sentence-level compression framework that decodes inference-time contextual utilization behaviors from head-wise attention patterns of frozen LLMs. To ground supervision in retrieval-dependent answering behavior, Sentinel trains a lightweight probe using QA examples where the model succeeds only when retrieved context is available. Sentinel performs compression using only a single non-autoregressive forward pass without dedicated compression training or autoregressive scoring. Empirically, we find that effective contextual utilization signals remain accessible even in compact proxy models. On LongBench, Sentinel with a 0.5B proxy model achieves up to 5$\times$ compression while attaining question-answering performance competitive with compression methods built on 7B-scale models. Despite being trained only on English QA data, Sentinel also generalizes effectively to Chinese and out-of-domain settings.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2601.22108

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

作者:

Shuqi Ke↗Giulia Fanti↗

arXiv:2601.22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations.

阅读与讨论 → 访问原文 →

25.

medRxiv (Medicine) 2026-06-11 DOI: HASH:230f18c8f9e055833ad0b0b7b0d16879

Incremental costs of transitioning from four to eight WHO-recommended antenatal care visits in Uganda: A costing analysis from a societal perspective

作者:

Atuhumuza↗E. B↗Atukunda↗E. C↗Musiimenta↗Mugyenyi↗G. R↗Haberer↗Obua↗Siedner↗M. J↗Matthews↗…

Background In 2016, the World Health Organization revised its antenatal care (ANC) recommendation from four to eight visits. For low- and middle-income countries like Uganda, where achieving even four visits remains a challenge, this transition has significant cost implications for both the health system and households. This study estimated the incremental costs of adopting the eight-visit model from a societal perspective. Methods The study was conducted in six government health facilities in southwestern Uganda. A micro-costing approach estimated health facility costs (personnel, equipment, consumables, and overhead). Costs incurred at patients end (transport, ultrasound, medical expenses, and time) were collected from 785 women using a questionnaire, with all costs in 2025 USD. Results For an average of 4.3 visits, total cost per woman was $100.1: facility costs $43.7 (43.7%), and patient costs $56.4 (56.3%). Transitioning to eight visits would increase total cost by $57.8 (57.8%), of which $36.4 (63.0%) would fall on households, equivalent to 68.8% of average monthly household income. Total costs would rise by 55.4% ($115.5 to $179.5) at Health Center IVs and 64.3% ($102.3 to $168.1) at Health Center IIIs, with facility costs up 43.4% and 62.9% and patient costs up 61.2% and 65.7%, respectively. Conclusion Transitioning to eight ANC visits would impose a large financial burden on households, with the incremental patient cost equivalent to more than two-thirds of average monthly household income. Equitable implementation requires improving availability of medicines and diagnostics, subsidizing transport, exploring telemedicine or community-based models, and improving efficiency at lower-tier health centers.

阅读与讨论 → 访问原文 →