中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (CS.LG) 2026-06-12

Majority-of-Three is Optimal

作者:
Divit Rawal↗Nikita Zhivotovskiy↗

arXiv:2606.13614v1 Announce Type: cross Abstract: We give a short proof that the majority vote of three independent consistent classifiers is an optimal learner in the realizable PAC setting. This proves optimality for the simplest voting scheme, while simplifying both the algorithmic structure and the probabilistic analysis of previous voting learners, including the algorithm of S. Hanneke and the analysis of bagging by K. Green Larsen.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-19

FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs

作者:
Elijah Feldman↗Dipak Meher↗Carlotta Domeniconi↗

Court proceedings contain valuable evidence about human smuggling networks, but this information is often buried within unstructured, jargon-heavy legal documents. While large language models (LLMs) can support knowledge graph construction through automated information extraction, existing approaches rely on general-purpose models that are not tailored to the entity and relationship definitions required in this domain. We introduce FineREX, a streamlined knowledge graph construction pipeline built around a fine-tuned LLM for named entity recognition and relationship extraction (NER-RE). Using a manually annotated dataset of $512$ text chunks, FineREX achieves absolute improvements of 15.50% and 31.46% in entity and relationship F1-score, respectively, compared to a larger general-purpose baseline. These gains translate into higher-quality knowledge graphs, reducing legal noise by nearly half and lowering node duplication on long documents from 17.78% to 11.17%. By eliminating document rewriting and redundant extraction stages, FineREX also reduces end-to-end processing time by 50.0%. Our results demonstrate that domain-specific fine-tuning can substantially outperform larger general-purpose models while improving both the quality and efficiency of knowledge graph construction for illicit network analysis.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-11

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

作者:
Suleyman Armagan Er↗Danilo Ribeiro↗Yogesh Virkar↗Surafel Lakew↗Adi Kalyanpur↗James Gung↗Thomas Delteil↗Arshit Gupta↗

Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long-term historical events or from previous agent-environment interactions, LLM agents are required to use memory mechanisms to store and retrieve experiences. While sophisticated memory systems exist for dialogue agents, few studies have empirically examined how to improve agents' tool-using capabilities through past user-agent conversations. We propose MemToolAgent, a framework that improves tool use through memory management. Our approach contains a memory extraction module that processes past experiences into structured memory entries, and a retrieval module that dynamically selects a subset of the stored memory entries. This enables more personalized and accurate responses aligned with user preferences and feedback without requiring LLM fine-tuning. In summary, this work has three main contributions: (1) a unified memory entry format that improves both general-purpose and personalized tool use without LLM fine-tuning, (2) a reflection-based memory extraction that uses environment and user feedback to distill wrong executions into critiques to store, and (3) a retrieval module that chooses how many past experiences to use based on the memory similarity distribution. MemToolAgent achieves 29%, 80%, and 17% relative improvements compared to strong baselines on the WorkBench, NESTFUL, and PEToolBench benchmarks, respectively.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CV) 2026-06-17

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

作者:
Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-16

Stable Menus of Public Goods: AI-Enabled Progress

作者:
Sara Fish↗

arXiv:2606.16989v1 Announce Type: cross Abstract: Using an open problem from the EC 2025 paper "Stable Menus of Public Goods" as a testbed, we conduct experiments to understand the effectiveness of different AI-for-EconCS research workflows. Specifically, we study three questions: Does providing human intuition in the prompt help? Does automated multi-turn interaction help? And, does an LLM outperform a first-year PhD student? Regarding the first two questions, we provide evidence for the following workflow suggestions: (1) prompting with human intuition can encourage the LLM to have better "taste", (2) multi-turn workflows help when the pipeline encourages "ambitious" steps. Regarding the third question, using an unpublished manuscript written by the paper's senior authors prior to collaborating with the first-year PhD student, we compare the effectiveness of the LLM with that of the first-year PhD student, and find that the LLM is slightly less effective.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CL) 2026-06-11

When Roleplaying, Do Models Believe What They Say?

作者:
Benjamin Sturgeon↗David Africa↗Sid Black↗

Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear truth probes, applying them to LLMs role-playing historical personas whose likely beliefs differ from modern consensus. For each persona, we compare false claims the persona would likely have endorsed (*era-believed*) with topic-matched false claims they would not have endorsed (*era-false*). Across prompting, in-context learning, and supervised fine-tuning, persona induction suppresses era-believed statements less than equally false alternatives, yet they remain classified as false overall. Role-play therefore shifts what these models say more than what they internally represent as true. We contrast this with models trained on harmful advice that exhibit Emergent Misalignment (EM). Across three model families (Qwen 2.5 14B, Qwen 3 8B, and Llama 3.3 70B), their false claims move substantially toward the true region of probe space, are defended under challenge roughly half the time versus about a sixth for role-play, and are used in downstream reasoning. Role-play and Emergent Misalignment thus are points on a spectrum of belief internalization, where role-play changes what a model says with little representational change, while Emergent Misalignment shifts the internal representation of false claims without fully marking them as true.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CV) 2026-06-15

Catching magnetic resonance imaging outliers in artificial intelligence-supported radiotherapy workflows: unsupervised detection and localization of image anomalies using deep learning

作者:
Mustafa Kadhim↗Viktor Rogowski↗Emilia Persson↗Camila Gonzalez↗Andr\'e Haraldsson↗Sofie Ceberg↗Mikael Nilsson↗Malin K\"ugele↗Sven B\"ack↗Christian Jamtheim Gustafsson↗

Artificial intelligence is increasingly integrated into radiotherapy workflows, yet such pipelines remain vulnerable to out-of-distribution image data that may introduce unexpected behavior in clinical tasks. Deep learning-based anomaly detection for pelvic magnetic resonance imaging (MRI) remains largely unexplored, and transparent evaluation of its feasibility for full automation is limited. We developed and evaluated a fully automated, unsupervised anomaly-detection framework for pelvic and brain MRI. A two-stage framework was trained on reference images from public datasets: LUND-PROBE for pelvic MRI, and IXI, fastMRI, and fastMRI+ for brain MRI. In the first stage, MRI slices were compressed into discrete tokens; in the second, the distribution of normal tokens was modeled. Anomaly evidence was estimated by combining perceptual image differences with token-surprisal scores based on negative log-likelihood. Automated detection was evaluated on pelvic MRI with synthetic global and real clinical anomalies, and on brain MRI with clinically annotated fastMRI+ abnormalities. Sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and false-positive behavior in held-out normal cases were assessed. The framework achieved robust detection across hidden evaluation cohorts, with AUCs of 0.97 (95% CI, 0.95-0.98) and 0.81 (95% CI, 0.74-0.87) for pelvic and brain MRI, respectively. Heatmap analysis showed strong spatial agreement between detected anomalies and ground-truth locations, supporting localization accuracy and interpretability. These results support the potential of unsupervised anomaly detection as an automated MRI quality-control layer for radiotherapy workflows, with transparent visualization of image regions likely to compromise downstream AI-based tasks.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CV) 2026-06-17

Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

作者:
Omar Sharif↗Eftekhar Hossain↗Nikhil Singh↗Patrick Ng↗

Reinforcement learning with verifiable rewards has driven major gains in LLM reasoning, and it is intuitive to assume this recipe will transfer well to multimodal models. However, multimodal models do two things: first, perceive what is in an image, then reason about what it implies. Because these stages are graded jointly, it is hard to tell how much room reasoning alone has to grow. We study this on algorithmic visual puzzles, where both components are necessary and show that perception, not reasoning, is the binding constraint. Replacing images with simple textual descriptions raises performance by over 20 points on average for Claude models. We then evaluate six reward designs aimed at inducing visual grounding during reasoning without chain-of-thought supervision. Training Qwen-2.5-VL-7B with GRPO, reward design induces long, structured reasoning with self-reflection and visual references, yielding a 5.56-point gain over the base model. These gains are, however, uneven; no single reward improves all categories, and rewards with verifiable accuracy signals trade out-of-domain transfer for in-domain accuracy. These results point to perception-aware reward design as a path forward, so that signals correct perception at its source rather than the reasoning that inherits its errors.

阅读与讨论 → 访问原文 →
09.
medRxiv (Medicine) 2026-06-18

Expert in Ultrasound Skills: Feasibility of an IMU-video platform to describe technical profiles during focused cardiac ultrasound. Pilot study

作者:
morales↗f. r↗Gonzalez↗S. R↗Osses↗M. F. S↗Hernandez↗B. L↗Ramirez↗D. A↗

Background: Focused cardiac ultrasound (FoCUS) is operator dependent and requires coordinated probe manipulation, image interpretation and iterative visual feedback. Existing assessment approaches often emphasize final image quality or expert rating. We developed Expert in Ultrasound Skills (EXUS) , a platform that synchronizes transducer-mounted inertial measurement unit (IMU) data with ultrasound video, and evaluated its technical feasibility during FoCUS acquisition. Methods: This observational pilot study included 6 operators performing two repetitions of a four-view FoCUS protocol, yielding 12 analytical sessions and 48 planned acquisitions. Feasibility was defined by acquisition completion, video availability, start/stop events, fused IMU-video windows, temporal coverage, complete human label entries and IMU integrity. A 100-image Likert rating task was used to summarize pairwise inter-rater agreement for still-frame image quality assessment. Results: All 48 planned acquisitions were completed with video, start/stop events, fused windows and complete human label entries. Temporal coverage was at least 90% in 47/48 acquisitions. IMU integrity endpoints exceeded the 80% threshold: 43/48 acquisitions had no extreme IMU-derived artifact, 43/48 had no active-segment IMU restart and 44/48 had no complete motion flatline. Mean pairwise exact agreement for the Likert task was 38.9%, with mean quadratic-weighted Cohen's kappa of 0.564. Post hoc profiles varied across duration, visual quality, mechanical load and motor efficiency. Conclusions: EXUS was technically feasible for synchronized IMU-video capture during FoCUS. The pilot supports multimodal acquisition data as a way to describe technical profiles and generate formative feedback hypotheses, but the post hoc indices are not validated competency measures. Keywords: focused cardiac ultrasound; point-of-care ultrasound; inertial measurement unit; medical education; deliberate practice

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CL) 2026-06-18

Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction

作者:
Zhuangzhuang Pan↗Ning Dong↗Yingna Su↗Yan Xia↗

Multimodal emotion-cause pair extraction (MECPE) requires reliable pair confidence over candidate pairs. Existing pair scorers commonly use pair-level cross entropy over valid candidates, which treats links mostly independently. This leaves the relative confidence geometry among competing causes under-constrained, allowing gold pairs to stay close to hard negatives or rely on incidental non-gold context. We study this vulnerability as pair-confidence brittleness and propose RPCL (Robust Pair Confidence Learning), a training-only framework for pair-confidence learning. RPCL encourages pair confidence to be both discriminative and stable: gold pairs are separated from row-wise hard negatives through a confidence-difference margin constraint, and clean pair predictions are aligned with predictions from a corrupted view where non-gold contextual utterance representations are partially corrupted. The original clean pair scorer and decoding pipeline are used unchanged at inference time. On ECF, MECAD, and MEC4, RPCL improves the three-seed mean Pair F1 over a matched base model by 2.58 to 2.83 percentage points in the full text-audio-video setting, and improves mean Pair AUPRC on all three datasets. Diagnostic analysis further shows larger gold-negative confidence gaps and lower margin-violation severity. These results suggest that explicitly shaping pair confidence is an effective training strategy for MECPE.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-12

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

作者:
Yuho Lee↗Jisu Shin↗Nicole Hee-Yeon Kim↗Jihwan Bang↗Juntae Lee↗Kyuwoong Hwang↗Fatih Porikli↗Hwanjun Song↗

arXiv:2606.13141v1 Announce Type: new Abstract: Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities. Yet progress in VideoRAG is limited by two gaps: existing benchmarks allow queries to be answered without the video, obscuring retrieval errors, and prior methods apply a single modality-granularity configuration per query, ignoring chunk-level variability. We address both by introducing V-RAGBench, a benchmark of $\langle$query, evidence chunk, answer$\rangle$ triplets that enables faithful, decoupled evaluation of retrieval and generation, and CARVE, a simple method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk. Each chunk then enters the generator under its winning configuration selected during retrieval, yielding an interleaved evidence form where the chunk-level decision propagates across both stages. CARVE outperforms eight recent VideoRAG baselines, with the chunks supplied to the generator interleaving multiple configurations rather than sharing a single one, a behavior unattainable by query-level methods.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.LG) 2026-06-15

Stability of a Generalized Debiased Lasso with Applications to Resampling-Based Variable Selection

作者:
Jingbo Liu↗

arXiv:2405.03063v3 Announce Type: replace-cross Abstract: We propose a generalized debiased Lasso estimator based on a stability principle. When a single column of the design matrix is perturbed, the estimator admits a simple update formula that can be computed from the original solution. Under sub-Gaussian designs with well-conditioned covariance, this approximation is asymptotically accurate for all but a vanishing fraction of coordinates in the proportional growth regime. The proof relies on concentration and anti-concentration arguments to control error terms and sign changes. In contrast, establishing comparable distributional limits (e.g., Gaussianity) under similar assumptions remains open. As an application, we show that the approximation significantly reduces the computational cost of resampling-based variable selection procedures, including the conditional randomization test and a local knockoff filter.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.AI) 2026-06-17

Combating Data Laundering in LLM Training

作者:
Muxing Li↗Zesheng Ye↗Sharon Li↗Feng Liu↗

arXiv:2604.01904v3 Announce Type: replace-cross Abstract: Post-hoc unauthorized-training data detection for large language models (LLMs) typically assumes a query-with-originals regime: rights holders query a target LLM with raw proprietary data and assess whether the model assigns them stronger memorization-based detection signals, e.g., higher confidence or lower loss, than held-out non-training reference texts. We show that this regime becomes brittle under data laundering, where the target LLM is trained on semantics-preserving but stylistically or structurally transformed surrogates of proprietary data to obfuscate provenance. Since training-time exposure occurs in the laundered form, memorization signals may no longer appear on the originals, collapsing the candidate-reference signal separation that standard detectors rely on. We counter this threat by studying laundering-aware detection with raw proprietary data, a held-out reference corpus, and query access to the target LLM, while the laundering transformation is undisclosed. Since exact recovery of the laundered corpus is infeasible, we infer a detection-useful synthesis process via an auxiliary LLM that maps originals into training-like queries. To make this search tractable, we introduce Synthesis Data Reversion (SDR), which constrains the unbounded space of natural-language transformations through a goal-details abstraction: a high-level transformation goal, e.g., "lyrical rewriting", and fine-grained details, e.g., "with vivid imagery". SDR identifies the most likely goal and iteratively refines details so synthesized queries elicit stronger target-model detection signals. Evaluated on the MIMIR benchmark against diverse laundering practices and target LLM families (Pythia, Llama2, and Falcon), SDR consistently restores detection signals, offering a practical auditing layer against data laundering.

阅读与讨论 → 访问原文 →
14.
bioRxiv (Bioinfo) 2026-06-16

Evidence for recombination in dengue virus genomes

作者:
de Paula Oliveira↗Jacob Machado↗Prieto Oliveira↗Ocana↗

Recombination is a key driver of RNA virus evolution, yet its extent and evolutionary implications in dengue virus (DENV) remain incompletely understood. We conducted a comprehensive, genome-wide recombination screen across 6,905 complete DENV genomes representing all four serotypes, 82 countries, and eight decades of sampling (1944-2023) retrieved from the Bacterial and Viral Bioinformatics Resource Center. Using seven complementary recombination detection methods implemented in RDP5, we identified 66 recombination events across 53 unique recombinant sequences, of which 29 are newly described. Events included intra-genotypic (n = 18), inter-genotypic (n = 32), and inter-serotypic (n = 16) exchanges spanning 14 genotypes and four continents, with no meaningful serotype-level enrichment (Cramer's V = 0.054). Recombination was concentrated in non-structural genes, most frequently NS3 (19 events), NS5 (17), and NS2 (12), while the capsid gene contained no recombination events, consistent with strong functional constraint. Single-nucleotide polymorphism analyses confirmed low divergence between recombinants and their inferred parents in both recombinant and non-recombinant regions. Phylogenomic analysis of 6,642 sequences revealed that recombinants cluster significantly closer to their major parents (p = 8.9 x 10-6 ) and that their removal does not significantly alter tree topology (p = 0.898), suggesting that the short length of recombinant regions limits phylogenetic conflict. We also introduce RECOSIM, an unsupervised machine-learning tool for recombination detection that achieved higher precision than RDP5 on both simulated (93.4% vs. 80.0%) and empirical (98.1% vs. 39.3%) datasets. Collectively, these results establish recombination as a widespread, pan-serotypic phenomenon in DENV with implications for genomic surveillance, vaccine evaluation, and evolutionary inference.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.AI) 2026-06-16

Beyond Models: Reflections on Engineering AI-enabled Systems in a Project-Based Course

作者:
Amir Mashmool↗Kishan Ravindra Sawant↗Mojtaba Shahin↗Nico Hochgeschwender↗Rainer Koschke↗

arXiv:2606.16842v1 Announce Type: cross Abstract: Teaching Software Engineering for AI-enabled systems entails addressing the integration of AI components within full-scale software architectures under realistic constraints. While machine learning courses emphasize model development, students often lack experience in architectural design, deployment, and monitoring of AI-enabled systems. Empirical evaluations of such system-oriented AI courses remain limited. This paper reflects on the design and implementation of a project-based master's-level course titled AI Algorithms: Theory and Engineering, at the University of Bremen, in which students developed a movie recommendation system while making architectural design decisions to address challenges related to scalability, deployment, and evolving requirements. We conducted a mixed-methods study combining analyses of student submissions and questionnaire responses to investigate integration challenges, learning outcomes, and opportunities for improvement. Our results indicate persistent difficulties in early architectural decisions, heterogeneous ML integration, evolving requirements, and data management, largely due to uneven ML and software engineering expertise. From the educator's perspective, the course fostered system-level reasoning and strengthened awareness of data-centric ML practices in AI-enabled systems.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-16

Planning with Unified Multimodal Models

作者:
Yihao Sun↗Zhilong Zhang↗Yang Yu↗Pierre-Luc Bacon↗

With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However, most of these approaches rely solely on language-based reasoning, which limits their ability to reason and make informed decisions. Recently, a promising new direction has emerged with unified multimodal models (UMMs), which support both multimodal inputs and outputs. We believe such models have greater potential for decision-making by enabling reasoning through generated visual content. To this end, we propose Uni-Plan, a planning framework built on UMMs. Within this framework, a single model simultaneously serves as the policy, dynamics model, and value function. In addition, to avoid hallucinations in dynamics predictions, we present a novel approach self-discriminated filtering, where the generative model serves as a self-discriminator to filter out invalid dynamics predictions. Experiments on embodied decision-making tasks show that Uni-Plan substantially improves success rates compared to VLM-based methods, while also showing strong data scalability, requiring no expert demonstrations and achieving better performance under the same training-data size. This work lays a foundation for future research in reasoning and decision-making with UMMs.

阅读与讨论 → 访问原文 →
18.
bioRxiv (Bioinfo) 2026-06-22

Complex-valued representations of time-series gene expression profiles for network analysis

作者:
Sun↗Cao↗Ikumi↗Shimizu↗K. K↗Sese↗

Time-series RNA sequencing provides a powerful framework for studying dynamic gene regulation, yet conventional analyses usually represent gene expression profiles as real-valued vectors in Euclidean space and quantify similarity using correlation or distance. Inspired by quantum information theory, we present a framework for encoding time-series gene expression profiles as complex-valued vectors comprising amplitude and phase components in Hilbert space. We designed multiple encoding models to represent gene expression in the amplitude of complex-valued vectors, encode temporal differences in the phase, and extend the phase representation to incorporate the direction of local expression changes. Gene-gene similarity was then quantified using fidelity, which measures the overlap between two encoded vectors. Evaluation using time-series RNA-seq datasets across diverse species and biological contexts showed that different encoding models produced distinct fidelity distributions that were related to, but distinct from, conventional correlation measures. We then constructed gene-gene networks using pairwise fidelity values and detected communities containing genes with similar temporal profiles. Although fidelity distributions differed across encoding models, the resulting communities captured major temporal expression programs, and functional annotations based on gene ontology and Kyoto encyclopedia of genes and genomes pathway analyses provided exploratory biological context. The detected communities were comparable to those obtained using conventional methods, including weighted correlation network analysis and fuzzy c-means clustering. Furthermore, as a proof-of-concept, we performed SWAP-test circuit simulations to mimic fidelity computation on a quantum computer; under noise-aware conditions, these simulations produced less accurate fidelity estimates with higher computational cost than classical computation. As a proof-of-concept, this study provides a complementary view of temporal transcriptome organization, rather than a uniformly superior alternative to conventional methods.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.LG) 2026-06-12

ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization

作者:
Shaghayegh Fazliani↗Krissh Chawla↗Jack Guo↗Yiren Shen↗Matthias Ihme↗Madeleine Udell↗

arXiv:2605.20763v2 Announce Type: replace Abstract: Rapid progress in aerodynamic shape optimization (ASO) has outpaced currently-available standardized evaluation frameworks. Fair comparison requires a unified benchmark spanning diverse shape classes, objective formulations, and matched-budget state-of-the-art baselines. We introduce ShapeBench, an open-source ASO benchmark with a unified API spanning 103 tasks across eight shape categories and multiple optimization regimes. Each ShapeBench task includes a validated surrogate for fast search; when feasible, a high-fidelity Computational Fluid Dynamics (CFD) pipeline for final verification is available, enabling systematic fidelity-gap analysis. ShapeBench provides a reproducible protocol with well-configured baselines to compare fairly using a consistent budget metric, allowing for comparison among both classical and LLM-driven methods, including general-purpose optimizers and a new domain-specialized evolutionary LLM baseline, ShapeEvolve. Results on ShapeBench demonstrate substantial variance in optimizer rankings across shape categories and problem formulations, with mean pairwise Spearman $\rho = 0.013$, so single-task conclusions do not reliably generalize across problem classes. The benchmark is also far from saturation; classical methods are rarely applicable across all shape categories and tasks, further highlighting the need for more general-purpose approaches.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CL) 2026-06-15

Persona-Pruner: Sculpting Lightweight Models for Role-Playing

作者:
Jinsu Kim↗Jihoon Tack↗Noah Lee↗Jongheon Jeong↗

Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at https://github.com/jsu-kim/Persona-Pruner.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-11

Models That Know How Evaluations Are Designed Score Safer

作者:
Katharina Deckenbach↗Haritz Puerto↗Jonas Geiping↗Sahar Abdelnabi↗

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-16

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

作者:
Yilong Zuo↗Xunkai Li↗Jing Yuan↗Qiangqiang Dai↗Hongchao Qin↗Ronghua Li↗

Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Existing RAG methods mostly rely on fixed Top-k retrieval over text chunks or pages. Text retrieval can compress the context but often loses visual and layout information; page-level visual retrieval preserves the original page, yet it also sends large irrelevant regions to the reader, leading to a static trade-off among evidence coverage, noise, and inference cost. This paper proposes MAGE-RAG, a multigranular adaptive graph evidence framework for long-document multimodal QA. MAGE-RAG uses page retrieval as the entry point for query-time evidence construction. Offline, it builds an evidence graph with page nodes and element nodes, encoding containment, reading order, layout adjacency, section hierarchy, and semantic-neighbor relations. At query time, an online evidence controller iteratively activates, opens, searches, and prunes evidence under explicit budgets. The resulting evidence subgraph is then rendered into structured multimodal reader input, allowing the LVLM to consume compact and relevant evidence within a limited context. On LongDocURL and MMLongBench-Doc, we establish a unified comparison and analysis protocol covering Direct MLLM, Text RAG, Page-level Visual RAG, and Graph/Agentic RAG. Experiments show that MAGE-RAG achieves 52.75 overall accuracy on LongDocURL, and 53.26 accuracy with 51.19 F1 on MMLongBench-Doc. Fine-grained breakdowns, budget-performance curves, ablations, and trace-based analysis further show that query-time evidence subgraph construction can balance dispersed evidence coverage with context-noise control. Our code is available at https://github.com/laonuo2004/MAGE-RAG.git.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.LG) 2026-06-11

MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs

作者:
Xinhao Cheng↗Zhihao Zhang↗Yu Zhou↗Jianan Ji↗Jinchen Jiang↗Zepeng Zhao↗Ziruo Xiao↗Zihao Ye↗Yingyi Huang↗Ruihang Lai↗Hongyi Jin↗Bohan Hou↗…

arXiv:2512.22219v2 Announce Type: replace-cross Abstract: We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kernel. MPK introduces an SM-level graph representation that captures data dependencies at the granularity of individual streaming multiprocessors (SMs), enabling cross-operator software pipelining, \rev{fine-grained overlap of computation and communication, and other optimizations that are infeasible under the conventional kernel-per-operator execution model}. The MPK compiler lowers tensor programs into optimized SM-level task graphs and generates fast CUDA implementations for each task, while the MPK in-kernel parallel runtime executes these tasks within a single persistent mega-kernel using decentralized scheduling across SMs. Together, these components provide end-to-end kernel fusion with minimal developer effort, while preserving the flexibility of existing programming models. Our evaluation shows that MPK significantly outperforms existing kernel-per-operator LLM serving systems, achieving up to 1.7$\times$ lower end-to-end inference latency and pushing LLM inference performance close to the limits of the underlying hardware. MPK is publicly available at https://github.com/mirage-project/mirage.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-16

Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction

作者:
Guangyue Peng↗Wei Li↗Wen Luo↗Houfeng Wang↗

Grammatical Error Correction (GEC) involves detecting and correcting the wrong usage of grammar. While large language models (LLMs) with in-context learning (ICL) capabilities have shown significant progress on various natural language processing (NLP) tasks, their few-shot performance on GEC remains suboptimal. This is mainly due to the challenge of retrieving suitable in-context demonstrations that capture error patterns instead of semantic similarity. In this paper, we demonstrate that LLMs can inherently capture information related to grammatical errors through their internal states. From these states, we extract the Grammatical Error Representation (GER), an informative and semantically neutral encoding of grammatical errors. Our novel GER-based retrieval method significantly boosts performance in ICL settings on multilingual GEC datasets, improving the precision of correction. For high-resource languages, our results on 8B-sized open-source models match those of closed-source models such as Deepseek2.5 and GPT-4o-mini. For low-resource languages, our $F_{0.5}$ scores surpass the baseline by up to a factor of 1.20. This method provides a more precise and resource-efficient solution for multilingual GEC, offering a promising direction for interpretable GEC research.

阅读与讨论 → 访问原文 →
25.
medRxiv (Medicine) 2026-06-19

"Us with them": Co-designing a caesarean section consent and debriefing intervention in West Cameroon

作者:
Fouogue↗J. T↗Sato↗Tina Day↗Matsui↗Kenne Djuatio↗W. C↗Kenfack↗Benova↗Filippi↗

Background Women-centred maternity care is a rights issue that determines the use of services. Such care ensures responsiveness to womens needs which is enacted through shared decision-making, review and response. In the West Region of Cameroon, informed consent (IC) and Debriefing for caesarean section (c-section) have been shown to be suboptimal or absent. This paper describes the participatory design of a quality-improvement hospital-based intervention. Methods From February to May 2025, we conducted a co-design process with three groups of stakeholders: 59 post c-section women and community representatives, 78 frontline c-section providers, and 29 directors of public and private hospitals. We followed four phases: planning, conducting, evaluating, and reporting. The conduct phase comprised five all-day workshops with post c-section women and community representatives, followed by five all-day workshops with the c-section providers. Finally, we held an 11th workshop with the hospital directors to scrutinize suggested interventions, evaluate their feasibility, and establish a consensus on their components. We described the intervention using the TIDieR (Template for Intervention Description and Replication) checklist. We documented the co-design process, using open-ended narratives to delineate interventions, and carried out real-time synthesis on visual aids (whiteboards and flipcharts). Intervention feasibility was quantified using a structured ad hoc matrix, while insights on facilitators and barriers were captured through qualitative free-text entries. We coupled data collection with constant comparison and triangulation through contemporaneous field notes, photographic documentation, and thematic mapping of stakeholders perceptions and interactive dynamics. Results Participants perspectives on the co-design were positive, and their motivation were very high although less than 50% reported previous involvement in co-design processes. More than 80% of participants found rated the co-design process as either good or very good. The final intervention comprised four components: (i) an in-service training; (ii) a standard operating procedure including a harmonised consent form and debriefing checklist; (ii) systematic supportive supervision, monitoring & evaluation; and (iv) a routine clinical audit. Each group of stakeholders upheld specific dimensions of the consent and debrief intervention. Post c-section women and community members emphasized emotional support, written discharge advice after debriefing, and zero tolerance of suboptimal consent and debriefing practices. Frontline c-section providers insisted on robust documentation for medico-legal protection. Hospitals Directors emphasized capacity-building and cultural friendliness. All the groups supported womans autonomous decision making. The intervention feasibility was rated high or very high by hospital directors except for the financial, infrastructural and technical domains. Conclusion This co-design process yielded a context-specific, multi-component intervention that was well accepted and deemed feasible across stakeholders. It provides a methodological approach to strengthening informed consent and debriefing as core elements of women-centred, accountable maternity care, and warrants implementation.

阅读与讨论 → 访问原文 →