探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19781

Towards Engineering Scaling Laws with Pretraining Data Composition

作者:

Jan-Lucas Uslu↗Kevin Greif↗Daniel Whiteson↗Benjamin Nachman↗

arXiv:2606.19781v1 Announce Type: cross Abstract: Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established for large language models, these relationships are emerging for large models in particle physics. As with language, empirical studies show that the performance scales as a power law. However, unlike natural language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining dataset itself to be engineered to influence the scaling. For the task of classifying hadronic jets produced in collisions of high-energy particle beams, we show that the scaling behavior can be engineered towards requiring more data rather than larger models by inclusion of pretraining data which is more diverse and better aligned with the downstream classification task.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2604.23130

From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks

作者:

Nilanjana Das↗Mathew Dawit↗Aman Chadha↗Manas Gaur↗

Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized. Recent mechanistic safety studies often explain such behavior through broad representational objects, including global refusal directions, activation steering vectors, and refusal-related SAE features. We instead ask whether jailbreak vulnerability can be traced to finer-grained, prompt-conditioned SAE feature subgroups. We introduce a token-driven mechanistic pipeline that decomposes the residual stream of Gemma-2-2B into Sparse Autoencoder (SAE) features and identifies feature subgroups associated with unsafe behavior. Using single-category unsafe examples from BeaverTails to reduce cross-category interference, we extract harmful concepts from adversarial responses and align them with concept-relevant prompt tokens through subspace similarity. We then apply three feature-grouping strategies: cluster-based, hierarchical-linkage, and single-token-driven, to identify SAE feature subgroups across all 26 layers. Finally, we amplify the top features in each subgroup and evaluate the resulting generations with a standardized harmfulness judge. Single-token-driven grouping achieves harmfulness comparable to full cluster-based grouping, showing that individual harmful prompt tokens are sufficient to localize vulnerability-relevant SAE feature subgroups without relying on broader cluster-level aggregation. These subgroups appear across early and mid-to-late layers, with stronger concentration in mid-to-late layers, where targeted steering exposes specific model vulnerabilities. Overall, our results suggest that jailbreak susceptibility can be traced to sparse, token-localized SAE feature subgroups, complementing prior accounts based on broad adversarial, refusal, or steering directions.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18782

RedactionBench

作者:

Sean Brynj\'olfsson↗Shashvat Jayakrishnan↗Esha Sali↗Diptanshu Purwar↗Madhav Aggarwal↗

Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII). While redacting PII is a data cleaning prerequisite, existing benchmarks conflate extraction mechanics with privacy semantics. A public phone number is not equivalent to a phone number in a medical record. Whether information constitutes a violation depends heavily on who holds it, why, and in what context, fundamentally differentiating redaction from simple entity recognition. Grounded in contextual integrity, we introduce RedactionBench, a manually annotated benchmark comprising 200 diverse documents across 11 domains, mostly seeded from real-world sources. We also introduce R-Score, a novel character-level metric that treats semantically similar redactions equally and nullifies shallow formatting choices, such as varying masking styles for phone numbers. Evaluations across Named Entity Recognition models, entity extraction Small Language Models, and frontier models equipped with agentic tools demonstrate that contextual redaction remains an unsolved problem. A human evaluation with over 80 users on RedactionBench reveals a stark dichotomy in privacy perceptions. Annotators show consensus with target labels for mandatory redactions (89.4 percent) and safe text preservations (94.1 percent), but fail to agree on contextual redactions (47.7 percent). This variance demonstrates the subjective nature of contextual privacy and motivates R-Score, which decouples contextual ambiguity from strict precision. We compare 35 models across families and report their performance in redacting PII. Finally, we release RedactionBench to establish a baseline for future privacy-preserving systems, hoping to inspire efficient model design and standardized evaluations.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11482

Building Social World Models with Large Language Models

作者:

Haofei Yu↗Yining Zhao↗Guanyu Lin↗Jiaxuan You↗

Understanding and predicting how social beliefs evolve in response to events – from policy changes to scientific breakthroughs – remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18191

DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction

作者:

Md Tawkat Islam Khondaker↗Raymond Li↗Muhammad Abdul-Mageed↗Laks V. S. Lakshmanan↗Issam H. Laradji↗

arXiv:2606.18191v1 Announce Type: new Abstract: Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries. In contrast, many enterprise tasks instead require an agent to identify concrete workflows which is a sequence of action-steps. For example, rather than summarizing budgeting policies, an agent should be able to determine the steps needed to answer a question such as: "How do I request new headcount given a fixed budget?". Therefore, we introduce DRFLOW, a benchmark for evaluating personalized workflows predicted by agents from heterogeneous sources. Each task requires the agent to identify relevant evidence from scattered sources, then use that evidence to predict the correct action-step sequence for the user's task. DRFLOW contains 100 tasks across five domains, with 1,246 reference workflow steps grounded in more than 3,900 sources. We define seven diagnostic metrics covering factual grounding, step recovery, structural ordering, condition resolution, and personalization. We further present DRFLOW-Agent (DRFA), a workflow-oriented reference agent to predict personalized workflow. We show that although DRFA improves over strong baseline agents (upto 10.02% average F1 score), there is substantial room for improvement remains across these workflow metrics, indicating that predicting complete and correct personalized workflows remains a challenging frontier for deep research.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2603.05167

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

作者:

Avni Mittal↗Rauno Arike↗

Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prior context) and coverage (whether essential intermediate inferences are present). Using controlled perturbations, we construct examples with known causal error positions by replacing a single step with a logically inconsistent variant, and with controlled coverage deletions at varying rates, enabling direct measurement against reference labels. We evaluate three frontier LLM judges across three tasks: binary causal detection, causal step localization, and coverage scoring. Our results reveal that judge reliability is highly task-dependent, with no single model dominating across settings. While models often detect that an error exists, they struggle to accurately localize it, indicating a substantial gap between detection and attribution. Moreover, all judges systematically overestimate reasoning completeness, assigning high coverage scores even when substantial portions of intermediate reasoning are missing. These findings expose fundamental limitations of LLM judges in process-level evaluation and highlight the need for more reliable and calibrated methods when using LLMs to assess reasoning quality.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13392

MiniMax Sparse Attention

作者:

Xunhao Lai↗Weiqi Xu↗Yufeng Yang↗Qiaorui Chen↗Yang Xu↗Lunbin Zeng↗Xiaolong Li↗Haohai Sun↗Haichao Zhu↗Vito Zhang↗Pengyu Zhao↗

arXiv:2606.13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale. We introduce MiniMax Sparse Attention (MSA), a blockwise sparse attention built upon Grouped Query Attention (GQA). A lightweight Index Branch scores key-value blocks and independently selects a Top-k subset for each GQA group, enabling group-specific sparse retrieval while maintaining efficient block-level execution; the Main Branch then performs exact block-sparse attention over only the selected blocks. Designed around a principle of simplicity and scalability, MSA is deliberately streamlined, making it straightforward to deploy efficiently across a broad range of GPUs. To translate sparsity into practical speedups, we co-design MSA with a GPU execution path that uses exp-free Top-k selection and KV-outer sparse attention to improve tensor-core utilization under block-granular access. On a 109B-parameter model with native multimodal training, MSA performs on par with GQA while reducing per-token attention compute by 28.4x at 1M context. Paired with our co-designed kernel, MSA achieves 14.2x prefill and 7.6x decoding wall-clock speedups on H800. Our inference kernel is available at: https://github.com/MiniMax-AI/MSA. A production-grade natively multimodal model powered by MSA has been publicly released at: https://huggingface.co/MiniMaxAI/MiniMax-M3.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2603.17531

Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing

作者:

Pengzhen Chen↗Yanwei Liu↗Xiaoyan Gu↗Xiaojun Chen↗Wu Liu↗Weiping Wang↗

Recent advancements in diffusion-based image editing pose a significant threat to the authenticity of digital visual content. Traditional embedding-based watermarking methods often introduce perceptible perturbations to maintain robustness, inevitably compromising visual fidelity. Meanwhile, existing zero-watermarking approaches, typically relying on global image features, struggle to withstand sophisticated manipulations. In this work, we uncover a key observation: while individual image patches undergo substantial alterations during AI-based editing, the relational distance between patch pairs remains relatively invariant. Leveraging this property, we propose Relational Zero-Watermarking (Rel-Zero), a novel framework that requires no modification to the original image but derives a unique zero-watermark from these editing-invariant patch relations. By grounding the watermark in intrinsic structural consistency rather than absolute appearance, Rel-Zero provides a non-invasive yet resilient mechanism for content authentication. Extensive experiments demonstrate that Rel-Zero achieves substantially improved robustness across diverse editing models and manipulations compared to prior zero-watermarking approaches.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.17106

HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools

作者:

Aashna Garg↗Siddharth Singha Roy↗Jinu Jang↗Federico Brancasi↗Shengyu Fu↗

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities, requiring retraining whenever the catalog changes. We present HyDRA (Hybrid Dynamic Routing Architecture), a framework that predicts fine-grained, multi-dimensional capability requirements per query and matches them against configuration-defined model profiles via shortfall matching. A ModernBERT encoder with K=4 independent sigmoid heads scores each query along reasoning, code generation, debugging, and tool use; a shortfall-matching algorithm then selects the cheapest model whose capabilities meet the predicted requirements. The deployed predictor runs at 86 ms median CPU inference latency in production, and is fully decoupled from the model catalog – adding or removing models requires only a configuration change, with zero retraining. On SWE-Bench Verified (5-model pool: GPT-5.4-mini, Claude Haiku 4.5, GPT-5.3 Codex, Claude Sonnet 4.6, GPT-5.4), HyDRA's tunable shortfall threshold spans three regimes: peak-quality exceeds the always-strong Claude Sonnet 4.6 baseline (75.4% vs. 74.2% resolution) at 12.9% cost savings; iso-quality matches Sonnet at 54.1% cost savings, a 6x improvement over our prior in-house binary router at 9.1%; aggressive pushes savings to 72.5% for a 3.2-point quality trade. Results generalize across LiveCodeBench, BigCodeBench, and tau-bench. HyDRA is deployed to all users in GitHub Copilot's VS Code Chat auto-mode and – to our knowledge for the first time in the LLM routing literature – demonstrates language-invariant routing across CJK, European, and other script families.

阅读与讨论 → 访问原文 →

10.

medRxiv (Medicine) 2026-06-17 DOI: HASH:e0de9ec2b3150cc8e212b0feed31a113

Preserved Medial Temporal Lobe Flexibility Predicts Memory Generalization Only in the Context of Good Sleep Quality among Older African Americans

作者:

White↗P. G↗Budak↗Moallemian↗Fausto↗Gluck↗

Objectives: Poor sleep quality is a risk factor for Alzheimer's disease (AD). Older African Americans experience disproportionately high rates of sleep disturbance and AD. Medial temporal lobe (MTL) flexibility reflects dynamic neural reorganization and may be a marker of generalization performance. This study examined whether sleep quality moderates the association between MTL flexibility and memory generalization. Methods: Fifty older African Americans (MeanAge=69.7{+/-}6.21 years; 80% women) underwent rs-fMRI to quantify MTL flexibility, Rutgers Acquired Equivalence Task for memory generalization, and Pittsburgh Sleep Quality Index for sleep quality. Results: Greater MTL flexibility was associated with better generalization (r=0.367, p=.017). Good sleepers showed higher MTL flexibility (F(1,44)=8.11, p2=.156, p=.007) and superior generalization (F(1,46)= 12.33, p2=.211, p=.001). Sleep quality significantly moderated the MTL flexibility and generalization relationship ({beta}=-1.519, p=.012). Conclusions: Preserved MTL flexibility may confer generalization only in good sleepers, suggesting that sleep disturbance may disrupt the MTL neural resilience among older African Americans.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19812

Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery

作者:

Anushree Sinha↗Srivaths Ranganathan↗Abhishek Dharmaratnakar↗Debanshu Das↗

arXiv:2606.19812v1 Announce Type: new Abstract: Autonomous Large Language Model (LLM) agents are increasingly deployed in electronic discovery (e-discovery), where compounding errors across multi-step reasoning chains can constitute legal malpractice. Unlike single-turn retrieval, agentic workflows operating over privileged document corpora exhibit a class of failure we term "trajectory collapse": an early misclassification silently propagates, rendering an entire privilege review invalid. This paper makes three contributions. First, we propose a structured taxonomy of agentic failures in legal information retrieval, organized by functional stage. Second, we introduce a four-layer verification architecture – spanning planning, reasoning, execution, and uncertainty quantification – designed to intercept these failures before they compound. Third, we present a preliminary simulation study on a synthetic e-discovery corpus that demonstrates how mandatory Human-on-the-Loop (HOTL) escalation thresholds reduce privilege-waiver risk relative to fully autonomous baselines. Our results suggest that calibrated uncertainty thresholds can reduce privilege-waiver risk by up to 61% versus fully autonomous deployment, while routing fewer than one quarter of documents to attorney review.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18989

G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment

作者:

Fengying Ye↗Yanming Sun↗Runzhe Zhan↗Zheqi Zhang↗Lidia S. Chao↗Derek F. Wong↗

Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We present G-IdiomAlign, a gloss-pivoted benchmark where each idiom is anchored by an English gloss from Wiktionary. We further construct a high-confidence reference alignment set for reproducible evaluation. G-IdiomAlign supports two protocols: (1) a controlled Multiple-Choice Idiom Equivalence with typed distractors for error attribution; and (2) a Gloss-Contrastive Generation contrasting No-gloss and With-gloss inputs to isolate the effect of an explicit semantic pivot. Across diverse LLMs, a bias to literal translation is a dominant failure mode, especially when the target is a low-resource language. Glosses consistently improve Gloss-Contrastive Generation under an embedding-based semantic proxy, but performance remains modest, indicating substantial headroom in the open output space. Subsequent analysis on Qwen3-8B further suggests that cross-condition differences are concentrated more in attention heads than in layers, while better With-gloss generations coincide with stronger gloss anchoring.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2510.06445

A Survey on Agentic Security: Applications, Threats and Defenses

作者:

Asif Shahriar↗Md Nafiu Rahman↗Sadif Ahmed↗Farig Sadeque↗Md Rizwan Parvez↗

LLM-based agents are now used throughout cybersecurity. While these agents facilitate powerful and autonomous security applications, their autonomy opens up new attack surfaces, and the security community is actively building defenses to secure them. Yet the literature on this subject has grown quickly and unevenly. Existing surveys treat applications, threats, and defenses in isolation, leaving no unified account of how an agent's capabilities, vulnerabilities, and countermeasures interconnect. In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of over 260 papers, explaining how agents are used in downstream cybersecurity applications, inherent threats to agentic systems, and countermeasures designed to protect them. In addition, we provide detailed pillar-specific and cross-cutting analyses that show the security-lifecycle coverage of agentic applications, comparison between red-teaming and blue-teaming agents, and the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. We further map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, data modality coverage, and the growth of attack and defense research over time. Taken together, these findings indicate that agentic systems are structurally fragile by default and that securing them will require defenses that span the full agent lifecycle rather than single-layer fixes.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17398

SoK: AI-Augmented Binary Reversing

作者:

Yujeong Kwon↗Yiyue Zhang↗Shakhzod Yuldoshkhujaev↗Kexin Pei↗Dokyung Song↗Hyungjoon Koo↗

arXiv:2606.17398v1 Announce Type: cross Abstract: Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the irreversible loss of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and agentic AI systems have accelerated the adoption of AI-augmented binary reversing. Yet, the resulting body of work has become increasingly fragmented across reversing domains, artifact representations, learning approaches, and evaluation practices. This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing. We analyze 144 research papers published since 2015, and organize them into 22 binary reversing domains according to the inference tasks. We further introduce a unified taxonomy spanning conventional and AI-augmented reversing pipelines. Our taxonomy connects traditional analysis techniques, binary-derived artifacts, representation strategies, learning paradigms, and downstream inference tasks, while clarifying the emerging roles of LLMs and agentic AI systems. By establishing a common vocabulary and structured framework, we provide a holistic view of the field's evolution over the past decade. Our study reveals common structures underlying seemingly disparate approaches, highlights persistent technical challenges and evaluation gaps, and identifies promising opportunities for future research. Collectively, these insights clarify the current state of the field and provide a foundation for the next generation of reliable and scalable AI-augmented binary reversing systems.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2606.11503

Percolation on hierarchical lattices

作者:

Caio Alves↗Rangel Baldasso↗Carlos Gustavo Moreira↗Augusto Teixeira↗

arXiv:2606.11503v1 Announce Type: new Abstract: We consider independent Bernoulli percolation on top of sequences of hierarchical graphs. Given a graph $G_{1}$ with two distinguished vertices $a_{1}$ and $b_{1}$, the hierarchical graph with seed $G_{1}$ is the sequence $\big( G_{k} \big)_{k \geq 1}$ resulting from the inductive procedure, where the graph $G_{k+1}$ is obtained from $G_{k}$ by replacing each of its edges with a copy of $G_{1}$, attached by the vertices $a_{1}$ and $b_{1}$. We prove that, under sharp hypotheses, percolation on these graphs presents a unique phase transition. Second, we establish the existence of several critical exponents in this context, such as the critical exponents for the correlation length $\nu$, the surface tension $\mu$, the one-arm exponent $\alpha_{1}$. Several results are also obtained for their infinite counterpart $G_\infty$, which is the Benjamini-Schramm limit of $G_k$: uniqueness of the infinite cluster, continuity of $\theta(p)$, existence of the percolation-probability exponent $\beta$ and scaling relations for the critical exponents $\alpha_1$, $\nu$ and $\beta$. Furthermore, we analyze noise sensitivity for crossing functions in $G_{k}$ and establish sharp noise sensitivity in this setting. Finally, we propose a setup where it is possible to verify the locality hypothesis, stating that the critical threshold for percolation is a local property, while critical exponents are determined by the global geometry of the graph. As a consequence of the techniques developed here, we also provide a necessary and sufficient condition for the existence of a unique fixed point for the map $p \mapsto \mathbb{E}_p[g]$ in $(0,1)$, where $g:\{0,1\}^n \to \{0,1\}$ is a nontrivial monotone Boolean function.

阅读与讨论 → 访问原文 →

16.

medRxiv (Medicine) 2026-06-16 DOI: HASH:c800d1a2450ae9b68cb6115a3e84d666

Validation of a Smartphone-Image-Based Computer-Vision Model for Lean Mass and Body Fat Estimation Against Dual-Energy X-ray Absorptiometry

作者:

Reynolds↗Gerard↗Jordan↗Streby↗Stoll↗Bowers↗Hewitt↗Bargamian↗Sapper↗Burdick↗T. E↗Kackley↗…

Introduction Body composition, rather than body weight alone, is an increasingly important health metric, and preservation of lean mass has become a central concern in obesity treatment, aging, and chronic disease management. Dual-energy X-ray absorptiometry (DXA) provides accurate assessment of fat and lean tissue, but its cost and logistical requirements limit repeated measurement. Computer-vision approaches show promise for estimating adiposity from smartphone images, but lean-mass estimation remains less established. Methods We evaluated a computer-vision body composition model, applied to consumer-grade smartphone photographs, against DXA in a held-out validation sample of 195 adults from an ongoing cross-sectional study. Body fat percentage and total lean mass percentage were co-primary outcomes; for total lean mass percentage, an image-only configuration (no added covariates) was pre-specified as primary. Agreement was quantified using Lin's concordance correlation coefficient (CCC) as the lead statistic, with Pearson correlation, mean absolute error, root mean square error, mean bias, and Bland-Altman limits of agreement. In secondary analyses, appendicular lean mass and total lean mass percentage were each estimated with and without routine anthropometric and demographic inputs (body weight, height, age, and sex). Results Total lean mass percentage agreed with DXA from image features alone (CCC 0.916). Body fat percentage, estimated with routine inputs added, agreed at least as closely (CCC 0.930). Adding routine inputs barely changed agreement for total lean mass percentage but markedly improved it for appendicular lean mass, an absolute quantity that scales with body size. Conclusions A smartphone-image-based model estimated both body fat and lean mass with strong agreement to DXA, with lean mass percentage from image features alone. The approach needs no fixed equipment or ionizing radiation. Whether it can track change over time, including in incretin-based weight loss where lean mass preservation is a concern, was not assessed in this cross-sectional study.

阅读与讨论 → 访问原文 →

17.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2606.11432

Additive Noise, Shift Recovery, and Signed Signals in the Cumulative Distribution Transform

作者:

Harbir Antil↗Ratna Khatri↗Aryan Saxena↗

arXiv:2606.11432v1 Announce Type: cross Abstract: The cumulative distribution transform (CDT) is a quantile-based transport representation that exactly linearizes one-dimensional translations of positive densities. We study how this structure behaves under additive perturbations and how it can be exploited for shift recovery. Under a local nondegeneracy condition, we derive a first-order expansion showing that additive noise in physical space induces a nonlocal perturbation in CDT space through the primitive of the noise, weighted by the reciprocal density. This yields an explicit description of transform-domain sensitivity and shows, in particular, that perturbations are amplified in low-density regions. When the physical-space perturbation is modeled as a centered Gaussian random field, the induced first-order CDT perturbation is again Gaussian, with an explicit covariance kernel. We then use this structure to study recovery in CDT coordinates. In the known-template setting, the transport shift is obtained by projection onto the constant mode, giving an explicit estimator together with exactness in the noiseless case and a stability bound under perturbations. In the unknown-template setting, multiple observations permit joint recovery of the shifts and a common template up to the natural constant-mode gauge, leading to a simple de-shift–and–average procedure. We also consider a signed-signal analogue based on the signed cumulative distribution transform (SCDT), where shifts are estimated numerically by feature matching and unknown templates are recovered by alternating alignment and averaging. Numerical experiments validate the perturbation analysis and illustrate effective recovery for both density-valued and signed signals.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16484

Unified Multimodal Model for Brain MRI Imputation and Understanding

作者:

Zhiyun Song↗Che Liu↗Tian Xia↗Avinash Kori↗Wenjia Bai↗

Multimodal large language models (MLLMs) hold great potential for medicine, as they inherit knowledge from LLM and allow multiple data modalities to be integrated, analysed and interpreted in natural language. However, the field of medical MLLMs is constrained by non-trivial challenges, notably the scarcity of high-quality training data and the frequent occurrence of missing data in the real-world clinical setting. Here, we propose a novel unified multimodal model, UniBrain, for brain magnetic resonance image (MRI) analysis. To address potential missing brain MRI modalities, we employ a unified training strategy to perform joint imaging modality imputation and brain image understanding. During training, an interleaved and description-enriched data flow is constructed to train the model in an autoregressive manner, enabling medical reasoning with generated multimodal data. A self-alignment strategy is introduced to leverage dense image embeddings to learn fine-grained anatomical features without requiring detailed image captions. Furthermore, we propose a dynamic hidden state mechanism to alleviate the exposure bias during long-context multimodal inference. Extensive experiments on multi-disease brain MRI dataset demonstrate that UniBrain achieves high performance for brain image imputation, understanding, and disease diagnosis under various extents of modality incompleteness.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20517

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

作者:

Maria Ivanova↗Pavel Zadorozhny↗Rodion Levichev↗Ivan Petrov↗Adamenko Pavel↗Ivan Lopatin↗Alexey Kutalev↗Dmitrii Babaev↗

arXiv:2606.20517v1 Announce Type: new Abstract: LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can generalize across the diverse programming languages required in real-world software engineering. We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python. Multi-LCB transforms Python tasks from the LCB dataset into equivalent tasks in other languages while preserving LCB's contamination controls and evaluation protocol. Because it is fully compatible with the original LCB format, Multi-LCB will automatically track future LCB updates, enabling systematic assessment of cross-language code generation competence and requiring models to sustain performance well beyond Python. We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting, language-specific contamination, and substantial disparities in multilingual performance. Our results establish Multi-LCB as a rigorous new benchmark for multi-programming-language code evaluation, directly addressing LCB's primary limitation and exposing critical gaps in current LLM capabilities.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2501.09310

Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors

作者:

Jiawei Shen↗Chengcheng Wan↗Ruoyi Qiao↗Jiazhen Zou↗Hang Xu↗Yuchen Shao↗Yueling Zhang↗Weikai Miao↗Geguang Pu↗

Large language models (LLMs) have been adopted for text-to-SQL tasks, utilizing their in-context learning (ICL) capability to translate natural language questions into SQL queries. However, such a technique faces correctness problems. In this paper, we conduct the first comprehensive study of text-to-SQL errors of ICL-based techniques. Our study covers four representative ICL-based techniques, five basic repairing methods, two benchmarks, and two LLM settings. We find that text-to-SQL errors are widespread and summarize 27 error types of 7 categories. We also find that existing repairing attempts have limited correctness improvement while having high computational overhead and many mis-repairs. Based on these findings, we propose MapleDoctor, a novel text-to-SQL error detection and repairing framework. The evaluation demonstrates that MapleDoctor outperforms existing solutions by repairing 13.8% more queries with a negligible number of mis-repairs and reducing 67.4% repair latency. The artifact is publicly available at GitHub.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14507

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

作者:

Chenyu Zhou↗Qiliang Jiang↗Boguang Pan↗

arXiv:2606.14507v1 Announce Type: new Abstract: Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs. We study this behavior as a generation and control surface. In Gemma 4 12B, high-capacity q/k/v/o LoRA raises class-aware F1@0.3 from 0.007 to 0.448 while inducing repeated-tail pressure (duplicate rate 0.080, max repeat 23). A q/v rank sweep keeps max repeat at 21-22 across ranks 4-64, showing capacity persistence. The target signal is separable: object-level repeat-stop removes exact repeated records (duplicate rate 0.000, max repeat 1) while preserving F1 (0.494 to 0.490) and stricter F1@0.5 (0.381 to 0.385). Structure-axis probes localize the effect to bbox-coordinate object lists; dense non-bbox and spatial/count JSON remain repeat-clean, including under high-capacity adapters. Qwen3-VL-8B reproduces a clean controlled endpoint (F1@0.3 0.318, duplicate rate 0.000), and COCO 2017 reproduces acquisition plus duplicate pressure. Dense coordinate-list adaptation therefore creates a structure-bound, cross-family interference surface that can be measured and controlled.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16590

Infant Spontaneous Movement Noise Improves Exploration in Deep RL

作者:

Francisco M. L\'opez↗Markus R. Ernst↗Francisco Cruz↗Matej Hoffmann↗and Jochen Triesch↗

arXiv:2606.16590v1 Announce Type: cross Abstract: Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise can improve exploration efficiency by producing smooth trajectories with better coverage of the state space. We inquire whether action noise inspired by infant spontaneous movements can also improve exploration in deep RL. We find that the power spectral densities of babies' end-effector velocities follow a colored noise process where the spectral exponent increases with age. Inspired by this developmental pattern, we introduce a mechanism that progressively increases the temporal auto-correlation of exploration noise during RL training, matching the infant statistics. Experiments across several RL environments show that infant-inspired noise produces structured exploratory behavior and can improve learning efficiency compared to conventional exploration strategies. These findings suggest that human motor and cognitive development can provide useful guidance for designing learning mechanisms in artificial agents. Our code is available at https://github.com/trieschlab/baby-noise-rl.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18124

Unintended Effects of Geographic Conditioning in Large Language Models

作者:

Naz Col↗David M. Chan↗

Modern conversational AI systems frequently rely on user metadata to localize responses, yet the unintended regional biases introduced by this hidden context remain poorly understood. In this work, we evaluate location leakage: the phenomenon where a model generates geographic references despite receiving a geographically neutral user prompt. Across both creative writing and open-ended Q&A prompts, even state-of-the-art LLMs systematically favor region-specific outputs when exposed to location metadata, with leakage spiking by up to 793 times above baseline (e.g., from 0.04% to 31.7% for Llama 3.1-8B, and 21.3% and 8.8% for Qwen3-8B and Claude Sonnet 4.6, respectively). Our analysis further shows a novel structural conditioning effect: replacing the injected location with the placeholder "Unknown" still elevates leakage by up to 72 times above baseline, demonstrating that the user profile frame itself, independent of any geographic content, acts as a generative conditioning signal.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.07840

SAGE: Scalable AI Governance & Evaluation

作者:

Benjamin Le↗Xueying Lu↗Nick Stern↗Wenqiong Liu↗Igor Lapchuk↗Xiang Li↗Baofen Zheng↗Kevin Rosenberg↗Jiewen Huang↗Zhe Zhang↗Abraham Cabangbang↗Satej Milind Wagle↗…

arXiv:2602.07840v4 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92$\times$ lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25\% lift in LinkedIn daily active users.

阅读与讨论 → 访问原文 →

25.

medRxiv (Medicine) 2026-06-16 DOI: HASH:57f5c75d29d8f40beb20ce338ce748df

Comparative Effectiveness and Safety of Prophylactic Vasopressors for Preventing Post-induction Hypotension in the Elderly: A Systematic Review and Network Meta-analysis

作者:

Zhang↗Wang↗Duan↗C. L↗Di↗Y. R↗

Background: Post-induction hypotension is a predictable haemodynamic hazard in older adults undergoing general anaesthesia. Prevention remains divided among volume optimisation, anaesthetic dose reduction, rescue treatment after hypotension occurs and proactive vasoactive support. Methods: We searched PubMed, Embase, Web of Science, CENTRAL, CNKI, Wanfang and VIP from inception to 30 March 2026. Eligible studies were randomised trials of prophylactic vasoactive drugs given before, during or immediately after induction in older adults. The primary outcome was post-induction hypotension. Secondary outcomes were post-induction mean arterial pressure (MAP), systolic arterial pressure (SBP), heart rate (HR) and reported haemodynamic adverse events. Random-effects network meta-analysis was used, and confidence in network estimates was assessed using CINeMA principles. Results: Thirty-one trials including 2,821 participants were included in the revised network. Compared with placebo/control, all active agents favoured lower post-induction hypotension. The most favourable point estimates were observed for phenylephrine (odds ratio [OR] 0.17, 95% confidence interval [CI] 0.01 to 2.16) and metaraminol (OR 0.19, 95% CI 0.02 to 1.53), although both were imprecise. More precise reductions were observed for methoxamine (OR 0.23, 95% CI 0.13 to 0.43), norepinephrine (OR 0.25, 95% CI 0.13 to 0.47) and ephedrine (OR 0.34, 95% CI 0.19 to 0.63). Phenylephrine ranked highest for MAP support, norepinephrine ranked highest for SBP support, and ephedrine ranked highest for HR preservation. Global inconsistency was detected for SBP but not for hypotension incidence, MAP or HR, supporting cautious profile-based interpretation. Conclusions: Prophylactic vasopressor choice during induction should be guided by haemodynamic phenotype rather than ranking alone. In the revised network, active prophylaxis consistently favoured lower hypotension, but sparse nodes produced uncertainty. Norepinephrine retained a comparatively balanced profile when vasodilatory post-induction hypotension is anticipated, phenylephrine and related alpha-agonists provided stronger pressure support when HR and cardiac-output reserve are preserved, and ephedrine was most relevant when chronotropic support is desired. Keywords: general anaesthesia; induction; hypotension; norepinephrine; phenylephrine; ephedrine; network meta-analysis; older adults.

阅读与讨论 → 访问原文 →