探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-10 DOI: HASH:ff752b76ef78c78b59a8576bee34cade

Developing a Unified Criminal Justice Pathway into Drug and Alcohol Treatment from Police Custody: A Public Health Service Evaluation and Pathway-Design Project in Blackpool, United Kingdom

作者:

Badmos↗A. O↗AbdulKareem↗Mills↗Gawne↗Idris↗

Introduction: Blackpool, England's most deprived local authority, has the highest drug-related death rate in the country. People in police custody with problem substance use are a key Core20PLUS5 inclusion-health group, yet referral from the police into structured drug and alcohol treatment is fragmented and relies heavily on self-report. We evaluated the current police-to-treatment route in Blackpool and designed an evidence-informed unified pathway. Materials and Methods: A mixed-methods service evaluation and pathway-design project was conducted during a six-month General Practice / Public Health rotation. Routinely collected referral data from Horizon (the local specialist drug and alcohol service) covering the 47-month period from December 2019 to October 2023 were analysed. Findings were triangulated with national policy, the Project ADDER and Liaison and Diversion evaluations, and the international evidence on police-led pre-arrest diversion. Results: Of 5,900 total referrals into Horizon over 47 months, only 269 (4.56%) originated from the police. Police referrals accounted for fewer than 5% of monthly referrals in 30 of 47 months, for 5 to 9.9% in 16 months, and for >/= 10% in only one month (10.8%, December 2022). Blackpool recorded 76 drug-misuse deaths in 2019-21 (19.4 per 100,000, approximately four times the England rate). A six-step unified pathway is proposed: Initiate Referral (opt-out, from ADDER Police and Liaison and Diversion); Initial Assessment; Tailored Treatment Plan; Continuous Support; Collaboration and Monitoring; and Evaluation and Adjustment. Conclusions: Police contact is markedly under-used as a gateway to treatment despite Blackpool having the highest drug-related mortality in England. An opt-out, multi-agency pathway anchored in Core20PLUS5 has the potential to narrow the treatment gap, reduce re-offending, and address the structural health inequalities that drive premature mortality.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15621

Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation

作者:

Nils Matteson↗

Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes. Published methods re-feed the transcript prefix as a fresh prompt, assuming this reproduces the state the model passed through during generation. We measure what that assumption costs on a stock inference engine, with a three-pass design: continuations resumed from the verified decode-time KV state, an identical second exact pass (a replica noise floor), and a re-feed pass. Across six configurations and three models (including a GRPO-trained checkpoint), at low-margin decision tokens, re-feeding changes the credit estimate at rates 14-28 percentage points above the replica floor (7-21pp under a treatment-independent conditioning; problem-clustered t = 2.9-6.4). Most changes are zero-boundary crossings of the quantized estimator rather than polarity reversals, and the perturbation is consistent with mean-zero, so averaged quantities are largely safe; but selection is not: a critical-token set chosen by thresholding $|\hat{A}_t|$ under re-feed overlaps the exact-resume selection at Jaccard 0.34-0.90, versus a 0.63-0.96 replica ceiling. A causal confirmation closes the loop: under vLLM's batch-invariant kernels all three passes are identical on every measured channel, with both disagreement rates exactly zero. Replica passes themselves disagree on 9-23% of eligible estimates: single-sample credit measurements at decision tokens are unreliable under any replay. Settings were fixed in advance; exact-pass cache hits in the second campaign are instrumented (100% hit rate, 3,434 pivots); total compute was under 10 USD. We recommend that counterfactual credit studies resume decoder state or use batch-invariant kernels, and report a replica floor.

阅读与讨论 → 访问原文 →

03.

medRxiv (Medicine) 2026-06-17 DOI: HASH:65a44857aaef1114ef08d121f834ffea

Proteomics Uncovers Cryptic JPH2 Loss in Paediatric Dilated Cardiomyopathy

作者:

Smith-Diaz↗C. C↗Iaprintsev↗Huckstep↗Macciocca↗Piers↗A. T↗Henden↗Bryen↗Stewart↗Butters↗Baker↗…

Despite recent advances in next-generation sequencing, genetic diagnostic rates for dilated cardiomyopathy (DCM) remain low. Among paediatric DCM, causes are often heritable, with a greater frequency of de novo, recessive and syndromic causes of disease. Novel diagnostic methods are therefore required to solve monogenic cases. To assess the value of proteomics as a diagnostic tool for paediatric DCM, we obtained left ventricle myocardial samples from paediatric patients undergoing heart transplantation at the Royal Children's Hospital, Melbourne. We performed genome sequencing and proteomics and leveraged this multi-omics dataset to uncover the molecular cause of disease in a gene elusive proband. The proband carried a heterozygous JPH2 frameshift variant identified on clinical exome sequencing. However, proteomic analysis showed a pronounced downregulation of JPH2, suggestive of biallelic loss-of-function. Closer inspection of the genomic data revealed a large inversion (~8.34 Mb) with a breakpoint falling within intron 5 of JPH2 that displaces the 3'UTR from the coding transcript. The two variants were confirmed to be in trans using long read DNA sequencing, consistent with a diagnosis of JPH2 autosomal recessive DCM. Finally, we applied RNA sequencing with total RNA library preparation to show that transcripts containing a 3'UTR were reduced to ~10% relative to controls. As a proof-of-principle, we present the first reported use of proteomics from explanted cardiac tissue to provide a genetic diagnosis. Our methodology has broad relevance to patients with genetically unsolved Mendelian diseases, who might undergo organ transplantation as part of clinical management.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2510.27353

An In-depth Study of LLM Contributions to the Bin Packing Problem

作者:

Julien Herrmann↗Guillaume Pallez↗

arXiv:2510.27353v2 Announce Type: replace Abstract: Recent studies have suggested that Large Language Models (LLMs) could provide interesting ideas contributing to mathematical discovery. This claim was motivated by reports that LLM-based genetic algorithms produced heuristics offering new insights into the online bin packing problem under uniform and Weibull distributions. In this work, we reassess this claim through a detailed analysis of the heuristics produced by LLMs, examining both their behavior and interpretability. Despite being human-readable, these heuristics remain largely opaque even to domain experts. Building on this analysis, we propose a new class of algorithms tailored to these specific bin packing instances. The derived algorithms are significantly simpler, more efficient, more interpretable, and more generalizable, suggesting that the considered instances are themselves relatively simple. We then discuss the limitations of the claim regarding LLMs' contribution to this problem, which appears to rest on the mistaken assumption that the instances had previously been studied. Our findings instead emphasize the need for rigorous validation and contextualization when assessing the scientific value of LLM-generated outputs.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16206

Measuring Whether LLM Tutors Teach or Solve: A Diagnostic for Educational Impact

作者:

Junyi Yao↗Zihao Zheng↗Baichuan Li↗

Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learning support. Motivated by recent calls to measure the social impact of NLP systems in practice, we study whether public LLM tutoring benchmarks distinguish learning-supportive behavior from mere answer production. We propose a lightweight diagnostic based on the gap between solving-oriented and pedagogy-oriented benchmark performance. Using public MathTutorBench leaderboard results, we show that these dimensions are only partially aligned: across eight publicly reported models, the correlation between solving and pedagogy composites is 0.421, and several models shift meaningfully in rank when evaluation moves from solving to pedagogy. We then analyze the public TutorBench sample and show that agency-relevant behaviors are explicitly encoded in benchmark rubrics, especially in active-learning settings that reward guiding questions, calibrated hints, and non-disclosive scaffolding. Together, these findings suggest that educational-impact evaluation should not treat task success as a sufficient proxy for learning support. We argue that public tutoring benchmarks can better support positive-impact evaluation by reporting solving-oriented and pedagogy-oriented scores separately and by making disclosure-sensitive, student-agency-preserving criteria more explicit.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15483

Evaluative Judgement in Teaching AI-based Translation: A Class-room Case Study of AI-Mediated Translation and Post-Editing

作者:

Gokhan Dogru↗

Drawing on 23 anonymized student pro-jects from a fourth-year Machine Transla-tion and Post-editing course in a BA-level translation programme, this paper exam-ines how structured comparison of gen-eral-purpose LLMs and online MT sys-tems can elicit evaluative judgement in AI-mediated translation. Students translat-ed short specialised English Wikipedia texts into Catalan or Spanish, generated four system outputs, evaluated them using automatic metrics and human adequa-cy/fluency assessment, selected one output for post-editing, and justified their deci-sion in written reports. Descriptive counts are reported for all 23 projects, while qualitative interpretation is based on the 22 cases accompanied by written reports. Results show that students did not treat automatic metrics as final authority: final post-editing selections often diverged from metric rankings and were justified through adequacy, fluency, terminology, naturalness, and expected post-editing ef-fort. The study therefore does not bench-mark systems under controlled conditions; it analyses how students justified system choice within an authentic classroom as-signment.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15693

Imperfect Visual Verification for Code Edition : A Case Study on TikZ

作者:

Charly Reux↗Mathieu Acher↗Djamel Eddine Khelladi↗Cl\'ement Quinton↗Olivier Barais↗

arXiv:2606.15693v1 Announce Type: cross Abstract: LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks involving programs such as TikZ that generate visual artifacts remain challenging, in particular on visual code customization. Unlike generation from scratch, customization requires localized, semantics-preserving edits: the model must locate relevant code, modify it according to the instruction, and preserve the remaining structure and rendering. Approaches based on post-hoc iterative refinement/correction where a verifier provides feedback to guide corrections, have shown promise. However, in the case of programs with a visual outcome such as in TikZ, where correctness is harder or likely impossible to formalize and evaluate automatically, deterministic verifiers do not exist. Hence, developers can only rely on imperfect verifiers. In this paper, we conduct an empirical study to answer:to what extent can iterative refinement remain effective when the verifier itself is unreliable?} We use TikZ as a focused case study that isolates the core difficulties of the problem (weak code structure, fine-grained visual semantics, and difficult feature localization) in a controlled and challenging setting. We define visual code customization as an iterative editing problem with an imperfect oracle, and introduce a framework for analyzing such iterative refinements. We conduct a large-scale study and evaluate multiple LLM-based and tool-augmented visual verifiers within iterative refinement pipelines, and perform extensive manual annotation of refinement trajectories to assess verifier behavior and feedback quality. Our findings show that even imperfect verifiers can determine with moderate accuracy whether visual instructions are applied to code, achieving F1-scores up to 0.815. Feedback improves iterative refinement, especially for weaker models, adding 11–20 perfect customizations for Qwen3-vl-30b-a3b-Instruct, while stronger models like Gemini-3 gain fewer improvements (+5) but benefit more from accurate verification that prevents premature acceptance. Feedback is effective only when it precisely identifies image issues, provides actionable guidance, addresses all relevant problems, and remains grounded in the original instruction.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16203

DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis

作者:

Jun-En Ding↗Spencer Chen↗Henry Noren↗Daniel Valdivia↗Christine Yohn↗Suhina Patel↗Taylor Zink↗Hai Sun↗Feng Liu↗

Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI), yet early identification remains challenging due to the complex structural and functional alterations it induces in the brain. To address this, we propose a dynamic multimodal Mixture-of-Experts (MoE) framework that integrates functional and structural MRI through time-aware functional-structural encoding and class-conditioned expert routing. Within this framework, modality-specific and cross-modal experts learn complementary representations, while a Modality-Class MoE (MCoE) module dynamically dispatches expert weights according to each classification objective. Experimental results across three binary classification tasks demonstrate that the framework consistently outperforms static fusion baselines, and high-interpretability analyses further reveal meaningful region-of-interest (ROI) interactions. This dynamic multimodal expert framework effectively captures class-dependent brain interaction patterns and provides an interpretable approach for PTE diagnosis and risk stratification.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2603.09420

Class-Incremental Motion Forecasting

作者:

Nicolas Schischka↗Nikhil Gosala↗B Ravi Kiran↗Senthil Yogamani↗Abhinav Valada↗

arXiv:2603.09420v3 Announce Type: replace-cross Abstract: Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents. However, existing approaches typically assume a closed-world setting with a fixed object taxonomy and access to high-quality perception, limiting their applicability in the real world where perception is imperfect, and new object classes may emerge over time. In this work, we introduce class-incremental motion forecasting, a novel setting in which new object classes are sequentially introduced over time and future object trajectories are predicted directly from camera images. We propose the first end-to-end framework for this setting, which adapts to newly introduced classes while mitigating catastrophic forgetting of previously learned ones. Our method generates motion forecasting pseudo-labels for known classes and matches them with 2D instance masks from an open-vocabulary segmentation model. This 3D-to-2D keypoint voting mechanism filters inconsistent and overconfident predictions, while a query feature variance-based replay strategy samples informative past sequences to preserve prior knowledge. Extensive evaluations on nuScenes and Argoverse 2 show that our approach successfully preserves performance on known classes while effectively adapting to novel ones. We further demonstrate zero-shot transfer to real-world driving and show that the framework extends naturally to open- and closed-loop end-to-end class-incremental planning on nuScenes and NeuroNCAP. Code and models will be made publicly available at https://omen.cs.uni-freiburg.de.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15219

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

作者:

Siyu Chen↗Beining Wu↗Miao Lu↗Zhuoran Yang↗Tianhao Wang↗

arXiv:2606.15219v1 Announce Type: new Abstract: In this work, we tackle the following question: Can neural networks trained with gradient-based methods achieve the optimal computational-statistical tradeoff in learning Gaussian single-index models? Prior research has shown that any polynomial-time algorithm under the statistical query (SQ) framework requires $\Omega(d^{s^\star/2}\lor d)$ samples, where $s^\star$ is the generative exponent representing the intrinsic difficulty of learning the underlying model. However, it remains unknown whether neural networks can achieve this sample complexity. Inspired by prior techniques such as label transformation and landscape smoothing for learning single-index models, we propose a unified gradient-based algorithm for training a two-layer neural network in polynomial time. Our method is adaptable to a variety of loss and activation functions, covering a broad class of existing approaches. We show that our algorithm learns a feature representation that strongly aligns with the unknown signal $\theta^\star$, with sample complexity $\widetilde{O} (d^{s^\star/2} \lor d)$, matching the SQ lower bound up to a polylogarithmic factor for all generative exponents $s^\star\geq 1$. Furthermore, we extend our approach to the setting where $\theta^\star$ is $k$-sparse for $k = o(\sqrt{d})$ by introducing a novel weight perturbation technique that leverages the sparsity structure. We derive a corresponding SQ lower bound of order $\widetilde{\Omega}(k^{s^\star})$, matched by our method up to a polylogarithmic factor. Our framework, especially the weight perturbation technique, is of independent interest, and suggests potential gradient-based solutions to other problems such as sparse tensor PCA.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15610

LLM Judges Have Dark Current: A Psychometric Datasheet for LLM-as-a-Judge Evaluation

作者:

Hiroyasu Usami↗Keisuke Hara↗Ayato Tsuboi↗Naohiko Matsuda↗

LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce. Yet these judges are often reported as scalar accuracy, win-rate, or agreement devices. We argue that a judge should instead be reported as a measurement instrument. We introduce a Judge Datasheet protocol that measures dark current under true-vacuum inputs, stable cross-sensitivity to same-quality surface variation, positional false preference, target sensitivity on a controlled quality ladder, and the criterion or operating point induced by tie instructions. The direction-stability decomposition reveals that apparent Delta0 preference can be stable surface response or disguised position bias. In a three-judge open-weight case study, Llama-3.1-8B shows high dark current and presentation-conflicted Delta0 behavior, Qwen2.5-14B is vacuum-clean and target-sensitive but mixes stable and positional over-discrimination, and Qwen2.5-32B is vacuum-clean with low stable cross-sensitivity and low positional false preference. A strict tie criterion eliminates Qwen32B Delta0 false preference but absorbs marginal Delta1 target signals into ties while preserving Delta5 sensitivity. The results show that prompting moves the criterion, not the resolution. We do not claim that the downstream mechanism hypothesis that motivated this work is confirmed; the contribution is a metrological protocol for measuring the measuring device before downstream claims are made.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11792

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

作者:

Yuansheng Gao↗Wenbin Xing↗Jiahao Yuan↗Kaiwen Zhou↗Han Bao↗Zonghui Wang↗Wenzhi Chen↗

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-22 DOI: HASH:8edbff62fe2b35fc62fa198183028e60

Associations of Chemical Exposures with Psychological Distress and Depression Diagnosis among Waste Pickers in Brasilia, Brazil: A Cross-Sectional Study

作者:

King Stone↗K. L↗Maia Pelagalli↗Melanson↗Steelman↗Cruvinel↗V. R. N↗Pintas↗C. P↗Macena↗Thygerson↗Thacker↗…

Introduction: Waste pickers face chemical exposures. We evaluated whether chemical exposure is associated with psychological distress and depression. Methods: A 2017 cross-sectional survey included 1,141 waste pickers working in the Estrutural open dump in Brasilia, Brazil. Participants self-reported occupational exposure to 11 chemical categories, 17 psychological distress symptoms, and depression diagnoses. Associations of chemical exposure with mean psychological distress scores and depression prevalence were assessed, adjusted for age, sex, marital status, and income. Results: Mean psychological distress score was higher among those exposed to any chemical (mean of 8.1 vs 6.1; adjusted mean difference [aMD]: 1.8 [0.9, 2.7]) and higher among those exposed to each of 11 chemical categories, for example, smoke (aMD: 1.2 [0.6, 1.7]), batteries (aMD: 1.5 [1.0, 1.9], and oils (aMD: 1.3 [0.9, 1.8]). Depression was more prevalent among those exposed to oils (16.6% vs 10.6%; adjusted prevalence difference [aPD]: 6.3% [95% CI: 2.3, 10.2]), cleaning products (aPD: 5.4% [1.2, 9.5]), medications (aPD: 4.7% [0.6, 8.8]), and aerosols (aPD: 5.3% [1.3, 9.3]) but, not smoke, batteries, greases, insecticides, solvents, paints, chemical containers, or any chemical. Conclusion: These associations highlight the need to consider policy level protections for waste pickers to reduce chemical exposure and guard against psychological distress. Further research is necessary to explore which specific chemicals, within broad chemical categories, are associated with psychological distress and depression.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13753

The Weight Norm Sets the Grokking Timescale: A Causal Delay Law

作者:

Truong Xuan Khanh↗Doan Hoang Viet↗Luu Duc Trung↗Phan Thanh Duc↗

arXiv:2606.13753v1 Announce Type: cross Abstract: Grokking is the delayed onset of generalization in neural networks, arising long after they fit the training data. Whether the weight norm causes this delay is disputed: some studies report a critical norm at the transition, others observe grokking with no fixed norm at all. We settle this by intervening on the norm during training rather than only observing it. Under free training with weight decay, networks grok when the weight norm reaches a value Wc that varies little across seeds and learning rates (CV 1 to 2 percent) and grows with the modular base as a power law. When we instead clamp the norm to a fixed multiple rho of Wc and hold it there, the network still groks, but the delay follows T_grok proportional to exp(alpha rho). One exponent, alpha near 7.5, fits this delay across four moduli (R^2 = 0.996). Over the swept ranges the held norm moves the delay by about 19x and the learning rate by only about 2x, and holding the norm above Wc slows grokking rather than preventing it. A final LayerNorm removes the dependence by decoupling weight scale from the network function; without it the exponential law returns. This pinned-norm delay is the exponential counterpart to the logarithmic delay predicted for a freely contracting norm.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13684

Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

作者:

Abdolali Faraji↗Mohammadreza Molavi↗Zohreh Rasoulkhani↗Mohammadreza Tavakoli↗G\'abor Kismih\'ok↗

Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematically studied. We evaluated the cross-dataset generalization of existing ML/DL methods and assessed LLMs with multiple prompting strategies on five datasets; the best prompting strategy combined in-context examples with course-specific action verbs. Supervised ML/DL models degraded substantially on unseen datasets, whereas LLMs were more stable, suggesting a robust alternative across diverse educational contexts. Based on the best prompting strategy, we also presented a lightweight UI that supports instructors in automatically classifying large question banks; a usability study indicated low workload and high usability.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11205

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

作者:

Matthew James Buchan↗

Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16056

Beyond the Blood Draw: Explainable Machine Learning for Non-Invasive Dysglycemia Risk Screening

作者:

Black Sun↗Chenyi Zhang↗Kaiyi Ji↗Xi Lu↗

arXiv:2606.16056v1 Announce Type: new Abstract: Dysglycemia, encompassing both prediabetes and diabetes, affects huge numbers of adults worldwide, yet many of them remain undiagnosed. We developed and validated machine-learning (ML) models for non-invasive screening of dysglycemia risk that require no laboratory tests. Pooling data from the National Health and Nutrition Examination Survey (NHANES) 2017–2023 (n=14,352), we trained six ML models with stratified 5-fold cross-validation and compared them with two established clinical risk scores. LightGBM achieved the highest area under the receiver operating characteristic curve (AUC=0.820, 95% CI: 0.806–0.835), outperforming the Finnish Diabetes Risk Score (0.745) and American Diabetes Association Risk Test (0.783). SHAP analysis identified age, race/ethnicity, and waist-to-height ratio as the most influential predictors. Subgroup analyses confirmed consistent performance across demographic strata (AUC: 0.735–0.832). These results demonstrate the feasibility of explainable, laboratory-free dysglycemia screening for deployment in community settings and self-tracking health applications.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13177

MemRefine: LLM-Guided Compression for Long-Term Agent Memory

作者:

Minjae Kim↗Jinheon Baek↗Soyeong Jeong↗Sung Ju Hwang↗

Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on resource-constrained platforms with hard memory budgets, motivating us to formulate storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions. To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met. Across multiple memory frameworks and long-term conversation benchmarks, MemRefine consistently meets target budgets while preserving downstream performance and outperforming rule-based baselines under tight budgets.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12199

Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation

作者:

Zhen Ye↗Xu Tan↗Yiming Li↗Guangyan Zhang↗Chimin Chan↗Haohe Liu↗Zhengxi Liu↗Hongzhan Lin↗Zheqi Dai↗Xinshen Zhang↗Peiwen Sun↗Qiuqiang Kong↗…

Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to a temporal-granularity mismatch: speech tokens are temporally redundant and far longer than text under matched semantics, diluting per-token semantic density and weakening text-native reasoning dynamics. We study speech token design as a representation selection problem and sweep frame rates under a frozen LLM backbone with a fixed information rate. To make low frame rates feasible, we introduce factorized FSQ and a lightweight non-autoregressive audio LM head, scaling capacity to nearly 300\,bits/frame without sacrificing efficient prediction. With the bottleneck removed, we sweep frame rates (50$\rightarrow$2.08\,Hz) and alignment depth, and observe a consistent best regime for speech QA at 4.17\,Hz with intermediate-layer representation alignment.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18312

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

作者:

William Kalikman↗Ivo Petrov↗Dimitar I. Dimitrov↗Martin Vechev↗

arXiv:2606.18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient inversion attacks show that these updates can reveal enough information to reconstruct client inputs. Existing attacks on transformers either optimize dummy inputs to match the true client updates, which is costly and unstable for modern models, or exploit the low rank of attention gradients to identify a subspace containing the true layer embeddings, followed by a discrete membership test for candidate tokens. However, this token test is brittle under numerical noise, i.e., from quantization or Differential Privacy (DP), and scales poorly for encoder models with non-causal attention. We introduce TIGER, a continuous gradient inversion attack that turns this subspace signal into a differentiable objective. Instead of searching over tokens or matching full gradients, TIGER directly optimizes token embeddings to minimize their distance to the subspace. Our experiments demonstrate that on encoder-only models, TIGER substantially improves both reconstruction quality and runtime over existing attacks, while on decoder models, TIGER is more robust than prior subspace-based attacks, enabling the first successful reconstructions in DP-defended federated learning settings.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2511.16681

SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases

作者:

Dong Liu↗Yanxuan Yu↗

Vector databases (VecDBs) are increasingly deployed in retrieval-augmented generation (RAG) pipelines where query processing and document ingestion occur concurrently. The index layer needs to provide low-latency search while incorporating new vectors without frequent global rebuilding. Existing VecDB pipelines typically operate within a uniform representation regime, despite substantial variation in the semantic granularity required across queries. This motivates an index design that supports incremental updates while adapting retrieval depth to query distribution and complexity. We propose Semantic Pyramid Indexing (SPI), a VecDB-layer indexing framework that organizes embeddings into $L$ semantically aligned resolution levels and selects retrieval depth per query via a lightweight uncertainty-aware controller. SPI supports progressive coarse-to-fine ANN search, level-wise streaming insertion without global rebuilds, and distributed execution through LSH partitioning with asynchronous gRPC coordination. Unlike hierarchical ANN structures with fixed traversal rules (e.g., SPANN), SPI adapts resolution at query time while remaining compatible with FAISS and Qdrant backends. On MS MARCO and Natural Questions, SPI achieves competitive Recall@10 with lower latency under the same dense encoder family, yielding a 1.4–2.3$\times$ average retrieval latency reduction under fixed Recall@10 targets relative to comparable approximate-ANN baselines. A prototype scaling study up to 8 nodes shows $6.2\times$ throughput scaling (${\approx}73\%$ efficiency); the 16-node configuration is included for completeness but shows diminishing efficiency. We provide a top-$K$ stability guarantee: queries with sufficient retrieval margin return an identical top-$K$ set at a shallower level. Code and configurations are available at https://github.com/FastLM/SPI_VecDB.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16611

TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction

作者:

Bohao Liao↗Boyu Deng↗Qipeng Song↗Jieling Wang↗Jingchao Wang↗

arXiv:2606.16611v1 Announce Type: new Abstract: Trust prediction infers latent user-user trust relations and provides important support for social recommendation, fake-review and manipulation detection, and risk identification. Graph neural networks have become a prominent approach to trust prediction because of their ability to learn network structures and complex trust dependencies. However, existing methods often rely on a unified representation of trust signals and do not disentangle heterogeneous trust evidence into separate evidence channels, failing to exploit the distinct roles that different evidence channels should play during trust modeling. To address this gap, this paper argues that trust evidence should not be treated as an undifferentiated input, but should be decomposed and used as functional control factors over graph propagation. We propose TCHG, a tri-trust conditioned heterogeneous graph learning framework that decomposes trust evidence into three channels and assigns them distinct functional roles in propagation: entity reliability governs message admission, interaction-behavior reliability modulates propagation strength, and contextual trust adjusts the propagation mode through context-conditioned operator selection. Since the three evidence channels evolve at different temporal scales, TCHG maintains independent temporal states with non-uniform decay rates to prevent rapidly changing contextual signals from overwriting slowly accumulated entity reliability. It further predicts trust probability and calibrates the output probability, improving predictive confidence under sparse or conflicting evidence. Extensive experiments on multiple public trust datasets show that TCHG achieves effective and reliable trust prediction compared with representative trust prediction and heterogeneous graph baselines.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17961

Robustness of Similarity-based Positional Encoding Under Rotations: Theoretical Analysis and Experimental Validation

作者:

Andrea Santomauro↗Luigi Portinale↗Giorgio Leonardi↗

Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs. Among recent alternatives to standard absolute and sinusoidal encodings, similarity-based positional encoding (simPE) has emerged as a flexible framework for representing positional structure through pairwise relations. simPE was originally designed for medical imaging applications, where geometric robustness is especially relevant: small rotations naturally arise during image acquisition, induced by imaging instruments, patient positioning, or slight acquisition misalignments. Despite its empirical promise, the theoretical behavior of simPE under geometric perturbations has not been fully characterized. In this paper, we study the robustness of simPE with respect to rotations, combining formal theoretical analysis with experimental validation. We first show that simPE is generally not rotation-invariant. We then prove that, under mild Lipschitz assumptions on the elementary components, simPE is stable under rotational perturbations and derive explicit perturbation bounds in Frobenius norm. We validate these findings experimentally on four controlled datasets–a synthetic Arrow dataset, a synthetic Shapes dataset (four geometric shape categories), a synthetic Digits dataset, and a benchmark image classification dataset (FashionMNIST)–in which training and validation images are kept in a fixed canonical orientation while test images are subjected to increasing rotation angles. Across all datasets, simPE consistently outperforms standard learned positional encoding in terms of accuracy, F1 score, precision, and recall under rotation, particularly in the small-to-moderate angle regime, corroborating the theoretical stability guarantees.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20523

SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm

作者:

Sol\`ene Debuys\`ere↗Nicolas Trouv\'e↗Nathan Letheule↗Elise Colin↗Georgia Channing↗

arXiv:2606.20523v1 Announce Type: cross Abstract: Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR–optical datasets largely rely on low-resolution, intensity-only Ground Range Detected~(GRD) products and do not preserve complex-valued SAR measurements or native acquisition geometry, which restricts physically grounded multimodal learning. In particular, large-scale public datasets combining very-high-resolution (VHR) SAR SLC, aligned optical imagery, and natural-language descriptions are still lacking. We present a VHR SAR–optical–text dataset built from open-access Umbra spotlight acquisitions distributed as Sensor Independent Complex Data (SICD). From around 2,500 worldwide scenes (VV/HH, 20cm–2m native resolution), we standardize all SAR data to an 80cm slant-range grid via band-limited FFT resampling and tile the imagery into 1024 by 1024 patches. For each SAR patch, we retrieve a high-resolution optical tile and warp it into the SAR grid using local coordinate correspondences for local pixel-level alignment. We further generate three caption variants (SHORT/MID/LONG) per sample to support vision–language training and evaluation. Our dataset contains 119,566 triplets (complex and amplitude slant-range SAR patch, aligned optical patch, natural-language description) covering 257 locations across 72 countries and a broad range of land types and infrastructures. We release fixed train/validation/test splits and the full preprocessing and baseline code to enable reproducible benchmarks for multimodal alignment on cross-modal retrieval and conditional generation in native SAR geometry. The dataset is publicly available on the Hugging Face Hub at https://huggingface.co/datasets/ONERA/SARLO-80.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13189

SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection

作者:

Fuqiang Niu↗Bowen Zhang↗

Prompt-based LLMs are increasingly used for stance detection, but harder examples are not always repaired by clearer instructions, reasoning prompts, retrieval, or debate. We introduce SICI (Stance Inference Complexity Index), a seven-dimensional diagnostic measure of the semantic-pragmatic burden imposed by a target–text pair. Across SemEval-2016 and VAST, SICI predicts LLM accuracy better than surface proxies and shows substantial cross-scorer reliability ($\alpha=0.771$). More importantly, LLM errors change regime as SICI increases: low-complexity examples invite over-attribution, especially Against predictions; intermediate examples form an unstable boundary; and high-complexity examples rapidly concentrate on None. This phase-transition-like structure persists across GPT-3.5, GPT-4o-mini, DeepSeek-V3, and GPT-4o, although stronger models move the boundaries. A 15-method intervention study further shows that prompting, retrieval, and debate often shift models along the attribution–abstention axis rather than removing the high-complexity bottleneck.

阅读与讨论 → 访问原文 →