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。

01.
medRxiv (Medicine) 2026-06-15

Longitudinal monitoring exposes correlated temporal protein variations in the female plasma proteome

The plasma proteome is a valuable resource for assessment of the physiological state of the donor. Containing hundreds of different proteins of variable concentrations, it displays substantial inter-donor differences in individual protein levels, making each plasma proteome highly donor-specific. Less is known about intra-donor variability in the plasma proteome over time, although such variations may even be more indicative of a changing physiological state. Here we assessed data obtained from the TIMES cohort, comprising 51 apparently healthy participants monitored monthly over 12 months, focusing especially on temporal variations in blood protein levels. Most strikingly, we observed that several women in this cohort revealed strongly correlated temporal variations in their plasma proteome, including most notably PZP, SHBG, FETUB, AGT, SERPINA6, SERPINA7, CP, APOL1 and KNG1, with levels sometimes fluctuating by more than 20-fold. In contrast, such variations were absent in men. Some of the fluctuating proteins have been known to be hormone-regulated (e.g., PZP, SHBG), but for others this was not yet fully clear. Through the tight co-variation observed for these proteins in the plasma proteome of women, we can conclude that all these proteins are similarly hormone regulated. The findings reported here not only corroborate previous studies showing estrogen-dependent regulation of several plasma proteins, but also extend this category to include also CP, APOL1, and KNG1. As these latter have been often proposed as candidate biomarkers, they should be validated in sex-balanced cohorts and interpreted with caution, especially in large-scale plasma proteomics studies wherein often only one or a few sampling time points are measured per donor.

02.
arXiv (CS.CV) 2026-06-11

Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions

Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs. Their interaction, however, remains poorly understood, particularly when mixup is applied only during student training. In this setting, the teacher is queried on inputs drawn from a vicinal distribution it never saw during training, a controlled mismatch whose effect on knowledge transfer has not been characterised. We show that this mismatch causes the teacher's supervisory signal to be dominated by distributional confusion rather than inter-class structure. Despite it, the student does not merely imitate the teacher: it independently acquires greater linearity in the vicinal region, a structural property that the teacher lacks, and goes beyond dark-knowledge transfer. KD with mixup consistently improves student accuracy and reduces overconfidence by an order of magnitude relative to the baseline, across CIFAR and ImageNet with varying-capacity teachers. Crucially, calibration propagates from teacher to student independently of accuracy transfer, and temperature scaling governs a measurable accuracy-calibration trade-off that becomes more pronounced under vicinal training. These results reframe mixup distillation not as a degraded version of standard KD, but as a richer transfer channel that simultaneously shapes discriminative performance, uncertainty estimation, and representational geometry.

03.
arXiv (CS.CL) 2026-06-17

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

Retrieval-Augmented Generation (RAG) is the prevailing architecture for grounding language model outputs in external evidence, yet its dominant evaluation paradigms and default configurations remain oriented toward factual question-answering. For interpretive disciplines such as historical studies, RAG embeds assumptions that conflict with scholarly practice. We introduce HistoRAG, a framework that translates historiographical principles into concrete architectural interventions. Separated retrieval and generation decouples source discovery from interpretation, temporal windowing enforces balanced source representation across the research period as a methodological requirement of historical inquiry, and LLM-as-judge evaluation makes relevance judgments transparent and contestable. We evaluate these interventions using SPIEGELragged, applied to 102,189 articles from Der Spiegel (1950-1979). Each intervention addresses a measurable deficiency in standard RAG: era-specific vocabulary retrieves zero chunks from the 1950s when using 1970s terminology, evidence of the temporal skew that motivates windowing; vector similarity and LLM-assessed relevance correlate only weakly (Spearman rho = 0.275), motivating post-retrieval evaluation; and keyword-based and semantic retrieval surface largely disjoint source pools, motivating an architecture in which both operate as complementary retrieval layers under a shared LLM evaluation filter. We also introduce the concept of Zwischentexte (intermediate texts that function as interpretive proposals rather than findings) as a framework for responsible integration of LLM-generated text into scholarly practice. The architecture offers a model for how domain-specific epistemological commitments can be translated into RAG design decisions, and may transfer to other interpretive disciplines working with large corpora.

04.
arXiv (CS.LG) 2026-06-16

Dynestyx: A Probabilistic Programming Library for Dynamical Systems

arXiv:2606.16985v1 Announce Type: cross Abstract: State-space models (SSMs) are the standard formalism for Bayesian treatment of dynamical systems, with natural applications in statistics, signal processing, and machine learning. Despite their importance in both theory and application, dynamical systems have proven difficult to incorporate in modern probabilistic programming languages (PPLs), making state-of-the-art methods less accessible to practitioners and introducing friction in following the "Bayesian workflow." We introduce dynestyx, a probabilistic programming library with first-class support for SSMs, including state-of-the-art methods in the estimation of both states and parameters. Through a single, unified interface, users may specify arbitrary priors for discrete-time or continuous-time dynamical systems, perform inference over mixed-effect data, and make state and parameter estimates with principled uncertainty quantification.

05.
Nature (Science) 2026-06-09

A unicellular relative links aggregative multicellularity to animal origins

作者:

How animals evolved complex multicellularity from their unicellular ancestors remains unanswered. Unicellular relatives of animals exhibit simple multicellularity through clonal division, formation of multinucleate coenocytes, or aggregation. 1 Therefore, animal multicellularity may have evolved from one (or a combination) of these behaviours. Aggregation has classically been dismissed as a means to complex multicellularity. 2 However, aggregation occurs in many extant animal cells and has also been recently described in three close unicellular relatives of animals (the choanoflagellates Salpingoeca rosetta and Choanoeca flexa, and the filasterean Capsaspora owczarzaki). 3-5 It is unclear whether aggregation in these species is derived or ancestral, and its relevance for animal origins remains unknown. To fill this gap, we investigated whether an additional close unicellular relative of animals can undergo aggregation. We discovered that the marine free-living bacterivorous filasterean Ministeria vibrans 6 forms homogeneous aggregates with reproducible kinetics that have long-term stability, and that improved feeding and mating may be evolutionary drivers of this aggregation. Notably, we found that homologs of many animal multicellularity genes involved in cell adhesion, signalling, and transcriptional regulation were deployed during the aggregation process, indicating that they may have been used for aggregation in the unicellular ancestors of animals before being co-opted into animal multicellular development. Thus, our results imply that aggregative multicellularity was key to the development of the multicellular animal genetic toolkit.

06.
bioRxiv (Bioinfo) 2026-06-10

Pseudoperplexity Probes Memorization in Protein Language Models

Protein Language Models (pLMs) have significantly advanced computational biology. Yet their scale and reliance on redundant training data raise a fundamental question: do pLMs generalize the statistical grammar of proteins, or do they simply memorize their training data? To investigate this, we used pseudoperplexity as a probe for sequence-level memorization, comparing ProtT5's pseudoperplexity on a pre-training proxy dataset against a post-training holdout of genuinely novel sequences. To ensure a valid comparison, we matched the datasets by sequence length, cluster size, and taxonomic family. As a statistical baseline, we trained n-gram language models; analysis of higher-order n-gram composition and a statistically significant divergence in perplexity confirmed that the post-training sequences were genuinely novel at the local sequence level. ProtT5 showed a statistically significant difference in pseudoperplexity between seen and unseen sequences, though further analysis revealed this memorization signal to be modest. These findings suggest that ProtT5 exhibits detectable but limited memorization of its training data as measured by a pseudoperplexity-based probe.

07.
arXiv (CS.CL) 2026-06-12

Operadic consistency: a label-free signal for compositional reasoning failures in LLMs

Detecting LLM reasoning failures at inference time without ground-truth labels has motivated a wide range of confidence baselines, including self-consistency, semantic entropy, and P(True), built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces by composing a stated decomposition of the same query. We instantiate this idea as operadic consistency (OC), a per-question signal. Across twelve instruction-tuned LLMs (4B to 671B parameters, open-weights and closed-source) on four multi-hop QA datasets, OC is strongly correlated with accuracy on every dataset (Pearson $r \in [0.86, 0.94]$, all $p \leq 0.0004$), and is the only signal we evaluate with $r \geq 0.85$ uniformly across all four datasets. Chain-of-thought self-consistency (CoT-SC; Wang et al., 2023) matches OC on HotpotQA and DROP ($r = 0.93, 0.87$) but drops to $r \approx 0.45$ on MuSiQue and StrategyQA. At the per-question level, OC contributes information beyond CoT-SC and semantic entropy on every dataset (cluster-robust $p \leq 10^{-16}$ for the OC coefficient), and the conclusion is robust to additionally controlling for constructed decomposition-aware baselines ($p \leq 10^{-13}$). The same signal yields selective-prediction improvements (accuracy at fixed coverage) over a tuned CoT-SC baseline at the equal-cost $K = 3$ budget (AUARC lifts of +0.086 to +0.096 and AUROC lifts of +0.092 to +0.164; 95% CIs exclude zero on every cell). On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction point-estimate lift on all 16 (dataset, budget, metric) cells tested, with 95% CIs excluding zero on 12 of the 16.

08.
bioRxiv (Bioinfo) 2026-06-17

MetaHarmonizer: robust biomedical metadata harmonization and a contamination control for inflated LLM performance on public benchmarks

Public biomedical repositories hold substantial reuse potential, but inconsistent metadata routinely blocks integration across studies. Recent LLM-based harmonization approaches address scale but suffer from non-determinism, hallucinated ontology terms, and, in their highest-accuracy configurations, dependence on proprietary APIs or labeled fine-tuning data. A more fundamental concern is that LLM accuracies on widely-used public benchmarks may substantially inflate transferable capability: under a contamination-controlled evaluation protocol we developed, the apparent LLM-only advantage on the GDC schema-mapping benchmark is inverted, and three out of five LLMs recover 80 -100% of GDC identifiers from zero-schema context, suggesting direct memorization. Building on this insight, we present MetaHarmonizer, an automated metadata harmonization system designed to be robust by construction: SchemaMapper aligns attribute names across schemas, and OntologyMapper standardizes values to controlled vocabularies. Both modules implement a multi-stage cascade that escalates to more resource-intensive methods only when earlier stages fall short, with all candidates grounded in pre-defined controlled vocabularies to preclude hallucinated outputs and LLMs used only as bounded preprocessing components rather than inference-time dependencies. On the GDC schema-matching benchmark, SchemaMapper with the deployment-optimized LLM-generated alias dictionary achieved 71.6% Top-1 accuracy and the higher Recall@GT than Magneto bipartite variants, recovering significantly more ground-truth mappings; with the best performing alias dictionary, it reached the highest Top-1/Top-5/Recall@GT, and also matched the best Magneto reranker (fine-tuned LLM-reranker) on MRR; and it also outperforms LLM-only performance under contamination-controlled conditions. On four EFO benchmarks, OntologyMapper achieved 77.9 - 95.5% Top-1 accuracy, outperforming text2term by up to 16.4 pp and direct LLM inference (against the smaller corpus) by 19.2 pp because memorization is not a viable shortcut for this task. Across both modules, calibrated confidence scores separate correct from incorrect predictions (AUC 0.73 - 0.94), enabling principled human-in-the-loop triage. Inference is fully local, deterministic, and computationally efficient - seconds on schema mapping and under a minute for ontology mapping of up to ~7,000 terms against the pre-indexed 33,230-term corpus. Released as a Python package with a domain-agnostic architecture, MetaHarmonizer provides a scalable foundation for improving the FAIRness of biomedical data and enabling cross-study integration, alongside an evaluation methodology applicable to any LLM-augmented bioinformatics benchmark built on public benchmarks.

09.
arXiv (quant-ph) 2026-06-12

Influence-solvability: a systematic theory of $(1+1)D$ solvability and its application to brickwork circuits

arXiv:2606.12538v1 Announce Type: cross Abstract: `Solvable' circuits, such as dual unitaries and its generalisations, have arisen as paradigmatic examples of tractable chaotic non-equilibrium dynamics, both in classical and quantum systems. However, while increasingly more complicated sufficient conditions have been proposed, a systematic theory classifying and understanding general features of solvable circuits is missing. We develop such a theory by introducing influence-solvable circuits, a class of $(1+1)D$ circuits whose influence matrix, which represents the `bath' generated by its own evolution, is given by a uniform MPS with finite bond-dimension $\chi$. This property allows for efficient computation of subsystem dynamics and essentially contains all known examples of solvable circuits. We derive a set of necessary and sufficient local conditions by using a version of the fundamental theorem of MPS for open boundary conditions. Next we apply our theory to brickwork circuits with $\chi=1$ influence-solvability and perform a systematic classification of classical brickwork circuits with local dimension up to $d=3$ and quantum brickwork circuits with $d=2$. Our search reveals new solvable circuits that are not captured by known solvability conditions.

10.
arXiv (CS.AI) 2026-06-12

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

arXiv:2606.12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.

11.
arXiv (quant-ph) 2026-06-19

Charge-Conjugation Violation and Population Asymmetry in Bipartite Fermionic Lattices

arXiv:2606.06138v2 Announce Type: replace-cross Abstract: Charge conjugation violation (CCV) is a central concept in particle physics and appears also for quasiparticles in quantum many-body systems, which typically relies on an embedded external symmetry breaking to the underlying system. An open question is how an intrinsic CCV mechanism could emerge and what its macroscopic consequences would be. We establish sublattice kinks in bipartite fermionic lattices as a concrete setup showing intrinsic CCV. The intrinsic CCV of the sublattice kink is based on the graph-topological nature of the underlying Hamiltonian, with no explicit symmetry breaking taking place. It leads to a population asymmetry of different configurations and imprints a hidden leaf-like structure in the eigenenergy spectrum. The population asymmetry also leads to an imbalanced sublattice-kink production triggered by the vacuum-instability in the quench dynamics. Our work demonstrates the graph topology as the microscopic origin of intrinsic CCV, with the population asymmetry as the macroscopic consequence, of which the proposed setup is highly amenable to experimental implementation via cold-atom quantum simulators.

12.
arXiv (CS.AI) 2026-06-19

SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs

arXiv:2606.20244v1 Announce Type: cross Abstract: Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidence-grounded confidence or shortcut collapse. To resolve this ambiguity, we introduce low-entropy anchors and an entropy-shaping objective that reduces answer uncertainty while preserving baseline high-confidence tokens. We instantiate this principle in SPOT-E, a plug-and-play test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning based on Group Relative Policy Optimization (GRPO). Across all benchmarks and different VLM families, SPOT-E yields consistent gains and improved robustness under visual corruptions. Code is publicly available at: \url{https://github.com/YinBo0927/SPOT-E}

13.
arXiv (CS.AI) 2026-06-11

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning

arXiv:2606.11092v2 Announce Type: replace-cross Abstract: Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball positions and strike timings; in contrast, task reward-driven RL struggles to explore and discover valid kicks from scratch. We therefore introduce RoboNaldo, a three-stage motion-guided curriculum RL framework for high-impulse humanoid interaction. A single human-kick reference is used as a scaffold and progressively shifts optimization towards shooting performance. The curriculum first learns a stable whole-body kicking prior, then adapts the kick to free-kick settings where the ball is stationary at random positions, and finally extends it to moving-ball shooting through a locomotion-command and kick-trigger interface. A high-level heuristic planner controls this interface during training, while alternative high-level controllers can drive the same low-level policy at inference. In simulation, RoboNaldo demonstrates free-kick shot error 48.6% lower and shoot velocity 2.96x than prior work baselines. In real world on a Unitree G1 with onboard perception, RoboNaldo attains 0.73 m and 0.86 m average target shooting error from 3 m away in free-kick and moving-ball cases, accordingly. And the post-contact ball velocity reaches 13.10 m/s, which is 59-71% of reported professional open-play shot speed. Project page: https://opendrivelab.com/RoboNaldo.

14.
medRxiv (Medicine) 2026-06-19

Reassessing Instrument Strength in Two-Sample Mendelian Randomization Analysis

Mendelian randomization (MR) analysis is widely used to estimate causal relationships between risk factors and outcomes of interest. Two-sample MR approaches have gained increasing attention in genetic epidemiology due to the growing availability of Genome-Wide Association Study (GWAS) summary statistics from public databases. A critical step in two-sample MR is the selection of genetic variants as instrumental variables (IVs). Although genome-wide significant variants are typically preferred, the inclusion of variants with weaker association p-values is considered, as they may potentially improve power through an increased instrument number of instruments, while they may introduce weak instrument bias and attenuate effect estimates towards the null. Our simulation results show that even modest levels of pleiotropy substantially increase the variability of causal effect estimates, while the inclusion of weak IVs does not substantially affect the direction and variability of causal effect estimates in most cases. In real data analyses, we used two released versions of FinnGen GWAS summary statistics with different sample sizes as exposure GWASs to assess the influence of weak IVs. Here, the inclusion of IVs with higher exposure-association p-values resulted in weakened estimated effect sizes, particularly when the exposure GWAS sample size was small. These findings suggest that incorporating weak IVs is reasonable when the exposure GWAS sample size is large, but it poses a risk of falsely concluding null associations when the exposure GWAS sample size is small.

15.
arXiv (CS.CV) 2026-06-18

URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification

作者:

Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators. We present KinemaForge, a constraint-driven pipeline that jointly infers part-level shape, joint topology, and joint parameters from short RGB-D sequences and validates the result against an energy-consistent verifier built on differentiable rigid-body dynamics. The pipeline introduces three components: a kinematic constraint graph that encodes joint-part incidences as soft edges; a differentiable screw-axis solver that backpropagates from rendered observations through Featherstone's articulated-body algorithm to joint parameters; and an energy residual loss that penalises non-physical free responses of the reconstructed model. Across five PartNet-Mobility categories and an internal RGB-D benchmark, KinemaForge reduces the average joint-axis error from 4.52 degrees to 2.83 degrees (-37.4%) over the strongest geometric baseline (PARIS) and from 5.30 degrees to 2.83 degrees (-46.6%) over the interaction-based Ditto baseline, lowers long-horizon simulation drift by 64% (vs. PARIS) over 50 s rollouts, and yields URDFs whose closed-loop manipulation success rate improves by 14.6 percentage points over Ditto in our preliminary evaluation. Code and reconstruction data will be released upon acceptance.

16.
medRxiv (Medicine) 2026-06-16

Development and reliability and validity test of the Questionnaire on Knowledge, Attitude and Practice of ICU Nurses on Blood Oxygen Saturation Management in Mechanically Ventilated Patients

Objective: A questionnaire on the knowledge, attitude and practice of ICU nurses regarding the management of blood oxygen saturation in patients with mechanical ventilation was compiled, and its reliability and validity were tested. Method: Drawing upon the knowledge-attitude-practice theory, the initial questionnaire draft was developed through literature review and consultation with Delphi experts. Employing convenience sampling, 32 nurses from the General ICU of Wuxi Second People's Hospital were surveyed between 1 August 2025 and 27 September 2025, enabling item screening and assessment of reliability and validity.The full version of the developed questionnaire is provided as Supporting Information (S1 File). All items are published under a CC BY 4.0 license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Result: A questionnaire on the knowledge, attitude and practice of ICU nurses regarding the management of blood oxygen saturation in mechanically ventilated patients was finalised, comprising 26 items: 11 in the knowledge dimension, 6 in the attitude dimension and 9 in the behaviour dimension. The overall Cronbach's coefficient for the questionnaire was 0.88, with dimension-specific coefficients of 0.787, 0.722, and 0.781 respectively. The Spearman-Brown coefficient for the entire questionnaire was 0.967, while dimension-specific coefficients were 0.796, 0.666, and 0.728 respectively. The content validity index at the questionnaire level (S-CVI) was 0.886, and the item-level content validity index (I-CVI) ranged from 0.913 to 0.967. 0.728. The questionnaire's level content validity index (S-CVI) was 0.886, and the item level content validity index (I-CVI) ranged from 0.913 to 1.00. Conclusion: The questionnaire on knowledge, attitude and practice of blood oxygen saturation management in mechanically ventilated patients demonstrates good reliability and validity. It may serve as an assessment tool for intensive care unit nurses regarding their knowledge, attitude, and practices concerning blood oxygen saturation management in mechanically ventilated patients, thereby establishing a foundation for developing targeted intervention strategies in future practice.

17.
arXiv (math.PR) 2026-06-16

Probabilities

arXiv:2601.18853v4 Announce Type: replace-cross Abstract: Probabilities is the English translation of the book Probabilités Tome 1 and Tome 2. The mathematic content is authored by Prof. Jean-Yves Ouvrard. The English version has been done by his eldest son Dr. Xavier Ouvrard. This probability theory book covers not only an introduction to this field, but also advanced concepts based on measure theory. The first part introduces the fundamentals of probability theory across 7 chapters, targeting bachelor level, including event algebras, random variables, independence, conditional probabilities, moments of discrete and continuous random variables, generating functions, and limit theorems. The second part contains 10 chapters and corresponds to master level. Following a brief introduction to measure theory, this part develops more advanced topics: probability measures and their complements, distributions and moments of random variables, modes of convergence, laws of large numbers, conditional expectation, Fourier transforms and characteristic functions, Gaussian random variables, convergence of measures, convergence in distribution, discrete-time stochastic processes, martingales, and Markov chains. The reader's work is greatly facilitated by the inclusion, in every chapter, of numerous exercises, all accompanied by detailed solutions that often provide substantial extensions to the theoretical material.

18.
arXiv (CS.CL) 2026-06-18

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Item discrimination is a fundamental psychometric property of educational assessment, which measures whether an item meaningfully distinguishes students with higher proficiency from students with lower proficiency. While various existing works have explored whether large language models (LLMs) can estimate item difficulty, it remains unclear whether they can capture item discrimination. In this work, we evaluate 42 proprietary and open-weight LLMs in zero-shot settings using two complementary approaches: direct discrimination prediction, where models explicitly estimate an item's discrimination value from its content, and response-based Classical Test Theory (CTT) calibration, where LLM answers are treated as synthetic student responses to compute discrimination scores. Our results show that direct prediction yields weak alignment with human-calibrated discrimination: the best-performing model reaches only a Spearman correlation of 0.152. Response-based CTT calibration provides a stronger but still limited signal, with the all-persona synthetic respondent pool reaching a Spearman correlation of 0.241. These findings highlight item discrimination as an open challenge for LLM-based psychometric evaluation: current LLMs contain non-random discrimination-relevant signal, but they do not yet reliably capture how assessment items distinguish human students.

19.
arXiv (CS.CL) 2026-06-19

Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer

We study cross-lingual transfer by fine-tuning seven large language models (4B–671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding – the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.

20.
arXiv (CS.AI) 2026-06-17

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

arXiv:2606.17165v1 Announce Type: cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost. We study when a treatment effect estimated on LLM outcomes recovers the effect that would have been measured on the human population of interest. Distributional equivalence between LLM and human outcomes would make any standard estimator valid but is unrealistic. We therefore develop a statistical framework that adapts surrogate endpoint theory to LLMs. The framework shows that calibrating LLM outcomes to human outcomes identifies the average treatment effect under surrogacy and comparability conditions that are jointly weaker than distributional equivalence. When these conditions fail, the effect of interest is only partially identified, and we provide diagnostics that can falsify surrogacy on historical experiments together with a bound on the worst-case bias from limited overlap. We further show that the stochasticity inherent to LLMs introduces both bias and variance, but using an average of multiple draws as the surrogate mitigates both. We illustrate the methods and theory in simulations and an application to A/B tests on Upworthy headlines. A central takeaway from our work is that the validity of LLM outcomes as surrogates can only be falsified for past treatments and never verified for new ones, so human experiments remain indispensable for novel interventions. We discuss the role of LLM choice, prompting, and temperature as design variables, and how to size human experiments for validation.

21.
arXiv (CS.AI) 2026-06-16

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

arXiv:2606.17006v1 Announce Type: cross Abstract: We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated on our held-out test split, supporting data filtering via a simple score threshold. TuneJury generalizes to both held-out test pairs and out-of-distribution benchmarks, remaining competitive with prior baselines on the latter. For generators released after training, we introduce anchor calibration, a post-hoc, per-system Bradley-Terry calibration that recovers agreement at substantially better data efficiency than from-scratch retraining. The same frozen reward drives consistent reward-axis gains across three downstream applications: inference-time best-of-N selection, DITTO-style latent optimization, and expert-iteration post-training. TuneJury is available at https://github.com/yonghyunk1m/TuneJury.

22.
arXiv (CS.AI) 2026-06-17

Beyond the Sampled Token: Preserving Candidate Support in RLVR

arXiv:2510.14807v3 Announce Type: replace Abstract: We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the candidate distribution for next-token prediction. We formally show that as probability concentrates on the top-$1$ candidate, the expected number of distinct responses collapses to one regardless of the sampling budget $K$. This theoretical implication is further verified by our empirical tracking of top-$N$ candidate probabilities during training, where the top-$1$ candidate progressively dominates while plausible alternatives are suppressed. These findings suggest a key desideratum for effective exploration: preserving non-negligible probability mass on the top-$N$ candidates. To this end, we propose Candidate-aware Support Preservation (CaSP), with two complementary designs. Specifically, CaSP redistributes positive gradients among top-$N$ candidates for correct responses, and applies a stronger penalty to the top-$1$ candidate for incorrect responses. Unlike many exploration-oriented methods that improve pass@$K$ at the cost of pass@1, CaSP improves pass@$K$ across the full $K$ spectrum. These gains generalize to 6 math, 2 logical-reasoning, and 2 coding benchmarks, and scales to 32B-parameter models and sampling budgets up to $K=1024$, positioning it as a principled, candidate-level approach for RLVR exploration.

23.
arXiv (CS.CV) 2026-06-11

Lighting-aware Unified Model for Instance Segmentation

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing Lighting Convolutional-Attention (\lca{)}, an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. \lca{} employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize \lca{} through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

24.
arXiv (CS.LG) 2026-06-19

Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting

arXiv:2606.19560v1 Announce Type: new Abstract: Seasonal influenza infects millions of people and causes substantial morbidity and mortality in the United States each year, making accurate short-term forecasting a core public-health need. Reliable forecasts of epidemic time series can inform vaccination timing, hospital staffing, and resource allocation, yet the comparative behavior of modern forecasting architectures on infectious-disease surveillance data remains insufficiently characterized. We address this gap through a systematic evaluation of regional influenza forecasting using influenza-like illness surveillance and influenza-associated hospitalization time series under both temporal and spatial generalization settings for 1-4-week-ahead prediction. We compare classical neural network architectures, numerical transformer-based models, pretrained time series foundation models, and LLM-based forecasting approaches. Across tasks, we demonstrate that a mixture-of-experts model that fuses multiple pretrained forecasters achieves the strongest overall performance, indicating that heterogeneous pretrained representations provide complementary predictive information. Our results further show that numerical transformer-based models produce reliable forecasts, while pretraining provides the largest gains at longer horizons, particularly when the pretraining domain is mechanistically aligned with influenza dynamics. In contrast, LLM-based time series methods underperform relative to numerical forecasters in this setting. Finally, we examine hospitalization information as both an auxiliary covariate and a pretraining source. Hospitalization signals provide complementary improvements in selected settings and clarify when additional surveillance streams enhance the robustness of multi-horizon forecasting. These findings provide actionable guidance on model selection, pretraining strategy, and auxiliary-signal use for influenza preparedness.

25.
arXiv (CS.AI) 2026-06-16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

arXiv:2606.16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.