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.
arXiv (CS.LG) 2026-06-17

Reward hacking in physical reinforcement learning revealed by turbulent drag reduction

arXiv:2606.06227v2 Announce Type: replace-cross Abstract: A reinforcement-learning agent maximises its reward, which can diverge from the outcome its designer intended. In physical control the reward rarely closes that gap, and drag reduction in wall turbulence makes it concrete. A mass-conservation projection couples agents' outputs and erases the per-agent credit the policy gradient needs; a memoryless policy cannot resolve the slow near-wall cycle it acts on; and a pressure-gradient reward pays for nominal drag reduction by pumping power through the wall. Two degenerate controllers achieve large drag reductions while total dissipation rises, so the reported figure can mask a more wasteful flow. We trace each fault to its cause and fix it: a differentiable projection that restores credit, a recurrent policy with a widened sensing stencil, and a reward scored on the true wall power. The corrected controller acts on the flow within a closed energy budget, earning a conservative $17\%$ under honest accounting.

02.
arXiv (CS.CV) 2026-06-24

FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation

Music-to-dance generation aims to translate auditory signals into expressive human motion, with broad applications in virtual reality, choreography, and digital entertainment. Despite promising progress, the limited generation efficiency of existing methods leaves insufficient computational headroom for high-fidelity 3D rendering, thereby constraining the expressiveness of 3D characters during real-world applications. Thus, we propose FlowerDance, which not only generates refined motion with physical plausibility and artistic expressiveness, but also achieves significant generation efficiency on inference speed and memory utilization. Specifically, FlowerDance combines MeanFlow with Physical Consistency Constraints, which enables high-quality motion generation with only a few sampling steps. Moreover, FlowerDance leverages a simple but efficient model architecture with BiMamba-based backbone and Channel-Level Cross-Modal Fusion, which generates dance with efficient non-autoregressive manner. Meanwhile, FlowerDance supports motion editing, enabling users to interactively refine dance sequences. Extensive experiments on AIST++ and FineDance show that FlowerDance achieves state-of-the-art results in both motion quality and generation efficiency. Code will be released upon acceptance.

03.
arXiv (CS.AI) 2026-06-16

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

arXiv:2606.15197v1 Announce Type: cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve modeling policies through large-scale annotated or curated training data, but are costly to adapt to new problem distributions. Meanwhile, one-shot generation remains brittle in hierarchical modeling, where early symbolic errors can propagate into invalid formulations. Test-time scaling offers a promising alternative by enabling structural exploration with additional instance-level computation; however, existing search-based methods typically rely on a fixed policy, causing repeated rollouts to inherit similar modeling biases and providing limited credit assignment for intermediate decisions. To address these limitations, we propose StarOR, a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling. StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node. By using MCTS-generated siblings as local comparison sets, StarOR transforms search-time exploration into instance-specific policy refinement. Moreover, an unsupervised multi-faceted reward system provides fine-grained feedback for intermediate formulation decisions without ground-truth labels. Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone, outperforming existing methods and the frontier LLMs.

04.
arXiv (CS.CV) 2026-06-19

Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications

AI vision models are a driving factor for the potential use case scenarios of cognitive robotics within in the industry and household applications. A large array of methods from semantic environment analysis towards 6D and grasping pose estimation have been proposed based on the latest AI achievements. However, such advancements require further strong and efficient methods w.r.t. training data and AI-architectures, which are capable in synergy to tackle current challenges, precision limits, and scalability beyond domain gaps. In this paper, we discuss these current limits and trends in the related state-of-the-art which are challenging those. Further we discuss our current work in progress on bridging the domain gap between simulations and real world applications by linking those in the training data generation.

05.
arXiv (CS.CL) 2026-06-16

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality into reward signals, but its efficiency depends on whether those criteria reliably capture the task scope and evidence needs. Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency. To obtain more reliable query–rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process: instead of inferring evaluation criteria for a given query, it first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query–rubric pairs from those evaluation targets. Starting from a sampled seed topic, DeepRubric builds an evidence tree by recursively expanding evidence-backed sub-questions, whose leaves serve as atomic and verifiable evaluation targets. It then uses the evidence tree to synthesize the training query and rubrics, ensuring that the reward evaluates exactly the information requested by the query. Using DeepRubric, we construct 9K query–rubric supervision examples and train DeepRubric-8B with rubric-based GRPO, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks with roughly 13x fewer RL GPU-hours.

06.
medRxiv (Medicine) 2026-06-16

Presurgical immune biomarkers associated with pain intensity and pain interference recovery after total knee arthroplasty: findings from the PRIME-KNEE study

Chronic postsurgical pain (CPSP) prevalence after total knee arthroplasty (TKA) is >20%. Circulating immune biomarkers are known factors of musculoskeletal pain but poorly understood as CPSP predictors. This prospective, longitudinal study of 203 patients s/p TKA tested presurgical plasma biomarkers associated with 6-month CPSP, using promising approaches from geriatrics biomarker research: expected recovery differential (ERD; resilience outcome) and penalized, machine-learning regularization modeling (elastic net and LASSO regression). Forty-nine presurgical candidate biomarkers were considered. CPSP was operationalized using ERDs built around PROMIS pain intensity and pain interference, which quantified the difference between observed and expected recovery after accounting for demographic, comorbidity, reserve, and perioperative factors. Plasma/ERDs from ~130 patients revealed 13 biomarkers with the highest selection stability criteria, and either positive or negative (+/-) associations with ERDs. Interleukin (IL) 5 (-) and Lipopolysaccharide-Binding Protein (LBP; +) were associated with both ERDs. Unique associations with pain intensity ERD included Cytomegalovirus-Specific IgG Negative (CMV IGg-; -), Macrophage Inflammatory Protein-1 Beta (MIP1b; -), IL12p70 (-, Cluster of Differentiation 30 (sCD30;-), Interferon alpha 2a (IFN2a;+), and Leukemia Inhibitory Factor (LIF;+). Unique associations with pain interference ERD included Lipopolysaccharide (LPS;-), Activin A (-), IL8 (-), Serum Amyloid A (SAA;-), and IL7 (+). Protein-protein interaction analyses and topology motifs suggest a centralized network with higher-than-expected connectivity, involving IL5, IL7, IL8, MIP1{beta}, and IFN2a, among others. This study proposes rigorous yet feasible approaches to expedite pain biomarker research, and introduces presurgical biomarkers t0 consider in future TKA-CPSP biosignature derivation.

07.
bioRxiv (Bioinfo) 2026-06-18

A data-driven rediscovery of the specificity-conferring code of adenylation domains in nonribosomal peptide synthetases

Nonribosomal peptide synthetases (NRPSs) are large modular enzymes that assemble structurally diverse peptides, many of pharmacological importance, including antibiotics and immunosuppressants. Within each NRPS module, the adenylation (A) domain selects the substrate to be incorporated, a choice governed by a small set of residues lining the binding pocket. For two decades, computational prediction of A-domain substrate specificity has relied on residue sets - most prominently the Stachelhaus code and the 34-residue "8 Angstrom code" - that were defined by spatial proximity to the substrate rather than by demonstrated predictive value. Here we revisit which residues govern substrate specificity from a purely data-driven perspective. We assembled a non-redundant dataset of 5,366 A-domain sequences (4,693 bacterial and 673 fungal) and used information-theoretic measures to rank alignment positions by their statistical association with substrate identity, without restricting candidate positions to any predefined structural shell. This procedure yielded two compact, kingdom-specific codes: IG15B (15 positions) for bacterial and IG13F (13 positions) for fungal A-domains. Both match or exceed the predictive accuracy of the 34-residue 8 Angstrom code while using fewer than half its positions, and both independently recover the majority of the classical Stachelhaus positions. Notably, our analysis identifies four positions (242, 280, 281, and 284) that lie outside all conventional codes yet carry non-redundant specificity information and co-localize with classical determinants on two helices flanking the binding pocket. These positions provide new candidate sites for the rational engineering of A-domain specificity.

08.
PLOS Medicine 2026-05-22

Differences in tuberculosis prevalence by sex in low- and middle-income countries over 1993–2025: A systematic review and meta-analysis

by Nicole A. Swartwood, Nanki Singh, Seyed Alireza Mortazavi, Melike Hazal Can, Hening Cui, Do Kyung Ryuk, Peter MacPherson, Katherine C. Horton, Nicolas A. Menzies Background Global and national initiatives to combat tuberculosis (TB) have expanded over recent years. Despite this, the TB burden remains high in some population groups, with men recognized as having elevated TB risks. Summary measures of sex differences in TB prevalence were last estimated in 2016. Since then, many additional prevalence surveys have been conducted, including in the highest TB burden countries. We conducted a systematic review of sex-stratified TB prevalence survey data published over 1993–2025, to provide updated estimates of male-to-female (M:F) TB prevalence ratios and determine whether sex-related disparities in TB burden have closed over time. Methods and findings We identified surveys reporting community-representative, sex-stratified estimates of pulmonary TB prevalence in low- and middle-income countries (LMICs), including surveys from an earlier review (covering January 1993–March 2016) and a new systematic review (covering 1st December 2015–13th October 2025). This review was prospectively registered with PROSPERO (CRD42024503853) and included searches of PubMed, Embase, Global Health, the Cochrane Library, Africa Index Medicus, LILACS, and SciELO. We extracted data on bacteriologically confirmed and smear-positive TB prevalence among adults (aged ≥ 15 years), stratified by sex. Risk of bias was evaluated using eight criteria specific to prevalence surveys. We fit multi-level Bayesian regression models with study- and country-level random effects to estimate the M:F ratio of TB prevalence (male prevalence divided by female prevalence), overall and for key subgroups. In meta-regression analyses, we estimated how prevalence ratios varied over time and according to known TB risk factors and TB case definitions.We identified 10,124 publications and extracted data from 100 eligible studies representing 102 unique prevalence surveys and 4,658,310 participants (45.6% male) in 33 LMICs. TB prevalence was higher in men than women in 90/102 of the included surveys, with a pooled M:F prevalence ratio of 2.02 (95% credible interval (CrI): 1.71, 2.34) for bacteriologically confirmed TB and 2.38 (95% CrI: 1.91, 2.90) for smear-positive TB. Time trend analyses showed a 2.0% (95% CrI: −0.2, 4.5%) average annual change in the M:F ratio of bacteriologically confirmed TB over the study period. The M:F prevalence ratio was estimated to be higher for countries with greater excess HIV prevalence among men, and countries with greater gender equity (as measured by the United Nation’s Gender Development Index). The estimated M:F prevalence ratio was also higher for surveys that did not restrict testing to individuals reporting TB symptoms. Study limitations include heterogeneity in survey methods and definitions, as well as limited data from the Americas, Eastern Mediterranean, and Europe WHO world regions and post-COVID-19 period. Conclusions Men in LMICs consistently experience TB at a higher prevalence than women. Time trend estimates are uncertain, but consistent with widening sex differences in TB prevalence over the last three decades, despite efforts to address the risk factors underlying this excess TB burden.

09.
arXiv (math.PR) 2026-06-12

Voronoi Percolation: Topological Stability and Giant Cycles

arXiv:2601.00793v2 Announce Type: replace Abstract: We study the topological stability of Voronoi percolation in higher dimensions. We show that slightly increasing p allows a discretization that preserves increasing topological properties with high probability. This strengthens a theorem of Bollobás and Riordan and generalizes it to higher dimensions. As a consequence, we prove a sharp phase transition for the emergence of i-dimensional giant cycles in Voronoi percolation on the 2i-dimensional torus.

10.
medRxiv (Medicine) 2026-06-23

A pharmacometric grey zone reconciles high metronidazole resistance rates with bismuth quadruple therapy efficacy in Helicobacter pylori

Summary Background Metronidazole (MET) resistance in Helicobacter pylori (H. pylori) exceeds 50-60% globally, yet MET-containing bismuth quadruple therapy (BQT) achieves &gt90% eradication in MET-resistant infections. We hypothesise this discordance stems from a structural limitation of two-fold dilution: a pharmacometric grey zone between the 128 and 256 &microg/mL breakpoints where treatable isolates are systematically misclassified as high-level resistance. Methods In a real-world cohort of 4610 treatment-na&iumlve children (2019-2024), checkerboard assays determined the bismuth-MET synergy factor (SF). Population PK/PD modelling simulated gastric MET exposure (AUC

11.
arXiv (CS.LG) 2026-06-11

Bergson: An Open Source Library for Data Attribution

arXiv:2606.11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation. However, significant engineering effort is required to perform it at scale, and many cutting edge techniques lack open-source tooling and support. Bergson is an open source library that aims to enable faster progress in the field by providing a host of techniques that scale to very large language models and pre-training datasets. The library natively supports on-disk gradient stores and multi-node distributed training, and provides quality of life tools for researchers. Finally, we introduce the first open-source implementations of three leading data attribution methods: MAGIC, SOURCE, and TrackStar. The library is available at https://github.com/EleutherAI/bergson .

12.
arXiv (CS.CL) 2026-06-11

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only $19.1\%$ Pass@1, whereas the full adapter reaches $73.4\%$ with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw $\times$ nine-model sweep and a five-claw $\times$ two-model sweep, model choice changes Pass@1 by $29.4$ pp and harness choice by $27.4$ pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

13.
arXiv (CS.CL) 2026-06-24

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations

Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows. However, it is difficult to disentangle which behaviors are explained by narcissism versus experimental confounds. Specifically, LLM evaluators may deliver self-preferring verdicts when comparing responses to questions they fail on; these verdicts may not depend on the identity of the author, but on evaluator quality. We correct this by directly comparing the judge's voting distribution in cases where it evaluates itself versus another model. This evaluator quality baseline reveals that only 51% of examples in previous findings retain statistical significance against this null hypothesis, covering 89.6% of total self-preference probability mass. Finally, we compare the entropy of voting distributions, suggesting uncertainty-driven overlap, and show that our procedure enables more careful documentation against the backdrop of judge-bias research.

14.
arXiv (CS.CV) 2026-06-11

From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning

Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects. Despite recent progress, large vision–language models (VLMs) remain brittle at such tasks, especially for interventional and counterfactual queries over multi-image inputs. Most existing explorations inject causal knowledge via textual prompts, leaving causal mechanisms external to model execution and limiting reliable control during inference. To address this problem, we propose BridgeVLM, which internalizes visual causal reasoning by inducing a causal graph from multi-image inputs and converting it into structured Causal Tokens executed by RAMP layers injected into the LLM decoder for causal message passing. We further introduce a unified training interface M3S for fine-grained causal supervision from different granularities (local/global level). BridgeVLM achieves 54.4% accuracy on intervention tasks on CausalVLBench (vs. 33.2% with prompt-level supervision), improves results on Causal3D from 43.6% to 49.0%, and substantially improves causal structure learning on CausalVLBench ($F_1$: 33.4% $\rightarrow$ 75.1%).

15.
medRxiv (Medicine) 2026-06-10

Healthy Heart Actions Right Time (HHART): Co-design priorities to connect Aboriginal and Torres Strait Islander community and clinic activities for healthy hearts

Aim: Healthy Heart Actions Right Time (HHART) is a multi-phased research project that seeks to identify, implement and evaluate strategies to connect community and clinical activities to reduce the burden of heart disease for Aboriginal and Torres Strait Islander people. The aim in Phase One was to identify priority activities for two participating services. Background: The ongoing effects of colonisation drive a disproportionate burden of heart disease for Aboriginal and Torres Strait Islander people. Clinical and community groups both have established strengths in reducing the risk of heart disease, but these are not always well connected. Methods: Using a case study methodology in two locations we partnered in a 12-month co-design process to identify priority activities to connect clinical and community activities. Findings: Three priorities emerged from the Phase One co-design process: (i) community-led gardening as a strategy to promote heart health through connection and healthy lifestyles; (ii) community days to increase engagement in heart checks and strengthen community-clinic relationship; and (iii) clinic-led development of culturally relevant education resources to promote clinician confidence and community heart health knowledge.

16.
Nature (Science) 2026-06-17

Navigating a crowded developing brain leaves neurons with broken DNA

As neurons migrate to their final destinations in the forming brain, their DNA gets damaged. The brain has evolved a fix, but there can be lasting consequences if repair fails. As neurons migrate to their final destinations in the forming brain, their DNA gets damaged. The brain has evolved a fix, but there can be lasting consequences if repair fails.

17.
arXiv (CS.LG) 2026-06-18

Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization

arXiv:2606.18961v1 Announce Type: new Abstract: Protein language models (PLMs) have emerged as powerful tools for controllable biomolecular design, yet their post-training adaptation typically relies on costly wet-lab validation or curated preference datasets. To overcome this supervision bottleneck, we introduce unsupervised reward optimization of PLMs, a comprehensive framework for steerable protein generation without ground-truth labels. Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with extrinsic semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes. Building upon this discovery, we propose two offline algorithms: Soft Reward Optimization (SRO) and Binarized Reward Optimization (BRO), which effectively maximize the classical RLHF objective induced by these proxy rewards. Extensive experiments on compositional out-of-distribution prompts demonstrate that both methods significantly outperform competitive baselines (DPO, KTO), while approaching oracle performance across multiple sampling temperatures, model scales and protein families. Moreover, PLMs fine-tuned with unsupervised rewards can achieve consistently higher coverage compared to their base model in pass@k evaluations. By enabling self-improvement of PLMs through their own generated experience, our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.

18.
arXiv (quant-ph) 2026-06-19

A Quantum Encoding of Traveling Salesperson Tours via Route Generation, Cost Phases, and a Reversible Valid-Permutation Oracle

arXiv:2603.21283v3 Announce Type: replace Abstract: For a traveling salesperson problem (TSP) of n cities, we present a compact quantum encoding based on a time-register representation of tours. A candidate route is represented as a sequence of n-1 city labels over discrete time steps, with one fixed start city and the remaining cities encoded in binary registers. We describe three ingredients of the construction: uniform route generation over the route register, a reversible validity oracle, and a phase oracle that encodes the total tour cost. The validity oracle checks both that the non-start city labels form a permutation and, for incomplete graphs, that every directed edge used by the route exists. The cost oracle then accumulates the start-edge, intermediate-transition, and return-edge costs into a tour-dependent phase for valid routes. This yields a coherent superposition of candidate routes with feasibility and tour-length information embedded directly in the quantum state. The complete construction uses O(n log n) qubits, while a naive implementation has worst-case elementary-gate complexity O(n^3 log n). The encoding is compatible with amplitude amplification or spectral filtering techniques such as the quantum singular value transform (QSVT) or Grover's algorithm. However, due to the exponentially small fraction of valid tours, the overall complexity remains exponential even when combined with amplitude amplification.

19.
medRxiv (Medicine) 2026-06-16

MRMU: A New Paradigm for Mendelian Randomization by Accounting for Measured Covariates and Unmeasured Confounders

Mendelian randomization (MR) is a powerful approach for causal inference, however, its reliability is frequently compromised by unadjusted covariates and unmeasured confounders, such as unmeasured pleiotropy and sample structure. To address these challenges, we introduce MRMU, a novel paradigm for the MR framework. Unlike traditional single-variable or multivariable MR methods, MRMU selects instrumental variables only from the exposure of interest and estimates one exposure effect at a time, while jointly accounting for measured covariates and unmeasured confounders. This design improves the reliability of MR analyses. In simulations and real data, MRMU achieved better type I error control, higher statistical power, and more accurate effect estimation than existing MR methods. Applying to coronary artery disease (CAD), MRMU identified robust cardiometabolic risk factors, including LDL-C, APOB, systolic blood pressure, body mass index, and smoking initiation, with consistent evidence across multiple CAD datasets. In contrast, traits such as HDL-C, height, and educational attainment, which were found to be significant by existing MR methods, were no longer supported by MRMU. MRMU further supported blood pressure-related traits, rather than lipid traits, as the more relevant pathway linking urate to CAD. Finally, by integrating large-scale plasma proteomics data, MRMU identified candidate CAD drug targets beyond established HMGCR- and PCSK9-related pathways, highlighting its utility for therapeutic target prioritization.

20.
arXiv (CS.CL) 2026-06-15

A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions

Transformer-based clinical language models are increasingly integrated into high-stakes clinical decision support pipelines, yet the computational mechanisms through which demographic associations encoded in medical documentation propagate into model probability distributions remain empirically underspecified. We present a systematic computational audit of representational bias in ClinicalBERT (Alsentzer et al., 2019), a BERT-based model pretrained on MIMIC-III discharge summaries, employing two complementary probing methodologies: Log Probability Bias Analysis (LPBA), which quantifies demographic descriptor-induced shifts in masked token probability distributions across behavioral and evaluative semantic categories, and Masked Language Model-based analysis (MLM), which probes internal representational structure for demographic agency attribution encoding across 98 real clinical sentence templates and eight intersectional race-gender combinations. Corpus frequency analysis operationalizes the distinction between statistical disparity and bias amplification by benchmarking model outputs against empirical term frequencies in the MIMIC-III training corpus. Of 32 statistically significant findings, 65.6% contradict observed corpus distributions, rising to 80% for Black patients and 87.5% for agency attribution under MLM probing, providing direct empirical evidence that representational bias in ClinicalBERT operates predominantly through model-internal amplification rather than training data inheritance. Keywords: natural language processing, clinical documentation, algorithmic auditing, representational bias, health equity 1

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

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

arXiv:2606.17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First, a single scalar signal conflates the two objectives of viability and efficiency; once basic success is achieved, the binary label provides no gradient to distinguish efficient completions from slow ones. Second, real-world rollouts mix autonomous and intervention segments; naively assigning episode outcomes across these boundaries introduces incorrect credit assignment. To address these issues, we propose Hierarchical Advantage-Weighted Behavior Cloning (HABC), which trains separate critic heads for these two objectives on different data subsets and combines their outputs with a state-adaptive balance. A state-adaptive gate $g_t$ merges their one-step advantages, prioritizing viability when success is uncertain and shifting to efficiency only when viability is high, and converts the result into per-transition weights on the actor loss. Intervention-aware credit assignment further restricts outcome labels to segments executed by the current policy, preventing supervision from leaking across intervention boundaries. In real-robot experiments on three contact-rich bimanual tasks, HABC raises success from supervised fine-tuning (SFT) baselines of 36%, 44%, and 12% to 92%, 88%, and 38%.

22.
arXiv (CS.LG) 2026-06-18

On the Stability of the Jacobian Matrix in Deep Neural Networks

arXiv:2506.08764v3 Announce Type: replace Abstract: Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian. Prior work has identified critical initialization schemes that ensure Jacobian stability, but these analyses are typically restricted to fully connected networks with i.i.d. weights. In this work, we go significantly beyond these limitations: we establish a general stability theorem for deep neural networks that accommodates sparsity (such as that introduced by pruning) and non-i.i.d., weakly correlated weights (e.g. induced by training). Our results rely on recent advances in random matrix theory, and provide rigorous guarantees for spectral stability in a much broader class of network models. This extends the theoretical foundation for initialization schemes in modern neural networks with structured and dependent randomness.

24.
medRxiv (Medicine) 2026-06-10

A Three-Tier Operational Benchmark for Evaluating Large Language Models on Hospital Medication Safety

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.

25.
arXiv (CS.AI) 2026-06-19

Secure Coding Drift in LLM-Assisted Post-Quantum Cryptography Development: A Gamified Fix

arXiv:2606.19474v1 Announce Type: cross Abstract: The transition to Post Quantum Cryptography (PQC) introduces considerable implementation complexity, requiring strict adherence to constant-time execution, side channel resistance, and precise parametrisation. Simultaneously, large language models (LLMs) are heavily embedded in software development workflows, including cryptographic engineering. While LLMs improve productivity, evidence shows that they frequently generate insecure or suboptimal code, particularly in security critical domains. This paper introduces Secure Coding Drift in PQC, a novel socio technical vulnerability model capturing the gradual degradation of secure coding practices due to sustained reliance on LLM-generated code. Unlike prior work that focuses on static vulnerabilities, we conceptualise security risk as a longitudinal behavioural phenomenon rising from human AI interaction. To mitigate this, we propose a gamified, LLM augmented secure coding framework that embeds adversarial evaluation, behavioural feedback, and security scoring into development workflows. Our approach reframes LLMs from passive assistants into active security co-pilots, contributing toward safer PQC implementation in AI mediated environments.