Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
medRxiv (Medicine) 2026-06-23

Estimating vaccine-prevented disease outcomes when vaccination has only direct effects

Vaccination can be a useful intervention for reducing infectious disease burden. Estimating numbers of vaccine-prevented health outcomes is one approach to quantifying the benefits of vaccination. Here we improve a method described by Foppa et al. (1) that assumes vaccination has only direct effects, that is, it cannot prevent infection or onward transmission of the disease. We rederive this method and derive an improved method that increases estimation accuracy with minimal additional analytical complexity. To evaluate the improved method, we simulated disease outbreaks and compared the accuracy of the two methods for estimating prevented disease outcomes. In 84% of simulations performed over a wide parameter space, the improved method had an equal or smaller estimation error compared to the original Foppa method, with 7.9-fold smaller mean error and 44-fold smaller standard deviation of errors. Our study improves a method for estimating prevented burden when assuming vaccination has only direct effects.

02.
arXiv (CS.CV) 2026-06-16

Multi-Modal Spatio-Temporal Graph Neural Network with Mixture of Experts for Soil Organic Carbon Prediction

Top-soil organic carbon (SOC) prediction is fundamental to agricultural sustainability, land use policy and fertilization planning. Existing approaches face two limitations: they pair hand-crafted covariates with classical ML or single-modal deep models that miss rich spectral and temporal information, and grid-based architectures ignore the irregular spatial structure of field measurements. We introduce SpTGNN, a multi-modal spatio-temporal graph neural network addressing both. SpTGNN represents soil measurements as nodes in a heterogeneous graph with three edge types (spatial proximity, spectral similarity, elevation), and applies relational graph attention to learn separate patterns per relation. A fine-tuned TerraMind encoder extracts node features from Sentinel-2, Sentinel-1 and DEM signals, combined with per-sample environmental covariates and learned positional and temporal embeddings. A sparse Mixture-of-Experts module fuses the four streams via top-$k$ routing. Uncertainty is captured by pairing heteroscedastic regression (aleatoric) with deep ensembles (epistemic), and a Moran's $I$ penalty regularizes spatial autocorrelation. We evaluate on a global SOC corpus split into three regional instances ($\sim$49k samples globally, Africa $\sim$26k, Europe $\sim$14k). Our 5-member deep ensemble reports $R^2=0.762$, RMSE $=3.51\pm0.48$ g/kg and MAPE $=22.9\%$ on the Africa test split, improving over a tabular XGBoost baseline; the best single checkpoint reaches validation $R^2=0.864$. Ablations confirm the heterogeneous graph, MoE fusion and fine-tuned backbone each contribute substantively, and the ensemble UQ stack achieves post-calibration ECE of $0.031$ (hybrid) and $0.026$ ($\beta$-NLL). To our knowledge, this is the first framework to unify foundation-model feature extraction, heterogeneous graph attention and decomposed uncertainty quantification for SOC estimation.

03.
arXiv (CS.AI) 2026-06-24

Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing

arXiv:2606.07558v2 Announce Type: replace-cross Abstract: Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale. This work addresses the need for an automated system to classify scanned page images based on visual content type - text, tables, and graphics - enabling content-specific downstream processing such as Optical Character Recognition (OCR) or structured data extraction. Methods: An image classification system was developed and evaluated on a dataset of over 48,000 annotated historical page images from century-old Czech archaeological archives, refined through four successive annotation stages with domain-expert review. A Random Forest Classifier baseline was established using hand-crafted image features. Subsequently, deep learning architectures were fine-tuned and compared: Convolutional Neural Networks (EfficientNetV2, RegNetY), Vision and Document Image Transformers (ViT, DiT), and multimodal CLIP models. An 11-category label scheme was designed collaboratively with domain experts and evaluated via five-fold cross-validation. Results: The feature-based baseline achieved approximately 75% accuracy. Fine-tuned CNNs and Transformers substantially outperformed it, with RegNetY-16GF achieving 99.16% and ViT-large 99.12% Top-1 accuracy on the held-out test set. CLIP ViT-B/16 reached 99.14% with optimized text descriptions. Conclusion: Image-only models, particularly RegNetY-16GF, deliver near-perfect classification accuracy and produce consistent labels across 649,508 unlabeled archival pages with over 90% inter-model agreement. Fine-tuned CLIP, despite competitive test-set accuracy, showed under 65% agreement with image-only models on unlabeled data, making it less suitable for deployment. The final models, annotated dataset, and software are publicly available under open-source licenses.

04.
arXiv (CS.AI) 2026-06-15

Q-Net: Queue Length Estimation via Kalman-based Neural Networks

arXiv:2509.24725v4 Announce Type: replace-cross Abstract: Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows complicates this task despite the availability of two privacy-preserving data sources: (i) aggregated vehicle counts from loop detectors near stop lines, and (ii) aggregated floating car data (aFCD) that provide segment-wise average speed measurements. However, how to integrate these sources with differing spatial and temporal resolutions for queue length estimation is rather unclear. Addressing this question, we present Q-Net: a queue estimation framework built upon a state-space formulation. This design addresses key challenges in queue modeling, such as violations of traffic conservation assumptions. Q-Net follows the Kalman predict-update structure and maintains physical interpretability in both the state evolution and measurement models. Q-Net uses an AI-augmented Kalman filter to learn time-varying gain dynamics from data. The framework supports real-time implementation and improves spatial transferability by grouping aFCD measurements into fixed-size local groups, making the number of learnable parameters independent of section length. Evaluations on urban main roads in Rotterdam, the Netherlands, show that Q-Net outperforms baseline methods, tracks queue formation and dissipation accurately, and mitigates aFCD-induced delays. By combining data efficiency, interpretability, real-time applicability, and spatial transferability, Q-Net makes accurate queue length estimation possible without costly sensing infrastructure like cameras or radar.

05.
arXiv (CS.LG) 2026-06-11

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling

arXiv:2509.20241v2 Announce Type: replace Abstract: As AI inference scales to billions of queries, estimates of per-query energy use are increasingly important for capacity planning, efficiency interventions, and policy. Yet many public estimates assume non-production settings, leading to systematic overestimation. We introduce a bottom-up framework estimating inference energy from token throughput, node power, and overhead under large-scale deployment assumptions. For frontier-scale models (>200B parameters) on H100 nodes, we estimate a median energy of 0.31 Wh/query (IQR 0.16-0.60), indicating widely cited estimates are overstated by 4-20x. In test-time scaling scenarios 15x longer than typical queries, the median energy rises 13x to 3.91 Wh (IQR 2.15-7.05). Across models, serving systems, and hardware, we estimate 8-20x line-of-sight energy reductions. At datacenter scale, serving 1 billion queries/day requires 0.7 GWh; if 10% are long queries, demand rises to 1.7 GWh/day. With efficiency interventions, it falls to 0.8 GWh/day, mitigating the energy impact of test-time scaling.

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

Purely unrectifiable sets, fractal percolation and graphs of functions

arXiv:2606.15745v1 Announce Type: cross Abstract: This paper contains a survey of some of the results of the author related to unrectifiablity and is an extended version of the author's talk given at the Second Winter School Geometric Measure Theory Rectifiability vs. Pure Unrectifiability in Hanghzou, China. These results include irregular/purely unrectifiable $1$-sets on the graphs of continuous functions like the Takagi, the Weierstrass-Cellerier and the typical (in the sense of Baire) continuous function. It is also discussed that there exists $ {\alpha}_{0}\alpha_0$. The background of the $1$-unrectifiability is discussed in more detail.

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

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

arXiv:2606.12940v1 Announce Type: cross Abstract: Neural speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Modifying the quantizer or increasing model capacity are common fixes, but they complicate downstream language modeling. Our core idea is to align the decoder's internal feature manifolds when processing both the quantized tokens and their original continuous embeddings, using a lightweight feature-mapping loss. This requires minimal training overhead and no inference-time changes. Applied to XCodec2, self-guidance improves all reconstruction metrics, achieving state-of-the-art low-bitrate performance. Notably, it enables a 4x codebook reduction without fidelity loss, which downstream TTS experiments show significantly improves LLM-based synthesis by simplifying the token modeling space. Multiple statistical observations and visualizations corroborate the enhanced internal manifold alignment in the decoder. Extensive experiments confirm its generality across various inductive biases. Self-guidance thus establishes an efficient, broadly applicable method for high-fidelity neural audio coding.

08.
arXiv (CS.CL) 2026-06-19

NEST: Narrative Event Structures in Time for Long Video Understanding

Recent progress in vision-language models has enabled the processing of increasingly long video sequences, but the ability to handle extended token streams does not translate to understanding of narrative structure in long videos. Existing long video benchmarks focus on needle-in-a-haystack retrieval rather than evaluating how low-level actions form events, how events interact across time, and how narratives progress, for example, whether a model can connect an early setback, such as a job loss to a later relationship breakup, despite long gaps, intervening scenes, or flashbacks that reframe what occurred. We introduce NEST (Narrative Event Structures in Time for Long Video Understanding), a dataset of 1005 full-length movies (avg. 98 minutes), each annotated with 102 multimodal narrative events grounded in visual content, dialogue, and audio. NEST captures multimodal narrative events with structured annotations grounded in visual content, dialogue, and audio, and links them through relations that reflect narrative structure, including temporal ordering, hierarchical composition, and long-range dependencies. We introduce baselines for event trigger detection (ETD), event localization (EL), event argument extraction (EAE), and event relation extraction (ERE). The benchmark is highly challenging for grounded event discovery, with ETD below 8%, EL under 6%, and EAE below 11%. In contrast, ERE is more tractable once events are given, reaching 35.45% F1 zero-shot and 44.42% F1 after fine-tuning.

09.
arXiv (CS.AI) 2026-06-19

FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS

arXiv:2606.20518v1 Announce Type: new Abstract: Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless the model is retrained. We introduce FlowEdit, a life-long adaptation framework for frozen flow-matching TTS that learns pronunciation corrections as latent conditioning edits rather than weight updates. When corrective feedback is provided, FlowEdit optimizes a token-level perturbation in the text embedding space, then stores the correction in a Modern Hopfield Network serving as content-addressable episodic memory. At inference, corrections are retrieved via soft attention with a similarity gate, enabling fuzzy morphological matching. On our curated benchmark of 312 multilingual proper nouns across 18 language families, FlowEdit reduces target-word Phoneme Error Rate by 92.7% relative to the zero-shot baseline while maintaining identical general-speech quality. Corrections complete in approximately 15 seconds on a single GPU.

10.
bioRxiv (Bioinfo) 2026-06-23

VCBench: A Multi-Dimensional Benchmark for Single-Cell Foundation Models

Single-cell foundation models are increasingly positioned as virtual cells, yet their capabilities are assessed by fragmented, largely single-task benchmarks that obscure where these models improve on simple baselines. VCBench addresses this by synthesizing four independent virtual-cell frameworks into seven capability dimensions: perturbation response prediction, cross-species universality, gene regulatory network (GRN) inference, modality integration, temporal dynamics, multi-scale integration, and in silico experimentation. Each dimension is assessed for operational testability under current architectures and datasets: five admit direct or proxy evaluation, while multi-scale integration and in silico experimentation are structurally untestable as end-to-end tasks. We evaluate five foundation models (Geneformer, scGPT, UCE, TranscriptFormer, Arc State) against pre-registered linear and nearest-neighbor baselines across the five testable dimensions, and report three findings. First, the baselines match or exceed every foundation model on four of the five scored dimensions, replicating the reported competitiveness of linear baselines on perturbation prediction and extending it to cross-species transfer, GRN inference, and temporal ordering. Second, TranscriptFormer alone exceeds the strongest baseline on cross-modal RNA-to-protein prediction (53% Pearson improvement, with a documented contamination caveat) and is the only model to reach Level 2 in the pre-registered Virtual Cell (VC) Level rubric; the architectural choice behind this advantage simultaneously causes a spectral collapse that destroys its temporal-ordering performance, a tradeoff invisible to single-task benchmarks. Third, no foundation model publishes a complete cell-level training manifest, leaving data contamination undetectable to users. Alongside the benchmark, VCBench releases a Contamination Reporting Schema and contributes two further methodological tools: a common-label-set protocol that controls for class-count confounds in cross-species transfer, and a spread-error correlation probe for epistemic calibration.

11.
arXiv (CS.AI) 2026-06-19

AI4SE and SE4AI Exploration: A Decade Looking Back and Forward

arXiv:2606.19630v1 Announce Type: new Abstract: The March 2020 INCOSE INSIGHT special issue on AI and Systems Engineering (SE) became the most downloaded issue in the publication's history and launched a research community that now draws over 250 registrants to its annual workshop. In this article, we trace the progress in AI and SE across three phases (labeled here foundational, applied, and LLM inflection) based on the authors' reading of the field's core papers, and describe our opinions of where the community has converged and where critical gaps remain. Separately, a human-AI agreement literature review leveraging both human expertise and six AI models was performed to assess the relevance of 1,712 INCOSE INSIGHT articles and 889 SERC publications. The results identify five critical research gaps and offer guidance for practitioners navigating AI adoption, assurance, and workforce transformation in SE. We share the agreement data and the AI4SE/SE4AI Explorer web application so readers can compare their own relevance judgments with the human and AI raters.

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

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

arXiv:2606.13125v1 Announce Type: cross Abstract: Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying processes capabilities are acquired or enhanced via reinforcement learning post-training. Our analysis, based on controlled math reasoning experiments with Qwen-2.5-1.5B, reveals two core mechanisms: strategy selection and strategy improvement. Our results highlight the role of SFT data and reinforcement learning data in activating these mechanisms, in particular showing how supervising the model on diverse reasoning strategies can enable strategy selection and how increasing difficulty in reinforcement learning data can enable strategy improvement. Taken together, our results provide mechanistic insight into RL training and suggest practical interventions to continue scaling reasoning capabilities.

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

E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis

arXiv:2606.23888v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) strategies typically optimize text fidelity alone, essentially rewarding correct diagnoses derived from language priors rather than genuine visual perception. To address this, we propose cross-view aligned Evidence-driven Multimodal Reinforcement Learning (Evidence-MRL, noted as E-MRL), a reliable RL reasoning framework that formulates the generation process as a Markov Decision Process of "diagnosis-localization-verification". Unlike standard approaches, our model is explicitly trained to identify a "key evidence slice" alongside the global diagnostic report, grounding its findings in verifiable visual evidence. Crucially, we introduce a novel cross-view consistency reward, which validates the semantic alignment between the golden-standard report and a local visual re-query of the selected key slice, providing additional rewards for correctly-localized reasoning. Experiments on large-scale 3D CT tumor datasets demonstrate that E-MRL significantly reduces hallucinations and improves diagnostic accuracy compared to SFT and RL baselines, offering a clinically interpretable solution for visually-grounded and tumor analysis.

14.
arXiv (CS.CV) 2026-06-16

CoMNeT: A MedNeXt-CorrDiff Framework for Volumetric Brain Tumor Segmentation

Accurate brain tumor segmentation from multiparametric magnetic resonance imaging (MRI) is critical for treatment planning, response assessment, and quantitative neuro-oncology research. However, automated segmentation remains a difficult task in computer vision because of variation in tumor appearance and MRI protocols across patient scans. Moreover, clinically important regions such as enhancing tumor (ET) and tumor core (TC) are often small relative to the full brain volume, furthering increasing the difficulty of achieving high voxel-level precision. In this paper, we show that combining a modern 3D convolutional segmentation model with corrective diffusion-based refinement and ensembling improves volumetric glioma segmentation on the UTSW-Glioma dataset. We propose CoMNeT, a MedNeXt-CorrDiff framework that uses four MRI modalities as input and predicts ET, TC, and whole tumor (WT) regions for automated brain tumor segmentation. MedNeXt is used as the primary segmentation model with Global Response Normalization for feature learning, while CorrDiff is trained as a postprocessing residual refinement method to correct errors in the probability maps before final thresholding. Using five-fold cross-validation, CoMNeT achieved the highest Dice score for most tumor regions, with ET, TC, WT, and average Dice scores of 0.7543 +/- 0.0261, 0.6806 +/- 0.0166, 0.9049 +/- 0.0128, and 0.7798 +/- 0.0184, respectively. CoMNeT outperformed two selected baseline models: SegResNet (0.7555 +/- 0.0190 average Dice) and standalone MedNeXt (0.7697 +/- 0.0154 average Dice). Our findings support the use of corrective diffusion and fold-level probability ensembling as practical additions to existing state-of-the-art 3D convolutional models for automated glioma segmentation.

15.
arXiv (quant-ph) 2026-06-19

Entanglement structure of the dynamical phases in the sub-Ohmic spin-boson model

arXiv:2606.20313v1 Announce Type: new Abstract: The sub-Ohmic spin-boson model exhibits three distinct dynamical regimes in its spin population dynamics, classified as coherent, incoherent, and pseudo-coherent. Whether these regimes correspond to distinct spin-bath entanglement structures remains an open question. Here we address this using tree tensor network states with projector-splitting time evolution (TTN-TDVP-PS), scanning a broad grid in the sub-Ohmic $(s, \alpha)$ plane. We find that the spin entanglement entropy $S_\mathrm{spin}(t)$ reaches a stationary plateau on a timescale shorter than the polarization relaxation, enabling construction of a stationary entropy landscape from the stationary value $S_\mathrm{stable}$. Within this scalar entropy landscape, the entropy ridge broadly follows the population-based phase boundary at small $s$, but does not reproduce the two-branch structure at large $s$. The ridge remains single-valued within the incoherent region rather than separately tracking both population-based transitions. The Bloch-sphere representation provides a geometric interpretation of this behavior. The entropy plateau corresponds to trajectories settling onto constant-radius shells, with the ridge marking the parameters of smallest stationary Bloch radius. Mode-resolved bath entanglement shows that low-frequency modes dominate the environmental entropy scale and that coherent dynamics enhance bath-mode correlations beyond direct spin–mode correlations. These results establish the stationary spin entanglement entropy as a physically informative observable that complements population-based classifications of dissipative quantum dynamics.

16.
arXiv (CS.AI) 2026-06-12

Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems

arXiv:2605.27628v2 Announce Type: replace Abstract: As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or alignment limitations, this paper explores the architectural vulnerability of unbounded autonomy - the presumption that an agent should continue operating regardless of rising uncertainty. It introduces a theory of managed autonomy that defines intelligent behavior through the formal capacity to detect epistemic drift, suspend reasoning, attempt recovery, and ultimately surrender control when reliability diminishes. We instantiate this theory via the SMARt (Self-Managing Multi-tier Autonomous Reasoning with Regulated/Revoked transitions) model, a four-layer framework featuring Stable, Meta-cognitive, Assisted, and Regulated states. By developing a timed, guarded Petri net formulation, we establish theoretically bounded properties for the system, demonstrating how architecture can formally mandate escalation, constrain invalid outputs, and ensure governance reachability under specified conditions. We further analyze how incorporating domain-specific trigger sets across varied operational settings (e.g., healthcare, robotics, etc.) can systematically preserve safety, assuming completeness and soundness criteria are met. Because these triggers are designed to be adaptive, the SMARt model accommodates the safe, controlled expansion of an agent's operational scope over time. We conclude that formalizing failure management within the autonomy lifecycle is a crucial step toward realizing reliable and governed artificial intelligence.

17.
arXiv (CS.CV) 2026-06-11

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation

The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. We introduce the Synthetic Dataset Quality Metric (SDQM) to assess data quality for object detection tasks without requiring model training to converge. This metric enables more efficient generation and selection of synthetic datasets, addressing a key challenge in resource-constrained object detection tasks. In our experiments, SDQM demonstrated a strong correlation with the mean average precision (mAP) scores of YOLO11, a leading object detection model, whereas previous metrics only exhibited moderate or weak correlations. In addition, it provides actionable insights into improving dataset quality, minimizing the need for costly iterative training. This scalable and efficient metric sets a new standard for evaluating synthetic data. The code for SDQM is available at https://github.com/ayushzenith/SDQM

18.
arXiv (CS.AI) 2026-06-24

Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation

arXiv:2606.24515v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces. However, reinforcement learning for CUAs remains difficult because open-ended desktop environments rarely provide scalable, machine-readable reward signals: task success is often visually grounded and hard to specify with handcrafted reward functions or dense manual labels. We propose an RL fine-tuning framework that uses autonomous vision-language evaluation as a scalable supervision signal for GUI agents. Given a final screenshot and the original instruction, a Vision-Language Model judges task completion and provides terminal feedback without task-specific heuristics or manual labels during policy optimization. Because autonomous evaluators are imperfect, we model their feedback as a noisy binary reward channel and derive a noise-corrected reward estimator for Proximal Policy Optimization. Experiments across macOSWorld, Windows Agent Arena, and OSWorld show that corrected evaluator rewards outperform both zero-shot baselines and raw evaluator rewards, improving success rates by an average of 12.6 percentage points over zero-shot performance and 5.1 points over raw evaluator fine-tuning. These results suggest that autonomous evaluation can serve as a practical reward signal for RL in GUI environments when evaluator noise is explicitly modeled and corrected.

19.
arXiv (CS.CL) 2026-06-17

In-Context Environments Induce Evaluation-Awareness in Language Models

Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent evaluation awareness. This raises concerns that models could strategically underperform, or sandbag, to avoid triggering capability-limiting interventions such as unlearning or shutdown. Prior work demonstrates sandbagging under hand-crafted prompts, but this underestimates the true vulnerability ceiling. We introduce a black-box adversarial optimization framework treating the in-context prompt as an optimizable environment, and develop two approaches to characterize sandbagging: (1) measuring whether models expressing intent to underperform can actually execute it across different task structures, and (2) causally isolating whether underperformance is driven by genuine evaluation-aware reasoning or shallow prompt-following. Evaluating Claude-3.5-Haiku, GPT-4o-mini, and Llama-3.3-70B across four benchmarks (Arithmetic, GSM8K, MMLU, and HumanEval), optimized prompts induce up to 94 percentage point (pp) degradation on arithmetic (GPT-4o-mini: 97.8\%$\rightarrow$4.0\%), far exceeding hand-crafted baselines which produce near-zero behavioral change. Code generation exhibits model-dependent resistance: Claude degrades only 0.6pp, while Llama's accuracy drops to 0\%. The intent – execution gap reveals a monotonic resistance ordering: Arithmetic $

20.
arXiv (CS.CL) 2026-06-19

Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorship

Large language models (LLMs) increasingly review and revise text, including their own. A documented self-preference bias (models favoring their own generations when acting as judges) raises the question of whether models also resist valid corrections to their own writing. We test this in a setting where "valid" is decided not by another model but by a deterministic verifier: instruction-following revision on IFEval. A model writes a draft; the official IFEval checker confirms the draft violates a constraint and that a candidate edit fixes it; the model then accepts or rejects that edit either as the genuine in-context author or as a fresh model that sees the draft neutrally. Across four mid-tier model families and 85 author-versus-fresh comparisons, we find no detectable self-preference: authors reject verified-good fixes to their own drafts at essentially the same rate as fresh models judging the same drafts (gap -5.1 pp, 95% CI [-12.9, +2.7]). A self-skepticism hint from a smaller pilot did not replicate at scale. The one robust observation is qualitative: when authors do reject a verified-good fix, 97% of their stated reasons are flaw-catching rather than preference, that is, about the character of rejections, not an elevated rate. Effects smaller than ~13 pp cannot be excluded at this sample size.

21.
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.

22.
arXiv (CS.CV) 2026-06-16

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change captioning datasets typically describe overall image-level differences, leaving fine-grained localized semantic reasoning largely unexplored. To close this gap, we present RSRCC, a new benchmark for remote sensing change question-answering containing 126k questions, split into 87k training, 17.1k validation, and 22k test instances. Unlike prior datasets, RSRCC is built around localized, change-specific questions that require reasoning about a particular semantic change. To the best of our knowledge, this is the first remote sensing change question-answering benchmark designed explicitly for such fine-grained reasoning-based supervision. To construct RSRCC, we introduce a hierarchical semi-supervised curation pipeline that uses Best-of-N ranking as a critical final ambiguity-resolution stage. First, candidate change regions are extracted from semantic segmentation masks, then initially screened using an image-text embedding model, and finally validated through retrieval-augmented vision-language curation with Best-of-N ranking. This process enables scalable filtering of noisy and ambiguous candidates while preserving semantically meaningful changes. The dataset is available at https://huggingface.co/datasets/google/RSRCC.

23.
arXiv (CS.AI) 2026-06-18

FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs

arXiv:2606.19025v1 Announce Type: cross Abstract: Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. While increasing model and dataset scale remains the dominant driver of performance, Mixture-of-Experts (MoEs) architectures have recently achieved state-of-the-art results by decoupling parameter count from computational cost. This efficiency enables training massive models on constrained compute budgets, yet it typically requires the high-speed interconnects of a single datacenter. To overcome these physical limits, recent approaches such as DiLoCo and Photon use low-communication data-parallel methods to enable scaling across geographically distributed, weakly connected data centers. However, these methods suffer from a fundamental inefficiency: they require full model replicas at every site, which imposes prohibitive memory constraints and communication overheads. In this work, we introduce FoMoE, a system that breaks the full-replica paradigm by partitioning expert layers across workers. We demonstrate that FoMoE: (I) reduces communication costs by up to 1.42x over efficient baselines and 45.44x over DDP via partial expert replication in the studied regimes; (II) achieves empirical throughput speedups of up to 1.4x through a novel skip-token mechanism; and (III) shows stable routing in the trained proxy regimes and projects the communication/memory benefits to 100B-scale configurations through system modelling.

24.
arXiv (CS.CV) 2026-06-16

SPDA-SAM: A Self-prompted Depth-Aware Segment Anything Model for Instance Segmentation

Recently, Segment Anything Model (SAM) has demonstrated strong generalizability in various instance segmentation tasks. However, its performance is severely dependent on the quality of manual prompts. In addition, the RGB images that instance segmentation methods normally use inherently lack depth information. As a result, the ability of these methods to perceive spatial structures and delineate object boundaries is hindered. To address these challenges, we propose a Self-prompted Depth-Aware SAM (SPDA-SAM) for instance segmentation. Specifically, we design a Semantic-Spatial Self-prompt Module (SSSPM) which extracts the semantic and spatial prompts from the image encoder and the mask decoder of SAM, respectively. Furthermore, we introduce a Coarse-to-Fine RGB-D Fusion Module (C2FFM), in which the features extracted from a monocular RGB image and the depth map estimated from it are fused. In particular, the structural information in the depth map is used to provide coarse-grained guidance to feature fusion, while local variations in depth are encoded in order to fuse fine-grained feature representations. To our knowledge, SAM has not been explored in such self-prompted and depth-aware manners. Experimental results demonstrate that our SPDA-SAM outperforms its state-of-the-art counterparts across twelve different data sets. These promising results should be due to the guidance of the self-prompts and the compensation for the spatial information loss by the coarse-to-fine RGB-D fusion operation.

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

Embedded Arena: Iterative Optimization via Hardware Feedback

arXiv:2606.16190v1 Announce Type: cross Abstract: Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints. Optimizing models for heterogeneous microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware – compiling, flashing, and measuring on real hardware – to enable closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with