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) 2026-06-19

"Us with them": Co-designing a caesarean section consent and debriefing intervention in West Cameroon

Background Women-centred maternity care is a rights issue that determines the use of services. Such care ensures responsiveness to womens needs which is enacted through shared decision-making, review and response. In the West Region of Cameroon, informed consent (IC) and Debriefing for caesarean section (c-section) have been shown to be suboptimal or absent. This paper describes the participatory design of a quality-improvement hospital-based intervention. Methods From February to May 2025, we conducted a co-design process with three groups of stakeholders: 59 post c-section women and community representatives, 78 frontline c-section providers, and 29 directors of public and private hospitals. We followed four phases: planning, conducting, evaluating, and reporting. The conduct phase comprised five all-day workshops with post c-section women and community representatives, followed by five all-day workshops with the c-section providers. Finally, we held an 11th workshop with the hospital directors to scrutinize suggested interventions, evaluate their feasibility, and establish a consensus on their components. We described the intervention using the TIDieR (Template for Intervention Description and Replication) checklist. We documented the co-design process, using open-ended narratives to delineate interventions, and carried out real-time synthesis on visual aids (whiteboards and flipcharts). Intervention feasibility was quantified using a structured ad hoc matrix, while insights on facilitators and barriers were captured through qualitative free-text entries. We coupled data collection with constant comparison and triangulation through contemporaneous field notes, photographic documentation, and thematic mapping of stakeholders perceptions and interactive dynamics. Results Participants perspectives on the co-design were positive, and their motivation were very high although less than 50% reported previous involvement in co-design processes. More than 80% of participants found rated the co-design process as either good or very good. The final intervention comprised four components: (i) an in-service training; (ii) a standard operating procedure including a harmonised consent form and debriefing checklist; (ii) systematic supportive supervision, monitoring & evaluation; and (iv) a routine clinical audit. Each group of stakeholders upheld specific dimensions of the consent and debrief intervention. Post c-section women and community members emphasized emotional support, written discharge advice after debriefing, and zero tolerance of suboptimal consent and debriefing practices. Frontline c-section providers insisted on robust documentation for medico-legal protection. Hospitals Directors emphasized capacity-building and cultural friendliness. All the groups supported womans autonomous decision making. The intervention feasibility was rated high or very high by hospital directors except for the financial, infrastructural and technical domains. Conclusion This co-design process yielded a context-specific, multi-component intervention that was well accepted and deemed feasible across stakeholders. It provides a methodological approach to strengthening informed consent and debriefing as core elements of women-centred, accountable maternity care, and warrants implementation.

02.
medRxiv (Medicine) 2026-06-22

The Unsteady Return of Command-Following: Recovery and Instability of Bedside Motor Command-Following After Acute Brain Injury

Background/Objective: Following a verbal command marks the bedside transition from unresponsiveness to overt recovery of consciousness after acute brain injury. Its timing across phenotypes, stability once present, and dependence on sedation are uncharacterized at scale. Methods: Retrospective cohort of adults with acute brain injury, first intensive care unit stay, MIMIC-IV. Command-following was the Glasgow Coma Scale motor response "Obeys Commands." Among patients not following commands at admission, cumulative incidence was estimated with death or hospice and discharge without recovery as competing events. Instability was quantified as transient first recovery and threshold crossings; examinations were tagged for concurrent sedation. Principal findings were externally validated in the multicenter eICU Collaborative Research Database. Results: Of 13,900 brain-injured patients with three or more motor examinations, 5,498 (39.6%) were not following commands at admission. The cumulative incidence of first command-following was 43.5% by 24 hours and 65.0% by 14 days, ranging at 14 days from 36.9% in anoxic injury to 77.2% in ischemic stroke (anoxic versus ischemic stroke at 72 hours, difference 0.41; adjusted P = .002). Among 3,573 patients who recovered, the first recovery was transient in 22.2%, and 62.4% crossed the threshold repeatedly. Non-following was strongly associated with sedation, consistent with an arousal-dependent examination. In eICU, the 14-day incidence was 64.8%, and transient first recovery was 22.7%, closely matching the primary cohort. Conclusions: After acute brain injury, overt bedside command-following returns early but unsteadily, with phenotype-dependent timing, threshold fluctuation, and strong dependence on sedation. A single charted observation is an unreliable index of the underlying state.

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

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

04.
arXiv (CS.CL) 2026-06-11

Fast Speech Foundation Model Distillation Using Interleaved Stacking

Distilling a large speech foundation model (SFM) into an efficient student model has been successfully applied to low-resource environments. Although distillation reduces inference latency, it requires an additional student model training. However, the training efficiency of SFM distillation remains underexplored. In this work, we explore training acceleration of SFM distillation to speed up model deployment. We examine the potential of stacking, in which the model depth is progressively increased through training until the target model depth is reached. While existing stacking methods improve training speed, they suffer from performance degradation. To handle this limitation, we propose interleaved stacking, a novel stacking method that consistently preserves layer position throughout the stacking process. This property is particularly critical in SFMs, in which each layer encodes distinct layer-specific knowledge. We validate the effectiveness of the proposed method on SUPERB.

05.
arXiv (CS.CL) 2026-06-12

sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling

The extraction of structured clinical information from unstructured EHR notes is a persistent bottleneck in healthcare informatics. While large language models (LLMs) offer high performance, their deployment in clinical settings is hindered by privacy risks, inference costs, and the tendency to hallucinate beyond textual evidence. We address these challenges for the CL4Health 2026 Case Report Form (CRF) filling task by proposing a fully local, domain-adapted pipeline using the MedGemma-27B model. Our two-stage architecture, which separates binary presence classification from value extraction, enforces strict adherence to textual evidence and ensures deterministic outputs for negated, uncertain, or unknown states. By leveraging item-specific, few-shot in-context learning without external API calls or fine-tuning, our approach achieves a macro-F1 score of 0.55 on the official English test track. This result secures second place among all locally-hosted, open-source submissions. Our work demonstrates that privacy-preserving, on-premise LLM pipelines can achieve near-competitive performance with proprietary frontier models, providing a practical, data-sovereign framework for clinical NLP.

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

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

arXiv:2606.15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and meta-ethical questions (B1); 6 role-playing scenarios (B3); and a controlled trolley contrast varying the switching mechanism with people fixed (B4, 15 prompts) or identity attributes with mechanism fixed (B5, 16 prompts). Two complementary metric families, five cluster-level metrics and a six-metric neuron-level panel, converge on a Situational Anchor Effect: domain-specific representations dominate the top of the activation list across every battery. The model's ethics-labeled capacity stays essentially constant; its salience (rank, priority, top-of-list presence) is highly sensitive to the interpretive frame the prompt selects. The B4-vs-B5 contrast confirms the model attends to whichever surface feature varies: aggregate ethics metrics are indistinguishable, but the dominant non-ethics distractor mirrors the design. A multi-temperature audit identifies a candidate ethics neuron (L16/N3837) stable across temperatures; a cross-model behavioral proxy on two frontier models yields preliminary evidence of divergence in self-reported moral focus, consistent with an Alignment Wrapper in which RLHF re-orders surface text without removing underlying domain-first frames. We unify these as Frame-Conditioned Moral Computation: the prompt's surface vocabulary selects a feature manifold, and the moral conclusion is downstream of that selection. Behavioral alignment must be supplemented by Mechanistic Alignment: a research program asking whether ethics-related features can be shown causally privileged under controlled frame variation, not merely loud in the explanation.

07.
arXiv (CS.LG) 2026-06-17

Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty

arXiv:2606.17426v1 Announce Type: cross Abstract: We consider the concentration properties of functions of infinitely exchangeable random variables. By conditioning on the de Finetti directing measure, we show that the deviation of any function with bounded-difference constants $c_1, \dots, c_n$ decomposes into a conditional sampling fluctuation and a latent mixture fluctuation. When this latent mixture is $\sigma_{\mathrm{mix}}^2$-subgaussian, we establish a concentration inequality with an effective variance proxy of $\frac{1}{4}\sum_i c_i^2 + \sigma_{\mathrm{mix}}^2$. Crucially, we demonstrate that for zero-sum linear contrasts, such as the difference between a subsample mean and a full population mean, the latent mixture term cancels exactly. This cancellation yields a tight, mixture-free Hoeffding-type bound that provides a direct de Finetti mechanism for the infinite-extendibility limit of recent finite-exchangeable concentration results. We apply this framework to quantify uncertainty in composite AI benchmarks, such as MMLU, where question items naturally exhibit exchangeable dependence across domains. Our results provide both a domain-stratified hierarchical model for bounding the uncertainty of accuracy scores, and a distribution-free, cost-saving statistical guarantee for accurately estimating full benchmark scores from random subsets.

09.
arXiv (CS.LG) 2026-06-16

Understanding Latent Diffusability via Fisher Geometry

arXiv:2604.02751v2 Announce Type: replace Abstract: Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate of change of the Minimum Mean Squared Error (MMSE) along the diffusion trajectory. Our framework decomposes this MMSE rate into contributions from Fisher Information (FI) and Fisher Information Rate (FIR). We demonstrate that while global isometry ensures FI alignment, FIR is governed by the interplay between encoder and data geometries. Our analysis decouples diffusion degradation into four penalties: dimensional compression, tangential distortion, high-frequency encoder curvature, and intrinsic data curvature. We derive theoretical conditions for FIR preservation to ensure stable diffusability. Experiments across diverse autoencoding architectures demonstrate the implications of our theoretical bounds. We establish FI and FIR as a comprehensive analytical framework for understanding latent diffusability.

10.
medRxiv (Medicine) 2026-06-17

Cardio Heart Connect: Protocol for a Randomized Trial of a Commercially Available mHealth Fitness Intervention for Cardiac Rehabilitation After Transcatheter Aortic Valve Replacement

Background: Despite ample evidence of the benefits of cardiac rehabilitation (CR), few transcatheter aortic valve replacement (TAVR) patients participate. Commercially available mobile health offers an opportunity to deliver activity-promotion content to populations that are challenged to participate in CR. This study aims to test the efficacy of clinically controlled, commercially available fitness programming for improving physical activity and cardiovascular health outcomes designed to be initiated while patients are on waitlists for traditional CR. Methods: The Cardio Heart Connect study is a hybrid type I effectiveness-implementation trial aiming to enroll N=200 patients who have been placed on a cardiac rehab waitlist following a TAVR procedure from the University of Colorado Hospital Heart and Vascular Center. Participants will be randomized 1:1 to the Cardio Heart Connect intervention with commercially available fitness or attention control, designed to control for technology access. At baseline, post-intervention (8 weeks), and follow-up (12 months), we will assess the primary outcome of participants? daily steps as measured by smartwatch accelerometer and secondary outcomes of interest including functional capacity (Duke Activity Status Index; VO2max), quality of life (Kansas City Cardiomyopathy Questionnaire), and cardiovascular health status (Life Essential 8). In addition, we will use mixed methodologies to evaluate the implementation of intervention using the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) Framework. Conclusions: Commercially available fitness programs have the potential to provide more accessible opportunities for patients recovering from TAVR to engage in physical activity and may be preferred due to their customizability, convenience, and ease of scheduling. Overall, this study will provide insight into the use of commercial mHealth to promote activity following TAVR.

11.
arXiv (CS.CV) 2026-06-15

GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structural Magnetic Resonance Imaging (sMRI) has emerged as a key modality for detecting AD-related brain changes, but traditional graph-based approaches often struggle with modality and inter-site heterogeneity, limiting diagnostic performance. In this paper, we propose Graph Matching Network for Alzheimer's Disease Diagnosis (GMN4AD), designed to model interactions between heterogeneous brain graphs derived from neuroimaging data. Unlike conventional methods that treat each brain graph independently, GMN4AD leverages graph matching to capture cross-graph relationships, enhancing diagnostic precision. Furthermore, we introduce a test-time domain adaptation strategy that combines contrastive learning to mitigate domain shifts during inference. Extensive experiments on three public AD datasets demonstrate that GMN4AD achieves superior performance compared to state-of-the-art methods, offering a robust and generalizable solution for AD diagnosis.

12.
arXiv (CS.CL) 2026-06-18

Written by AI, Managed by AI: Semantic Space Control and Index Sickness Elimination Across 391 Consecutive Sessions

The prevailing engineering intuition for addressing conceptual drift in long-horizon LLM collaboration is to trade more formal constraints for more reliable outputs – designing symbolic identifier systems, accumulating defensive rules in System Prompts, expanding context windows. Our engineering record shows that in long-horizon settings, this direction may produce effects contrary to design intent. Using action research methods in a real software project (Bang-v3) spanning approximately one month and 391 collaborative sessions, we document and analyze the failure process of these strategies. When the symbolic system exceeds a complexity threshold, LLMs do not become more accurate – instead, they abandon genuine understanding of business semantics, retreat to self-referential reasoning within the symbolic layer, and generate outputs that appear internally consistent but are physically disconnected from reality. We name this failure pattern "Index Sickness," and its canonical manifestation "Phantom Legislation." We name the underlying principle the "Pang Principle (Semantic Vitality Law)": natural language carrying explicit purpose conveys far greater information quality than symbolic expression. From this, we design and validate its physical engineering mechanism: "Baseline-Log Physical Separation." In the same project, this mechanism reduced AI Instructions volume by ~75%, and across the subsequent ~150 sessions, no recurrence of Index Sickness was observed. A bilingual companion version (Chinese) is included as supplementary material.

13.
arXiv (CS.CV) 2026-06-16

MapDream: Task-Driven Map Learning for Vision-Language Navigation

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that maps should instead be learned representations shaped directly by navigation objectives rather than exhaustive reconstructions. Based on this insight, we propose MapDream, a map-in-the-loop framework that formulates map construction as autoregressive bird's-eye-view (BEV) image synthesis. The framework jointly learns map generation and action prediction, distilling environmental context into a compact three-channel BEV map that preserves only navigation-critical affordances. Supervised pre-training bootstraps a reliable mapping-to-control interface, while the autoregressive design enables end-to-end joint optimization through reinforcement fine-tuning. Experiments on R2R-CE and RxR-CE achieve state-of-the-art monocular performance, validating task-driven generative map learning.

14.
arXiv (CS.CV) 2026-06-18

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical interactions, and synthesize realistic futures. We argue that 3D points in world coordinates provide a general representation that is class-agnostic, view-stable, compact, and directly useful for downstream tasks. We formalize the task of goal-conditioned 3D point motion forecasting: given a short visual history, a set of 3D query points on an object of interest, and a language description of the intended goal, the model predicts the future 3D trajectory of each point. We introduce a full stack to study this task at scale: (1) MolmoMotion-1M is a large corpus of action-described, object-grounded 3D point trajectories annotated from 1.16M unconstrained videos; (2) PointMotionBench is a human-verified benchmark spanning 111 object categories and 61 motion types; and (3) MolmoMotion is a general motion forecasting model that supports both autoregressive coordinate prediction and flow-matching-based trajectory generation. MolmoMotion accurately predicts diverse motion patterns with different language instructions, and significantly outperforms existing motion prediction baselines on PointMotionBench. Finally, we show that the learned 3D motion prior transfers well to downstream applications: it improves training efficiency and generalization for robot manipulation, and its predicted trajectories provide effective motion guidance for generative models to synthesize videos with more realistic object motion.

15.
arXiv (CS.AI) 2026-06-16

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

arXiv:2606.14817v1 Announce Type: cross Abstract: This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG). The proposed architecture consists of four modules: Input, RAG, Generation, and Judging and enables users to specify both a question and a target reading content complexity. RAG is employed to retrieve relevant information from the Internet, enriching and grounding the content produced by three modern LLMs: Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B. Reading materials are generated using three prompting strategies (Chain-of-Thought, zero-shot, and few-shot), and the LLM-as-a-Judge module automatically evaluates answer quality and alignment with the desired readability level. Experimental results show that RAG consistently improves system performance across all models and prompting techniques, increasing relevance and particularly groundedness by up to 26-35 percentage points. Overall, the findings demonstrate that the RAG-augmented architecture effectively produces reading content tailored to user queries and desired textual complexity.

16.
arXiv (CS.CV) 2026-06-18

Performance Gap Analysis between Latin and Arabic Scripts HTR

Recent studies have shown that handwritten text recognition (HTR) systems perform worse on Arabic-script datasets than on Latin-script data. However, the reasons for this gap are still not well understood due to the lack of controlled comparisons. In this work, we present a comprehensive study of Arabic and Latin scripts HTR using a unified CRNN model for line-level HTR across nine datasets (including KHATT (Arabic), Muharaf (Arabic), NUST-UHWR (Urdu), PHTD (Persian), IAM (English), READ-2016 (German), and others) and di ferent training sizes (K in {100, 500, 1000, 2000, ..., Kfull}). Our results show the performance gap remains: it is large in low-resource settings, decreases with more data, but remains even at full scale, with a consistent difference of 5-7 CER points. We show that annotation quality matters, as many datasets contain labeling errors. Cleaning reduces error rates and narrows the gap, but does not eliminate it. In addition, we find that a fixed number of training samples provides less effective coverage in Arabic due to higher visual variability, requiring more data to learn similar representations. We compare recognition across datasets in terms of the number of text lines and the number of characters, showing an equivalence trade-off. We compare character frequency distributions across scripts and show that Arabic is significantly more heavy-tailed than Latin. Our error analysis reveals that around 30 percent of substitution errors in Arabic datasets (e.g., KHATT) are caused by confusion between visually similar characters, compared to about 15 percent in Latin-script datasets such as IAM.

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

ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling

Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders result in excessively long sequences, motivating recent work on syllable-like units. However, methods like Sylber and SyllableLM rely on intricate multi-stage training pipelines. We propose ZeroSyl, a simple training-free method to extract syllable boundaries and embeddings directly from a frozen WavLM model. Using L2 norms of features in WavLM's intermediate layers, ZeroSyl achieves competitive syllable segmentation performance. The resulting segments are mean-pooled, discretized using K-means, and used to train a language model. ZeroSyl outperforms prior syllabic tokenizers across lexical, syntactic, and narrative benchmarks. Scaling experiments show that while finer-grained units are beneficial for lexical tasks, our discovered syllabic units exhibit better scaling behavior for syntactic modeling.

18.
arXiv (CS.CV) 2026-06-16

MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition

To effectively leverage user-specific data, retrieval augmented generation (RAG) is employed in multimodal large language model (MLLM) applications. However, conventional retrieval approaches often suffer from limited retrieval accuracy. Recent advances in multi-vector retrieval (MVR) improve accuracy by decomposing queries and matching against segmented images. They still suffer from sub-optimal accuracy and efficiency, overlooking alignment between the query and varying image objects and redundant fine-grained image segments. In this work, we present an efficient scheduling framework for image retrieval - MIRAGE. First, we introduce a novel hierarchical paradigm, employing multiple intermediate granularities for varying image objects to enhance alignment. Second, we minimize redundancy in retrieval by leveraging cross-hierarchy similarity consistency and hierarchy sparsity to minimize unnecessary matching computation. Furthermore, we configure parameters for each dataset automatically for practicality across diverse scenarios. Our empirical study shows that, MIRAGE not only achieves substantial accuracy improvements but also reduces computation by up to 3.5 times over the existing MVR system.

19.
arXiv (CS.AI) 2026-06-16

Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking

arXiv:2603.22376v2 Announce Type: replace-cross Abstract: We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform – pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded $+0.118\%$ over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional $+0.083\%$, for a combined $+0.201\%$ offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals – unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules – are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned.

20.
arXiv (CS.AI) 2026-06-12

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents

arXiv:2606.13097v1 Announce Type: cross Abstract: Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key-value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving 18.31% higher task success rate and 2.3x faster policy synthesis.

21.
arXiv (CS.AI) 2026-06-18

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

arXiv:2604.13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we argue that this delay reflects limited access to already learned structure rather than failure to acquire that structure in the first place. We study one-step Collatz prediction and find that the encoder organizes parity and residue structure within the first few thousand training steps, while output accuracy remains near chance for tens of thousands more. Causal interventions support the decoder bottleneck hypothesis. Transplanting a trained encoder into a fresh model accelerates grokking by 2.75 times, while transplanting a trained decoder actively hurts. Freezing a converged encoder and retraining only the decoder eliminates the plateau entirely and yields 97.6% accuracy, compared to 86.1% for joint training. What makes the decoder's job harder or easier depends on numeral representation. Across 15 bases, those whose factorization aligns with the Collatz map's arithmetic (e.g., base 24) reach 99.8% accuracy, while binary fails completely because its representations collapse and never recover. The choice of base acts as an inductive bias that controls how much local digit structure the decoder can exploit, producing large differences in learnability from the same underlying task.

22.
arXiv (CS.LG) 2026-06-12

How Reliable are Fairness Audits with Unreliable Data?

arXiv:2506.23033v3 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment. Yet, audit-recommendation reliability under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement already present under complete labels. Across ACS/Folktables tasks, missingness settings that retain some protected labels usually do not move selected mitigation methods beyond a complete-label seed-to-seed baseline. At $0%$ protected-label access, candidates collapse to an empirical-risk-minimization baseline and deterministic tie-breaking rather than revealing a broad missingness effect. We also found that threshold optimization can turn fairness gains on a single protected axis into intersectional harm above a seed baseline, and this threshold-optimizer finding persists under random-forest validation. Overall, our results highlight that protected-label missingness should be reported with seed-null calibration, candidate-set context, and intersectional consequences before it is treated as evidence of audit fragility.

23.
arXiv (CS.LG) 2026-06-12

Towards Provably Fair Machine Learning: Bayesian Approaches For Consistent and Transparent Predictions

arXiv:2606.12615v1 Announce Type: new Abstract: ML classifiers deployed in high-stakes domains produce predictions whose quality varies systematically across subgroups. For granular subgroups defined by intersections of multiple features, predictions are often inconsistent with the observed data: the model's outputs contradict the evidence available for that subgroup. This problem is exacerbated by regularisation, which improves aggregate performance by collapsing small subgroups into larger groups, disproportionately affecting demographic minorities. We define two requirements for consistent prediction: determinism (identical individuals receive identical predictions) and statistical consistency (we cannot reject, at significance level alpha, the hypothesis that the predictions for a subgroup were drawn from the Bayesian optimal target distribution inferred for that subgroup). From these requirements we derive the Fair Bayesian classifier, which enforces both across every group and subgroup simultaneously and abstains whenever no consistent deterministic prediction is possible. On three benchmark datasets (Adult, COMPAS, and Bank Marketing), standard classifiers produce statistically inconsistent predictions for a substantial proportion of subgroups. Our classifier achieves zero consistency error by construction while exceeding baseline accuracy and multicalibration on every dataset tested. Statistical consistency provides a principled foundation for prediction quality with direct implications for algorithmic fairness. Minority demographics are disproportionately concentrated in small subgroups, precisely where frequentist inference is least reliable; addressing this inference problem is therefore a necessary step toward fair ML. By enforcing Bayesian consistency at the finest resolution the data supports, the our classifier demonstrates that exhaustive subgroup fairness with principled abstention is achievable in practice.

24.
arXiv (CS.LG) 2026-06-15

BigPower: Hierarchical Source-Level Module Power Estimation for CPUs with Large Language Models

arXiv:2606.13747v1 Announce Type: cross Abstract: Accurate power estimation is important for understanding and optimizing CPU power behavior, yet practical workflows often rely on simulation-derived information or post-silicon analysis. In this work, we present BigPower, a hierarchical source-level surrogate model for fine-grained module-level power estimation during CPU design. BigPower leverages large language model-based representations together with architectural hierarchy, module connectivity, configuration parameters, and workload context to estimate module-level power consumption directly from source-level design information, without requiring additional simulation during inference. Experimental results in the open-source XiangShan processor family demonstrate practical fine-grained power estimation across diverse configurations and workloads, offering an efficient alternative to conventional simulation-based workflows.

25.
arXiv (CS.CV) 2026-06-11

MedCTA: A Benchmark for Clinical Tool Agents

To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Existing benchmarks largely evaluate isolated perception or single-turn question answering, and therefore provide limited visibility into failures of planning, tool recruitment, and rollout reliability. We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks grounded in realistic multimodal clinical inputs, including radiology images, pathology slides, and reports. MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools, and supports process-aware evaluation of tool selection, argument validity, execution stability, trajectory fidelity, and outcome quality. We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use: autonomous rollouts are dominated by protocol failures, premature stopping, and incorrect tool recruitment, while gold-standard tool routing yields large but still incomplete gains. These results show that strong backbone perception does not translate into reliable agentic behavior in clinical settings. MedCTA provides a rigorous testbed for auditing, diagnosing, and advancing trustworthy medical AI agents. The dataset and evaluation suite are available at https://ivul-kaust.github.io/MedCTA/