Ten simple rules for writing a peer review
by Farzana Rahman, Dan DeBlasio
Academic Intelligence · Curated Daily
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.
by Farzana Rahman, Dan DeBlasio
arXiv:2601.08782v2 Announce Type: replace Abstract: Bosonic codes constitute a promising route to fault-tolerant quantum computing. Existing Floquet protocols enable analytical construction of bosonic codes but typically rely on slow adiabatic ramps with thousands of driving periods. In this work, we circumvent this bottleneck by introducing an analytical and deterministic Floquet method that directly synthesizes arbitrary unitaries within a single period. The phase-space unitary ensembles generated by our approach reproduce the Haar-random statistics, enabling practical pseudorandom states in continuous-variable systems. We prepare various prototypical bosonic codes from vacuum and implement single-qubit logical gates with high fidelities using quantum lattice gates. By harnessing the full intrinsic nonlinearity of Josephson junctions, quantum lattice gates decompose quantum circuits into primitive operations for efficient continuous-variable quantum computing.
arXiv:2604.06802v2 Announce Type: replace Abstract: Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competition-style problem solving. However, competition mathematics represents only a narrow slice of mathematical reasoning: problems are drawn from limited domains, require minimal advanced machinery, and can often reward insightful tricks over deep theoretical knowledge. We introduce Riemann-Bench, a private benchmark of expert-curated problems designed to evaluate AI systems on research-level mathematics that goes far beyond the olympiad frontier. Problems are authored by Ivy League mathematics professors, graduate students, and PhD-holding IMO medalists, and routinely took their authors weeks to solve independently. Each problem undergoes double-blind verification by two independent domain experts who must solve the problem from scratch, and yields a unique, closed-form solution assessed by programmatic verifiers. We evaluate frontier models as unconstrained research agents, with full access to coding tools, search, and open-ended reasoning, using an unbiased statistical estimator computed over 100 independent runs per problem. Our results reveal that all frontier models currently score below 10%, exposing a substantial gap between olympiad-level problem solving and genuine research-level mathematical reasoning. By keeping the benchmark fully private, we ensure that measured performance reflects authentic mathematical capability rather than memorization of training data.
arXiv:2606.15504v1 Announce Type: new Abstract: In recent years, the advances of large language models and autonomous agents have revolutionized the healthcare field, facilitating diagnosis and improving treatment results. However, most existing AI systems rely on pre-trained knowledge and predefined pipelines, which struggle to learn dynamically from the interactive chat session history that contains patient outcomes and past failures. To address this limitation, we propose VIBEMed, a multi-agent framework with a built-in self-evolution mechanism and architecture-level safety sandbox for robust clinical decision support. The system integrates three specialized agents, including a Clinical Diagnostic Agent (CDA) for hypothesis generation, a Therapeutic Execution Agent (TEA) for treatment planning, and a Clinical Evolution Manager Agent (CEMA) that distills longitudinal clinical feedback into reusable knowledge, transforming multimodal patient information into personalized medical decisions. Through self-evolution mechanism, the framework enables iterative updates across memory, model behavior, and decision strategies, allowing the system to improve over time. Experimental results show that VIBEMed demonstrates superior performance through its evolving mechanism in complex clinical cases, particularly in tasks that require integrated decision-making and longitudinal planning. The framework also supports reliable end-to-end decisions in challenging scenarios such as oncology treatment planning, highlighting its feasibility in real-world clinical contexts. Overall, VIBEMed provides a practical path beyond static AI systems toward adaptive, experience-driven clinical decision support, demonstrating the value of combining multi-agent collaboration with continuous evolution for advancing precision medicine.
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.
arXiv:2502.19193v2 Announce Type: replace-cross Abstract: Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Language Models (LLMs) to simulate the iterative evolution of language strategies under regulatory constraints. In this framework, participant agents, as social media users, continuously evolve their language expression, while supervisory agents emulate platform-level regulation by assessing policy violations. To achieve a more faithful simulation, we employ a dual design of language strategies (constraint and expression) to differentiate conflicting goals and utilize an LLM-driven GA (Genetic Algorithm) for the selection, mutation, and crossover of language strategies. The framework is evaluated using two distinct scenarios: an abstract password game and a realistic simulated illegal pet trade scenario. Experimental results demonstrate that as the number of dialogue rounds increases, both the number of uninterrupted dialogue turns and the accuracy of information transmission improve significantly. Furthermore, a user study with 40 participants validates the real-world relevance of the generated dialogues and strategies. Moreover, ablation studies validate the importance of the GA, emphasizing its contribution to long-term adaptability and improved overall results.
arXiv:2606.15276v1 Announce Type: cross Abstract: We study collapsibility in the multiparametric models of random simplicial complexes, namely the lower and upper models. In the upper model, we improve upon a result of Farber and Nowik, and assert that the homology is a.a.s concentrated in a single dimension by proving that the complex collapses to that \di. In the lower model, we prove that the complex a.a.s collapses to the \di\ with maximal non-trivial cohomology. We then compare this threshold to the ones derived previously for the special cases of the clique complex (by Kahle) and the Linial-Meshulam model.
arXiv:2502.10502v3 Announce Type: replace-cross Abstract: Since the advent of quantum mechanics, classical probability interpretations have faced significant challenges. A notable issue arises with the emergence of negative probabilities when attempting to define the joint probability of non-commutative observables. In this work, we propose a resolution to this dilemma for quantum spin chains, by introducing an exact representation of their dynamics in terms of classical continuous-time Markov chains (CTMCs). These CTMCs effectively model the creation, annihilation, and propagation of pairs of classical particles and antiparticles. The quantum dynamics then emerges by averaging over various realizations of this classical process.
arXiv:2606.18726v1 Announce Type: cross Abstract: Structurally constrained event sequence generation remains challenging because generated paths must preserve transition feasibility, temporal order, termination, and attribute consistency. In predictive process monitoring (PPM), this challenge appears as full event sequence generation, whereas existing work mainly addresses component tasks such as next activity, remaining time, outcome, and attribute prediction. This paper proposes the Graph Grounded Cross Attention Transformer Neural Network (GGATN) for this unified PPM task. GGATN uses a global process graph as structured activity memory, contextualizes sequence positions through Transformer self attention, and injects process topology through graph grounded cross attention. Unlike autoregressive decoding, GGATN generates activities, timestamps, length, and event level and sequence level attributes in a single pass, followed by Viterbi style graph constrained decoding for feasible paths and explicit termination. Experiments on six benchmark event logs show more reliable generation quality than local instruction prompted LLM baselines. GGATN achieves strong performance on sequence similarity, Damerau Levenshtein similarity, bigram based control flow similarity, and duration distribution, while maintaining zero hallucinated activities and zero sequence level attribute inconsistency. Ablation analyses confirm the global graph encoder as a stable structural prior. Interpretability analyses show how graph structure, sequence context, feedback refinement, and constrained decoding shape generation.
arXiv:2507.09839v2 Announce Type: replace Abstract: An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model behavior. Recent Automatic Prompt Optimization (APO) methods iteratively refine prompts using model-generated critiques (often called textual gradients), but they predominantly optimize from failures and underutilize information contained in correct predictions, leading to instability and semantic drift. We propose TRAS (Textual Regularization with Aggregated Signals), a feedback-centric framework that is plug-and-play with existing APO search backbones. It retains the standard textual gradient signal from prior work for error correction and introduces a complementary textual regularizer derived from successful predictions to preserve beneficial prompt components. Because both signals are stochastic and can be noisy, we further introduce Monte Carlo Signal Aggregation (MCSA), which samples multiple gradients or regularizers and aggregates them into a single actionable directive, emphasizing consistent, actionable advice while filtering out outliers. Motivated by rapid model churn, we also formalize Automatic Prompt Migration (APM), the practical problem of adapting an expert prompt across model versions or API providers without losing critical instructions. Across standard APO and APM scenarios, our approach consistently outperforms strong baselines, yielding higher accuracy, faster convergence, and lower query cost, while substantially reducing the degradation observed under naive prompt migration.
Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.
Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.
by Gabriela Lima de Melo Ghisi, Rachael P. Carson, Karam Turk Adawi, Rongjing Ding, Warner M. Mampuya, Mariya P. Jiandani, Jimena Martinez, Monserrat Cruz Rivero, Claudia V. Anchique, Dinah L. van Schalkwijk, Jonathan Gallagher, Buket Akinci, Dion Candelaria, Jirapa Champaiboon, Daniel F. Quesada-Chaves, Tone M. Norekvål, Iwona Szadkowska, Borut Jug, Evangelia Kouidi, Marta Supervia, Won-Seok Kim, Chamila Mettananda, Lilian Mbau, Gulsim T. Aimakova, Sherry L. Grace, on behalf of the ICCPR Global Cardiac Rehabilitation Audit Update Investigators Background Cardiovascular disease (CVD) remains a leading global health burden. Cardiac rehabilitation (CR) is essential to reducing morbidity and improving patient outcomes. Since the COVID-19 pandemic, CR delivery worldwide has evolved, yet these changes have not been systematically charactemkjrized. The objective of this study was to characterize globally: (1) the delivery of core CR components, including risk factors assessed, patient education practices, and program resources; (2) differences in these elements by country income classification and relative to the initial 2016 Global CR Audit. Methods and findings A cross-sectional Audit update was conducted. Program-level data were collected from May 1st to September 1st 2025 using a REDCap survey adapted from previous Audits. Eligible respondents were leads of phase II/post-discharge CR programs providing at least an initial assessment, structured aerobic exercise, and ≥1 additional core component. ICCPR associations and local leaders supported program identification. Main outcomes were core components delivered (10 assessed), risk factors assessed (14 assessed), patient education dose (hours/patient/program), and program resources (17 assessed). Generalized linear mixed models (GLMM) tested differences by income classification and (when applicable) changes since 2016. Of 7,025 programs identified globally, 1,505 (62% median country response rate) initiated a survey from 90/113 (80%) countries with CR. The median number of core components offered was 8/program (p25, p75 = 6, 10), with upper-middle income countries offering significantly more components overall (median = 9), and also high-income countries offering more than low-income countries (8 versus 6, p
While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.
arXiv:2511.14555v4 Announce Type: replace-cross Abstract: Decoded Neurofeedback (DecNef) is a promising non-invasive approach to brain modulation with wide-ranging applications in neuromedicine and cognitive neuroscience. However, progress in DecNef research remains constrained by subject-dependent learning variability, reliance on indirect measures to quantify progress, and the high cost and time demands of experimentation. We present DecNefSimulator, a modular and interpretable simulation framework that formalizes DecNef as a machine learning problem. Beyond providing a virtual laboratory, DecNefSimulator enables researchers to model, analyze and understand neurofeedback dynamics. Using latent variable generative models as simulated participants, DecNefSimulator allows direct observation of internal cognitive states and systematic evaluation of how different protocol designs and subject characteristics influence learning. We demonstrate how this approach can (i) reproduce empirical phenomena of DecNef learning, (ii) identify conditions under which DecNef feedback fails to induce learning, and (iii) guide the design of more robust and reliable DecNef protocols in silico before human implementation. In summary, DecNefSimulator bridges computational modeling and cognitive neuroscience, offering a principled foundation for methodological innovation, robust protocol design, and ultimately, a deeper understanding of DecNef-based brain modulation.
A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code.
arXiv:2606.15096v1 Announce Type: new Abstract: The Riemann Hypothesis remains one of the central unsolved problems in mathematics. Rather than claiming proof, we investigate whether a verifiable AI-assisted reasoning system can produce reliable, formally checked partial progress while explicitly identifying the remaining mathematical obstructions. We apply the Verifiable Growing Physical Transformer with Recursive Self-Improvement (VGPT-RSI) to two RH-adjacent certification tasks. First, we construct and verify a finite RH-boundary certificate for inequality on a parameterized safe lower curve over a region. The numerical boundary curve is converted into a certificate-backed lower curve, audited using outward-rounded interval arithmetic and Arb/FLINT ball arithmetic, and then checked in Rocq/CoqInterval for the parameterized theorem. Second, we initiate a formal Lagarias-route certificate. Lagarias criterion states that RH is equivalent to the global inequality. We formalize the finite quantity and produce a Coq-checked finite certificate. The final system identifies the exact unresolved mathematical bottlenecks: formalizing the Lagarias equivalence, proving the global tail theorem beyond any finite cutoff, and potentially reducing counterexamples to colossally abundant or related extremal integers. These results demonstrate that VGPT-RSI can produce certified RH-adjacent formal progress, organize proof dependencies, and avoid overclaiming when the remaining obstruction is genuinely mathematical.
arXiv:2606.15693v1 Announce Type: cross Abstract: LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks involving programs such as TikZ that generate visual artifacts remain challenging, in particular on visual code customization. Unlike generation from scratch, customization requires localized, semantics-preserving edits: the model must locate relevant code, modify it according to the instruction, and preserve the remaining structure and rendering. Approaches based on post-hoc iterative refinement/correction where a verifier provides feedback to guide corrections, have shown promise. However, in the case of programs with a visual outcome such as in TikZ, where correctness is harder or likely impossible to formalize and evaluate automatically, deterministic verifiers do not exist. Hence, developers can only rely on imperfect verifiers. In this paper, we conduct an empirical study to answer:to what extent can iterative refinement remain effective when the verifier itself is unreliable?} We use TikZ as a focused case study that isolates the core difficulties of the problem (weak code structure, fine-grained visual semantics, and difficult feature localization) in a controlled and challenging setting. We define visual code customization as an iterative editing problem with an imperfect oracle, and introduce a framework for analyzing such iterative refinements. We conduct a large-scale study and evaluate multiple LLM-based and tool-augmented visual verifiers within iterative refinement pipelines, and perform extensive manual annotation of refinement trajectories to assess verifier behavior and feedback quality. Our findings show that even imperfect verifiers can determine with moderate accuracy whether visual instructions are applied to code, achieving F1-scores up to 0.815. Feedback improves iterative refinement, especially for weaker models, adding 11–20 perfect customizations for Qwen3-vl-30b-a3b-Instruct, while stronger models like Gemini-3 gain fewer improvements (+5) but benefit more from accurate verification that prevents premature acceptance. Feedback is effective only when it precisely identifies image issues, provides actionable guidance, addresses all relevant problems, and remains grounded in the original instruction.
arXiv:2601.03035v2 Announce Type: replace Abstract: This is a set of lectures on tensor networks with a strong emphasis on the core algorithms involving Matrix Product States (MPS) and Matrix Product Operators (MPO). Compared to other presentations, particular care has been given to disentangle aspects of tensor networks from the quantum many-body problem: MPO/MPS algorithms are presented as a way to deal with linear algebra on extremely (exponentially) large matrices and vectors, regardless of any particular application. The lectures include well-known algorithms to find eigenvectors of MPOs (the celebrated DMRG), solve linear problems, and recent learning algorithms that allow one to map a known function into an MPS (the Tensor Cross Interpolation, or TCI, algorithm). The lectures end with a discussion of how to represent functions and perform calculus with tensor networks using the "quantics" representation. They include the detailed analytical construction of important MPOs such as those for differentiation, indefinite integration, convolution, and the quantum Fourier transform. Three concrete applications are discussed in detail: the simulation of a quantum computer (either exactly or with compression), the simulation of a quantum annealer, and techniques to solve partial differential equations (e.g. Poisson, diffusion, or Gross-Pitaevskii) within the "quantics" representation. The lectures have been designed to be accessible to a first-year PhD student and include detailed proofs of all statements.
No abstract for this item (typically a correction, editorial or news piece — the publisher provides none)
Remote sensing visual grounding (RSVG) aims to localize a referred target in a remote sensing image or video according to a natural language expression. Existing RSVG methods usually rely on task-specific manual annotations, which are costly to collect and inevitably limited in covering the diversity of real-world geospatial scenarios. As a result, they often struggle to generalize to open-vocabulary queries involving novel objects, fine-grained attributes, complex spatial relationships, and functional semantics. In this paper, we propose RSVG-ZeroOV, a training-free framework that leverages frozen generic foundation models for zero-shot open-vocabulary RSVG. RSVG-ZeroOV follows an Overview-Focus-Evolve paradigm, which exploits the distinct yet complementary attention patterns of vision-language models (VLMs) and diffusion models (DMs) to progressively generate precise grounding results. Specifically, (i) Overview utilizes a VLM to extract cross-attention maps that capture semantic correlations between the referring expression and visual regions; (ii) Focus leverages the fine-grained modeling priors of a DM to compensate for object structure and shape information often overlooked by VLM attention; and (iii) Evolve introduces a simple yet effective attention evolution module to suppress irrelevant activations, yielding purified object masks. To handle video inputs, we further present Video RSVG-ZeroOV, which extends image-level grounding to spatio-temporal grounding through a query-relevant key-frame selector and a temporal propagator, enabling efficient and temporally coherent video grounding without video annotations or fine-tuning. Extensive experiments on six image and video grounding benchmarks show that RSVG-ZeroOV consistently outperforms existing zero-shot baselines and achieves competitive or superior performance compared with weakly- and fully-supervised methods.
Camera-trap monitoring in African tropical forests increasingly extends beyond closed-canopy interiors to riverbanks, clearings, and park edges. Among available open tools for African forest camera-trap classification, DeepForestVision is the only one providing a matched offline workflow for both photographs and videos, and previous work showed that it outperformed other available baselines on a comparable benchmark. However, it was designed for closed-canopy, ground-level forest interiors and uses a 35-class prediction space that becomes too coarse when deployments encounter arboreal primates, birds, semi-aquatic taxa, or human-associated confounders such as livestock. We present DeepForestVisionV2, an ecology-driven expansion from 35 to 64 prediction classes (61 animal classes plus human, vehicle, and blank) designed to address three recurrent deployment gradients: vertical stratification, scene openness, and anthropogenic interfaces. DeepForestVisionV2 retains the same offline workflow and is trained on 1,535,010 photographs and 243,354 videos from multi-country African tropical-forest projects. Evaluation combines a cross-country cropped-photo validation set, used to assess robustness across sites and camera-trap settings, with three held-out Uganda video benchmarks spanning the targeted gradients. On the validation set, DeepForestVisionV2 reaches 0.86 accuracy, 0.82 macro-F1, and 0.81 balanced accuracy. On the deployment benchmarks, it preserves or improves baseline accuracy despite its harder classification task, while increasing the number of identified taxa from 22 to 29 in forest-interior videos and from 4 to 9 at riverbanks. In the park-edge use case, it raises accuracy from 0.62 to 0.86 and reduces false alarms from 11 to 0. These results show that DeepForestVisionV2 materially improves field utility while preserving robustness across sites, habitats, and camera-trap settings.
arXiv:2606.25092v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages. We test this causally on Command A+, a frontier open-weights MoE (218B total / 25B active; 128 experts, 8 active, +1 shared). We build a routing-mass atlas, pre-register six family-to-axis hypotheses before any intervention, and ablate each family at inference time against a size-matched random-expert null, measuring whether it selectively breaks its own axis (worst off-target effect at most one third of on-target). Crucially, we test the same families under four metrics and a held-out, independent-corpus run with bootstrap confidence intervals. Our finding is cautionary: robust functional modularity is rare and measurement-dependent. Of six pre-registered families, only one, the Arabic-language family, is a clean selective module that survives an independent corpus and a conservative statistical bar (1/6; a more permissive pre-registered point rule admits 3/6, but that count is threshold-sensitive). Every other family has a real causal effect yet fails selectivity, and its apparent modularity flips with the measurement: with the corpus, the metric, and the statistical bar. A positive control on Qwen3-30B-A3B recovers its published disjoint structure, confirming the method detects modularity when present. The verdict reproduces on the un-quantized BF16 model, ruling out a 4-bit quantization artifact. We conclude that ablation-based modularity verdicts are not safe unless the corpus, metric, and statistical bar are controlled. We release the atlas and ablation data.
arXiv:2606.03077v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a standard post-training paradigm for shaping large language models (LLMs) into capable agents. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that expose two fundamental challenges in resource management. First, due to the long-tail distribution, a small fraction of trajectories dominates rollout makespan. Second, rollout and training are subject to cross-stage imbalance, as they exhibit strong asymmetry in compute patterns, memory demands, and sensitivity to sequence length. Compounding this asymmetry, the sequence length distribution drifts continuously as the policy evolves, rendering any static resource split progressively suboptimal. We present Libra, a resource management system to address both challenges via two core mechanisms. The first is a global resource planner that jointly optimizes GPU allocation across rollout and training clusters. It leverages an elastic hybrid pool to enable lightweight, non-blocking worker reallocation between stages. The second is a causality-driven multi-level feedback queue (C-MLFQ) scheduler, which routes requests to heterogeneous rollout buckets based on causal signals derived from tool-return outcomes, rather than relying on fragile length predictions. Evaluated on 48 A800 GPUs, Libra achieves up to 3.0x higher throughput and converges up to 2.5x faster in reward compared to the baselines.
Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable fine-tuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 "Cortonese") and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis