论文广场 - AcademicHub

01.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.16741

Scalable generation of heralded single photons via active feed-forward switching of a fiber delay line

作者:

Xavier Barcons Planas ↗Helen M. Chrzanowski ↗Janik Wolters ↗

arXiv:2606.16741v1 Announce Type: new Abstract: Quasi-deterministic single-photon generation is a key requirement for many photonic quantum technologies. Photon sources based on spontaneous parametric down-conversion (SPDC) are widely used for producing high-quality photons; however, the probabilistic nature of the process limits the generation of synchronized multi-photon states. Here, we demonstrate temporal synchronization of multiple photon-generation events using a free-space-fiber hybrid delay line with feed-forward control, enabling fast and efficient switching and scalable operation. Narrow-band, telecom-wavelength photons compatible for fiber transmission are heralded from a monolithic cavity SPDC source and synchronized across 20 time bins. This yields a sixfold enhancement in synchronized rates and enables multi-photon synchronization, with only a marginal increase of higher-order photon-number contributions.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19607

Which Pairs to Compare for LLM Post-Training?

作者:

Jiangze Han ↗Vineet Goyal ↗Will Ma ↗

arXiv:2606.19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models. A common data-collection strategy is to generate a small set of completions for each prompt and label the resulting comparison pairs. However, human preference labels are often much more expensive than generating additional completions, suggesting a different use of the same labeling budget: generate a larger pool of completions, but label only the most informative comparison pairs. This paper studies which pairs should be compared in preference-based post-training. We formulate comparison curation as a sampling-design problem and evaluate designs by the quality of the final policy under the preference-based post-training objective. We instantiate this framework for Direct Preference Optimization (DPO), analyzing how the choice of labeled pairs propagates through DPO training to downstream policy performance. Our main results provide matching upper and lower bounds on the post-training optimality gap of the DPO-trained policy. The bounds show that comparison selection affects downstream performance through a single design-dependent information matrix, which links label allocation to parameter estimation error and policy suboptimality. This yields an explicit optimization criterion for budgeted comparison curation and motivates practical sampling designs for selecting informative pairs from large generated completion pools. Experiments on synthetic settings and language-model post-training benchmarks show that the proposed designs consistently improve sample efficiency over common comparison-selection heuristics.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15621

Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation

作者:

Nils Matteson ↗

Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes. Published methods re-feed the transcript prefix as a fresh prompt, assuming this reproduces the state the model passed through during generation. We measure what that assumption costs on a stock inference engine, with a three-pass design: continuations resumed from the verified decode-time KV state, an identical second exact pass (a replica noise floor), and a re-feed pass. Across six configurations and three models (including a GRPO-trained checkpoint), at low-margin decision tokens, re-feeding changes the credit estimate at rates 14-28 percentage points above the replica floor (7-21pp under a treatment-independent conditioning; problem-clustered t = 2.9-6.4). Most changes are zero-boundary crossings of the quantized estimator rather than polarity reversals, and the perturbation is consistent with mean-zero, so averaged quantities are largely safe; but selection is not: a critical-token set chosen by thresholding $|\hat{A}_t|$ under re-feed overlaps the exact-resume selection at Jaccard 0.34-0.90, versus a 0.63-0.96 replica ceiling. A causal confirmation closes the loop: under vLLM's batch-invariant kernels all three passes are identical on every measured channel, with both disagreement rates exactly zero. Replica passes themselves disagree on 9-23% of eligible estimates: single-sample credit measurements at decision tokens are unreliable under any replay. Settings were fixed in advance; exact-pass cache hits in the second campaign are instrumented (100% hit rate, 3,434 pivots); total compute was under 10 USD. We recommend that counterfactual credit studies resume decoder state or use batch-invariant kernels, and report a replica floor.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2605.23243

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

作者:

Vivek Dahiya ↗Sunny Nehra ↗Vipul Dholariya ↗Bhavik Shangari ↗Chandra Khatri ↗

arXiv:2605.23243v2 Announce Type: replace-cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source). We test six frontier models (GPT-5.4, Codex~5.3, Claude Opus~4.6, Sonnet~4.6, Gemini~3.1~Pro and Gemini~3~Flash) and two domain-specialized models across four testing paradigms. Our findings are sobering: (1)~every frontier model produces 10-50% false positive rates in white-box detection, systematically over-predicting vulnerabilities; (2)~in black-box testing, frontier models achieve only 4-8% ground-truth coverage, improving to just 10-19% even with external security tools (Playwright MCP, Burp Suite MCP); (3)~structured penetration-testing methodology encoded in domain-specialized agents raises per-family detection above 50%, demonstrating that methodology, not scale, is the primary lever; and (4)~a domain-specialized defense model achieves the highest precision (0.904) and lowest false positive rate (9.7%) among all models, on a single GPU. We identify the absence of structured security testing traces end-to-end request/response sequences, failure-heavy data, and multi-step attack chains as the fundamental training data bottleneck, and propose self-play security testing as a data generation strategy. Our results make the case for vertical foundation models purpose-built for cybersecurity.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15892

Scalar-pathway fidelity improves physical accuracy in short-range equivariant interatomic potentials

作者:

Jia Bi ↗Alin Marin Elena ↗Samuel Pinilla ↗

arXiv:2606.15892v1 Announce Type: new Abstract: Accurate interatomic potentials enable molecular dynamics of materials, molecules, and interfaces beyond density-functional-theory length and time scales. Equivariant neural network potentials have improved the representation of local geometry. However, their deployable energy surfaces ultimately manifest through invariant scalar channels, whose aggregation and spectral resolution remain comparatively underexamined. Here we use Physics-Aware Neighborhood (PAN) pooling and Physics-Guided Spectral (PGS) mixers as controlled scalar-pathway probes: lightweight, symmetry-preserving modifications that act only on $\ell=0$ channels while leaving the equivariant tensor backbone unchanged. Using MACE as a high-body-order mechanistic scaffold, PAN adds coordination-sensitive amplitude modulation, whereas PGS augments edge and readout scalar features with radial and tapered spectral bases. Across metallic Ag, covalent Si, a short-range ionic LiF/Li–F subset, and MD17/rMD17 molecules, this scalar-pathway correction reduces MACE force errors by 22–27\% and energy errors by 19–22\%; on systems with stress labels, stress errors decrease by 27–28\%, at approximately 5\% additional inference-FLOPs cost. Directionally consistent gains in Allegro and NequIP further indicate that the correction is portable across distinct short-range equivariant backbones, although effect sizes remain architecture-dependent. These results identify scalar-pathway fidelity as a practical design dimension for short-range equivariant interatomic potentials.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15914

Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing

作者:

Ariyan Hossain ↗Kazi Kamruzzaman Rabbi ↗Farig Sadeque ↗S M Taiabul Haque ↗

Gender bias in LLMs has been studied extensively in model outputs, with biased prompts shown to amplify stereotyped generations. Whether such bias propagates into text produced by humans who use these systems, however, remains underexplored. We investigate whether gender bias in an LLM writing assistant transfers into career plan essays written by students. We first verify that a gender-biased prompt induces gender-differentiated language in LLM-generated essays, while a neutral prompt does not. We then recruited participants (N = 123) in a controlled environment to write career plan essays for paired biographical profiles differing only in gender under three conditions: no AI assistance, neutral LLM assistance, or gender-biased LLM assistance. Students in the biased condition produced essays with a significantly larger agentic gap and more gender-stereotypic occupation suggestions than those in the control and neutral conditions. Our results also reveal that this bias transfer is asymmetric: agency is suppressed in female-target essays while male-target writing remains largely unaffected. Our findings highlight the risk of bias propagation in AI-assisted writing, calling for fairness-aware design in educational AI tools.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.10820

K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

作者:

Zhiwei Tang ↗Yuanyu He ↗Yizheng Han ↗Wangbo Zhao ↗Jiasheng Tang ↗Fan Wang ↗Bohan Zhuang ↗

Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving–the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping–one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2604.13082

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

作者:

Laura Gomezjurado Gonzalez ↗

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.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.09347

IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal

作者:

Haojun Guo ↗Fan Feng ↗Ziquan Wang ↗Yongsheng Zhang ↗Ying Yu ↗

Synthetic aperture radar (SAR)-assisted optical cloud removal aims to recover surface information obscured by clouds in optical remote sensing images by exploiting complementary SAR observations. Existing multimodal fusion methods typically rely on direct spatial concatenation and pixel-wise supervision, which can propagate SAR speckle noise into optical reconstruction and lead to over-smoothed results. To address these limitations, we propose an Information Bottleneck-driven High-Fidelity Network (IB-HFN) for SAR-assisted optical cloud removal. IB-HFN employs a dual-stream backbone to preserve modality-specific representations before deep semantic fusion, thereby mitigating premature cross-modal contamination. At the fusion stage, we introduce a Spatial Information Bottleneck Fusion module that compresses SAR features through a channel-wise variational information bottleneck to suppress unstructured speckle noise. In parallel, a local-global gating mechanism predicts clear-sky regions and routes reliable optical details through a Dirac-initialized skip connection, decoupling noise suppression from texture preservation. We further develop a joint optimization strategy that integrates feature-level bottleneck regularization with image-level constraints on reconstruction accuracy, structural consistency, spectral fidelity, and contrastive sharpness. A dynamic weighting schedule balances these objectives to stabilize training and reduce hazy artifacts. Experiments on the SEN12MS-CR dataset under challenging spatio-temporal splits demonstrate that IB-HFN achieves superior structural preservation and spectral fidelity over existing methods.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19266

Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

作者:

Ikram Belmadani ↗Oumaima El Khettari ↗Carlos Ramisch ↗Frederic Bechet ↗Richard Dufour ↗Benoit Favre ↗

The development of large language models (LLMs) has led to an increased focus on their adaptation to specialized domains and languages, yet the effectiveness of domain adaptation strategies remains unclear. We present a study of medical domain adaptation using French medical question-answering (QA) as a case study. We compare continual pretraining (CPT), supervised fine-tuning (SFT), and their combination across three model families, multiple sizes, and three initialization types, explicitly disentangling adaptation effects from base model choice. We evaluate both multiple-choice (MCQA) and open-ended QA (OEQA) under greedy and constrained decoding using automatic metrics and LLM-as-a-Judge evaluation. For MCQA, CPT+SFT most often achieves the best scores, but gains over SFT are small and frequently not statistically significant, making SFT a strong and cost-effective default. For OEQA, CPT consistently improves overlap-based metrics, while SFT often degrades generation quality; instruction tuning and CPT+SFT are preferred by LLM-based evaluation. Cross-lingual experiments further show effective transfer from French adaptation to English benchmarks. Overall, we provide practical guidelines for selecting adaptation strategies under computational constraints.

阅读与讨论 → 访问原文 →

11.

medRxiv (Medicine) 2026-06-15 DOI: HASH:0ccda549d474892c12771a3a8f6c6649

Automated AI-Based Ventricular Subcompartment Segmentation and Volumetry in Idiopathic Normal Pressure Hydrocephalus

作者:

Mutke ↗M. A ↗Griot ↗S. A ↗Wasserthal ↗Indrakanti ↗A. K ↗Vishwanathan ↗Mahmutoglu ↗D'Antonoli ↗T. A ↗Bach ↗…

Purpose In idiopathic normal pressure hydrocephalus (iNPH), longitudinal monitoring of ventricular size is important for diagnosis and treatment follow-up. This study aimed to validate a fully automated AI model for CT ventricular volumetry with subcompartments and to compare AI-derived volume changes with routine radiology assessments. Methods This retrospective, single-center study included 88 patients with iNPH and 456 non-contrast-enhanced head CT examinations. The model was trained on 38 manually labeled CT scans with 12 ventricular subcompartments. Outcomes included segmentation accuracy, correspondence between AI-derived longitudinal ventricular volume changes and radiology report categories (decreased, unchanged, increased), radiologist detection thresholds for ventricular change, and paired pre- and postoperative volume changes in 22 patients with ventriculoperitoneal shunt. Results Mean segmentation accuracy was high (Dice, 0.83). 91% of 100 segmentations were rated as excellent by an expert neuroradiologist. AI-derived ventricular volume changes corresponded well to radiology report categories (median total ventricular volume changes of -17% in cases reported as decreased, 0% in unchanged cases, and +22% in increased cases; all p < 0.001). Radiologists reported ventricular volume change in 50% of cases at an AI-measured relative volume change of +/-6%, and in 90% of cases at +21% for enlargement and -18% for decrease. After shunt placement, ventricular volume decreased by -8% (median), with the largest relative reductions observed in the right temporal and occipital horns. Conclusions Automated AI-based ventricular segmentation on CT enables accurate and reproducible assessment of ventricular volume changes in iNPH and complements routine radiological evaluation for longitudinal and postoperative monitoring.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13177

MemRefine: LLM-Guided Compression for Long-Term Agent Memory

作者:

Minjae Kim ↗Jinheon Baek ↗Soyeong Jeong ↗Sung Ju Hwang ↗

Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on resource-constrained platforms with hard memory budgets, motivating us to formulate storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions. To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met. Across multiple memory frameworks and long-term conversation benchmarks, MemRefine consistently meets target budgets while preserving downstream performance and outperforming rule-based baselines under tight budgets.

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2511.20868

Tungsten Germanide Superconducting Nanowire Single-Photon Detectors with Saturated Internal Detection Efficiency at Wavelengths up to 29 {\mu}m

作者:

arXiv:2511.20868v2 Announce Type: replace-cross Abstract: Superconducting nanowire single-photon detectors (SNSPDs) are among the most sensitive single-photon detectors available and have the potential to transform fields ranging from infrared astrophysics to molecular spectroscopy. However, extending their performance into the mid-infrared spectral region - crucial for applications such as exoplanet transit spectroscopy and vibrational fingerprinting of molecules - has remained a major challenge, primarily due to material limitations and scalability constraints. Here, we report on the development of SNSPDs based on tungsten germanide, a novel material system that combines high mid-infrared sensitivity with compatibility for large-scale fabrication. Our detectors exhibit saturated internal detection efficiency at wavelengths up to 29 {\mu}m, while using 2.7x thicker films (8 nm vs 3 nm) and up to 4.5x wider nanowires (360 nm vs 80 nm) compared to mid-infrared-optimized SNSPDs fabricated from tungsten silicide. This advance will enable scalable, high-performance single-photon detection in a spectral region that was previously inaccessible, opening new frontiers in remote sensing, thermal imaging, environmental monitoring, molecular physics, and astronomy.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.12035

Shadow Engineering of Quantum Processes

作者:

Tian-Ci Tian ↗De-Tao Jiang ↗Wei-Ming Zhu ↗Wei-You Liao ↗Hong-Wei Li ↗He-Liang Huang ↗

arXiv:2606.12035v1 Announce Type: new Abstract: Characterizing quantum processes is essential for hardware benchmarking, error diagnosis, and algorithm verification. While recent work [PRX QUANTUM 4, 040337 (2023)] extended classical shadows from quantum state to quantum process, enabling efficient single-channel $\mathcal{E}$ property prediction, its applicability to composite processes $f(\mathcal{E}_1, \mathcal{E}_2,\cdots, \mathcal{E}_k)$ remains unexplored. We introduce shadow engineering, a framework encoding the classical shadows of processes into sparse transfer matrices to predict $f(\mathcal{E}_1, \mathcal{E}_2,\cdots, \mathcal{E}_k)$ properties with proven polynomial sample complexity, matching single-channel efficiency while exponentially lower than quantum process tomography. Crucially, this approach repurposes existing $\mathcal{E}_m$-shadow data without physical execution of $f(\mathcal{E}_1, \mathcal{E}_2,\cdots, \mathcal{E}_k)$, enabling flexible quantum process characterization with minimal hardware overhead. We demonstrate the framework's effectiveness and practicality on a superconducting quantum processor for typical applications such as error mitigation and Hamiltonian dynamical simulation. This framework unlocks new capabilities for predicting complex quantum behaviors without physical re-execution, with immediate applications in near-term device calibration and quantum simulation.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14095

Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs

作者:

Tianhao Wu ↗Matthew Zurek ↗Weina Wang ↗Qiaomin Xie ↗

arXiv:2606.14095v1 Announce Type: new Abstract: We study the sample complexity of learning in average-reward weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs) under a generative model. Naive reduction to a tabular MDP leads to high complexity bounds as the state-action space is exponentially large in the number of arms $N$. By exploiting the weakly coupled structure, we show that near-optimal policies can be learned with sample and computational complexities that are polynomial in $N$. Specifically, we analyze the plug-in approach, which applies an efficient planning algorithm to an empirical model estimated from data. For fully heterogeneous WCMDPs, we establish the first finite-sample PAC guarantee with polynomial complexity and an $O(1/\sqrt{N})$ optimality gap. For homogeneous RBs, we further prove that a smaller optimality gap is achievable under mild structural assumptions. A primary technical contribution of our work is a novel Lyapunov-based analysis framework. Unlike classical approaches that rely on the difficult-to-control bias function, our framework uses an explicitly constructed Lyapunov function along with a drift transfer technique between the true and empirical models. A key step of independent interest in our framework is a fine-grained perturbation analysis for the underlying linear programming (LP) relaxation, which provides a general tool for analyzing LP-based policies and weakly-coupled systems.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15589

Is Code Better Than Language for Algorithmic Reasoning

作者:

Terry Tong ↗Yu Feng ↗Surbhi Goel ↗Dan Roth ↗

arXiv:2606.15589v1 Announce Type: cross Abstract: For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism. We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer. On a 40-task verifiable algorithmic benchmark, deterministic code execution outperforms natural-language reasoning by +31.6pp. We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp). These results suggest that, in our evaluated setting, changing the intermediate representation alone does not explain the tool-use advantage, providing evidence for the performance gains requiring reliable external execution. We formalize this intuition with a simple statistical decision-theoretic model that characterizes when execution dominates end-to-end risk in our disentangled trace-generation/execution regime. We validate our theory using a reconstruction intervention that leverages a proxy language model to infer natural-language reasoning traces from code representations, recovering performance comparable to the original natural-language reasoning pipeline. All experiments are at https://github.com/TerryTong-Git/ToolProj.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2605.07022

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

作者:

Haydn Jones ↗Yimeng Zeng ↗Alden Rose ↗Li S. Yifei ↗Yining Huang ↗Kaiwen Wu ↗Jiaming Liang ↗Maggie Ziyu Huan ↗Yoseph Barash ↗Cesar de la Fuente-Nunez ↗Osbert Bastani ↗Zachary Ives ↗…

arXiv:2605.07022v3 Announce Type: replace Abstract: Manually curated biomedical repositories – spanning bioactivity, genomics, and chemistry – are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate than the curated databases they replace. We present three coupled contributions: (1) an LLM-based entity-tagging pipeline, grounded in nine biomedical ontologies, that tags 4.5B entities across 19 categories in a 22.5M-paper, 2.5T-token PubMed corpus; (2) hybrid sparse-dense retrieval supporting entity-filtered semantic queries over the tagged corpus; and (3) Starling, a multi-agent deep research system that, given only a natural-language task description, designs precision- and recall-targeted retrieval filters, induces an extraction schema, and emits structured records with nuance-rich fields and supporting passages. Across six tasks – blood-brain barrier permeability, oral bioavailability, acute toxicity (LD50), gene-disease associations, protein subcellular localization, and chemical reactions – Starling produces ~6.3M records (91K-3M per task); several are, to our knowledge, the largest public datasets for their property. Frontier-model rejection of our extractions is 0.6-7.7% across tasks, far below error rates we measure on widely used curated counterparts (e.g., 16.5% on BBB_Martins, 7.3% on Bioavailability_Ma). Beyond scale and accuracy, the supporting passages carry nuance tabular databases discard – e.g., oral bioavailability may depend on fed vs. fasted state. Together, the corpus, retrieval, and agent establish a foundation for AI-driven therapeutic design. Code and datasets: https://github.com/starling-labs/starling.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14123

Recovering Stranded Discrimination in Knowledge Tracing: Per-Item Bias Correction via Empirical-Bayes Shrinkage

作者:

Xiaoran Yan ↗Cheng Tang ↗Atsushi Shimada ↗

arXiv:2606.14123v1 Announce Type: cross Abstract: Deployed knowledge-tracing models are typically frozen after training, yet systematic per-item logit bias arises, from limited per-item expressivity in backbone architectures and from post-deployment shifts in item properties, degrading prediction quality. Global post-hoc calibrators such as Platt scaling, temperature scaling, and isotonic regression improve probability estimates but leave discriminative ability, as measured by AUC, unchanged. This AUC invariance is a structural consequence of monotone score-only transforms; recovering the stranded discrimination requires conditioning on item identity. We propose SLC (State-space Logit Correction), which converts binary observations to Gaussian pseudo-observations via Laplace/IRLS, applies empirical-Bayes shrinkage through a Kalman smoother, and fits an offset-Platt link. The state-space formulation also yields a detectability bound that characterizes the Bernoulli information floor, explaining why temporal tracking provides no benefit at current data densities. Across four datasets, five backbones, and three seeds, SLC improves AUC on all four datasets and NLL on three, with the advantage concentrating on sparse items. Cross-domain controls suggest that the same phenomenon can arise beyond education when the deployed backbone leaves entity-level bias.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20347

Critical Percolation as a Synthetic Data Model for Interpretability

作者:

Aryeh Brill ↗Tom Ingebretsen Carlson ↗

arXiv:2606.20347v1 Announce Type: new Abstract: Neural networks learn features that reflect the hierarchical, multi-scale structure of natural data. Synthetic datasets used to evaluate interpretability methods typically lack this structure, limiting their value as realistic toy models. To close this gap, we introduce a family of synthetic datasets consisting of hierarchical functions defined on critical mean-field percolation clusters embedded in a high-dimensional data space. The percolation data consists of sparse, low-dimensional fractal clusters with a power-law size distribution. Latent variables modeling a taxonomic hierarchy generate each data point's target value. The data model is analytically tractable with known critical exponents that fix its properties without requiring hyperparameter tuning. We leverage a mapping between percolation clusters, random trees, and additive coalescence to propose an almost linear-time algorithm to jointly sample a random tree and its hierarchical latent decomposition, enabling data generation at arbitrary scale. Using probing experiments, we find that the model's ground-truth latent variables can be linearly decoded from neural network activations. Together, sparsity, self-similarity, power-law statistics, and analytical tractability make critical percolation a principled testbed for interpretability research.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2510.16380

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

作者:

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models' abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19245

TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

作者:

Hannah Le ↗Ramesh Ramasamy ↗Alex Urrutia ↗Mahsa Yazdani ↗Tim Proctor ↗Kenny Workman ↗

arXiv:2606.19245v1 Announce Type: new Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from literature. The benchmark contains 100 evaluations indexed by program stage, assay type, and task structure, spanning mechanism-of-action (MoA) and pharmacodynamic (PD) reasoning, compound-target engagement, causal target validation, developability and safety, and translational efficacy. Agents receive realistic workflow snapshots, inspect files in a coding environment, and return structured answers graded deterministically. Across 16 model-harness configurations, comprising 11 models and 4,800 trajectories, no system reliably recovered preclinical pharmacology decisions. The strongest configuration, Claude Opus 4.8 / Pi, passed 59.3\% of endpoint attempts (178/300; 95\% CI, 51.1-67.6), followed by GPT-5.5 / Pi at 55.3\% (166/300; 47.0-63.6).

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16990

Analytic Torsion and Spectral Gap Capture Persistent-Laplacian Performance

作者:

Jernej Grlj ↗Aaron D. Lauda ↗

arXiv:2606.16990v1 Announce Type: new Abstract: While persistent Laplacians (PL) offer a richer geometric representation of data than persistent homology, utilizing their full eigenspectrum for learning tasks is often hampered by high dimensionality and the ``varying length'' problem across different filtration scales. We propose a compact spectral representation that distills the persistent Laplacian into three mathematically grounded invariants: Betti numbers, the spectral gap, and analytic torsion. Across benchmark datasets including MNIST, QM-3D, and SKEMPI WT, we demonstrate that this reduced feature space captures the essential predictive signal of the full spectrum, and in some cases outperforms it, while significantly reducing computational overhead and preventing the noise introduced by higher-frequency eigenvalues. Our results suggest that these invariants provide a principled, fixed-length interface between spectral geometry and topological learning.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-22 DOI: HASH:8edbff62fe2b35fc62fa198183028e60

Associations of Chemical Exposures with Psychological Distress and Depression Diagnosis among Waste Pickers in Brasilia, Brazil: A Cross-Sectional Study

作者:

King Stone ↗K. L ↗Maia Pelagalli ↗Melanson ↗Steelman ↗Cruvinel ↗V. R. N ↗Pintas ↗C. P ↗Macena ↗Thygerson ↗Thacker ↗…

Introduction: Waste pickers face chemical exposures. We evaluated whether chemical exposure is associated with psychological distress and depression. Methods: A 2017 cross-sectional survey included 1,141 waste pickers working in the Estrutural open dump in Brasilia, Brazil. Participants self-reported occupational exposure to 11 chemical categories, 17 psychological distress symptoms, and depression diagnoses. Associations of chemical exposure with mean psychological distress scores and depression prevalence were assessed, adjusted for age, sex, marital status, and income. Results: Mean psychological distress score was higher among those exposed to any chemical (mean of 8.1 vs 6.1; adjusted mean difference [aMD]: 1.8 [0.9, 2.7]) and higher among those exposed to each of 11 chemical categories, for example, smoke (aMD: 1.2 [0.6, 1.7]), batteries (aMD: 1.5 [1.0, 1.9], and oils (aMD: 1.3 [0.9, 1.8]). Depression was more prevalent among those exposed to oils (16.6% vs 10.6%; adjusted prevalence difference [aPD]: 6.3% [95% CI: 2.3, 10.2]), cleaning products (aPD: 5.4% [1.2, 9.5]), medications (aPD: 4.7% [0.6, 8.8]), and aerosols (aPD: 5.3% [1.3, 9.3]) but, not smoke, batteries, greases, insecticides, solvents, paints, chemical containers, or any chemical. Conclusion: These associations highlight the need to consider policy level protections for waste pickers to reduce chemical exposure and guard against psychological distress. Further research is necessary to explore which specific chemicals, within broad chemical categories, are associated with psychological distress and depression.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2507.01414

Decomposing Prediction Mechanisms for In-Context Recall

作者:

Sultan Daniels ↗Dylan Davis ↗Dhruv Gautam ↗Wentinn Liao ↗Gireeja Ranade ↗Anant Sahai ↗

arXiv:2507.01414v2 Announce Type: replace Abstract: We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall. We pretrain transformer models on sample traces from this toy, specifically symbolically-labeled interleaved state observations from randomly drawn linear deterministic dynamical systems. We study if the transformer models can recall the state of a sequence previously seen in its context when prompted to do so with the corresponding in-context label. Taking a closer look at this task, it becomes clear that the model must perform two functions: (1) identify which system's state should be recalled and apply that system to its last seen state, and (2) continuing to apply the correct system to predict the subsequent states. Training dynamics reveal that the first capability emerges well into a model's training. Surprisingly, the second capability, of continuing the prediction of a resumed sequence, develops much earlier. Via out-of-distribution experiments, and a mechanistic analysis on model weights via edge pruning, we find that next-token prediction for this toy problem involves at least two separate mechanisms. One mechanism uses the discrete symbolic labels to do the associative recall required to predict the start of a resumption of a previously seen sequence. The second mechanism, which is largely agnostic to the discrete symbolic labels, performs a "Bayesian-style" prediction based on the previous token and the context. These two mechanisms have different learning dynamics. To confirm that this multi-mechanism (manifesting as separate phase transitions) phenomenon is not just an artifact of our toy setting, we used OLMo training checkpoints on an ICL translation task to see a similar phenomenon: a decisive gap in the emergence of first-task-token performance vs second-task-token performance.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16969

Probing Low Frame Rate Degradation in Neural Audio Codecs

作者:

Alex Gichamba ↗Moise Busogi ↗

arXiv:2606.16969v1 Announce Type: cross Abstract: Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost scales linearly with the sequence length. Recent work has demonstrated that codecs can operate at 12.5 Hz and below, but the mechanisms underlying low frame rate degradation remain insufficiently understood. We investigate these mechanisms through a controlled frame rate ablation. We reproduce a quality cliff at 6.25 Hz reported in previous works and evaluate candidate explanations: phonemic collisions and codebook saturation, neither of which shows evidence of a fundamental barrier. The cliff is instead caused by suboptimal training configuration: fixed clip duration during training yields too few tokens at low frame rates, starving the decoder of inter-token context. Once corrected, WER degrades smoothly with phonemic load down to 3.1 Hz and 1.6 Hz, suggesting the inference-time efficiency gains of low frame rate codecs are more accessible than previously assumed.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络