探索全球前沿学术脉络

01.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2604.06464

Weighted Bayesian Conformal Prediction

作者:

Xiayin Lou↗Peng Luo↗

arXiv:2604.06464v2 Announce Type: replace Abstract: Conformal prediction provides distribution-free prediction intervals with finite-sample coverage guarantees, and recent work by Snell \& Griffiths reframes it as Bayesian Quadrature (BQ-CP), yielding powerful data-conditional guarantees via Dirichlet posteriors over thresholds. However, BQ-CP fundamentally requires the i.i.d. assumption. Meanwhile, weighted conformal prediction handles distribution shift via importance weights but remains frequentist, producing only point-estimate thresholds. We propose Weighted Bayesian Conformal Prediction (WBCP), which generalizes BQ-CP to arbitrary importance-weighted settings by replacing the uniform Dirichlet $\Dir(1,\ldots,1)$ with a weighted Dirichlet $\Dir(\neff \cdot \tilde{w}_1, \ldots, \neff \cdot \tilde{w}_n)$, where $\neff$ is Kish's effective sample size. We prove four theoretical results: (1)~$\neff$ is the unique concentration parameter matching frequentist and Bayesian variances; (2)~posterior standard deviation decays as $O(1/\sqrt{\neff})$; (3)~BQ-CP's stochastic dominance guarantee extends to per-weight-profile data-conditional guarantees; (4)~the HPD threshold provides $O(1/\sqrt{\neff})$ improvement in conditional coverage. We instantiate WBCP for spatial prediction as Geographical BQ-CP, where kernel-based spatial weights yield per-location posteriors with interpretable diagnostics. Experiments on synthetic and real-world spatial datasets demonstrate that WBCP maintains coverage guarantees while providing substantially richer uncertainty information.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18413

Searching for Synergy in Shared Workspace Human-AI Collaboration

作者:

Nachiket Kotalwar↗Rohini Das↗Carolyn Rose↗

arXiv:2606.18413v1 Announce Type: new Abstract: Automated AI agents are increasingly capable, yet many scientific and professional tasks require human judgment and contextual expertise. We study shared-workspace human-AI teams, where AI agents and human collaborators must coordinate responsibilities before submitting a final answer. Using the Collaborative Gym environment with DiscoveryBench tasks, we examine when adding simulated human collaborators improves performance and when process loss turns additional collaborators into coordination overhead. Across 1,482 sessions, adding relevant collaborators can lower performance when teams lack structure to coordinate their contributions. We then evaluate scaffolding that combines shared group memory with simulated human-in-the-loop (HITL) gates, where selected actions require approval from a designated simulated participant. This scaffolding yields higher mean performance, most clearly in three-person teams, with clearer responsibility signals and stronger routing of expertise to team actions. Overall, how human-AI teams coordinate and integrate expertise matters as much as the capability available to them.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19005

Sumi: Open Uniform Diffusion Language Model from Scratch

作者:

Mengyu Ye↗Keito Kudo↗Wataru Ikeda↗Ryosuke Matsuda↗Keisuke Sakaguchi↗Jun Suzuki↗

Diffusion models have become a promising alternative to autoregressive models. Among these, uniform diffusion language models (UDLMs) permit any token to be updated at any step, in principle enabling more flexible generation. However, no UDLM has yet been pretrained from scratch at both large parameter scale and large token budget. Both autoregressive modeling and masked diffusion modeling already have capable models at scale that the community can study and build on; uniform diffusion has none. A scratch-pretrained UDLM at scale would provide a clean reference point for studying scaling behavior, generation dynamics, controllability, and trade-offs against established autoregressive and masked diffusion models. To this end, we introduce Sumi ("ink" in Japanese), a fully open 7B uniform diffusion language model pretrained from scratch on 1.5T tokens. Sumi performs competitively with autoregressive models trained at comparable token budgets on knowledge, reasoning, and coding benchmarks, while under-performing on commonsense benchmarks, where our education-heavy data mixture is a likely contributor. We release our model weights, checkpoints, and full training recipe, including a complete specification of the data mixture over publicly available corpora. We hope this release enables the community to study native uniform diffusion at scale and catalyzes work on its as-yet poorly understood aspects.

阅读与讨论 → 访问原文 →

04.

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 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.08532

DN-Hypo-Pipeline: An AI-Driven Workflow for Hypothesis Generation via Large Language Models and Scientific Explanations

作者:

Lei Lin↗Ronghao Wang↗Chunbao Zhou↗Jue Wang↗Yangang Wang↗

arXiv:2606.08532v2 Announce Type: replace Abstract: A scientific hypothesis is the first step in research and undergoes experimental validation, yet it also reflects a deep understanding of and reasoning about scientific phenomena. We introduce DN-Hypo-Pipeline, an AI-powered workflow based on large language models, designed to support structured scientific thinking and hypothesis generation by leveraging scientific explanations as prior knowledge. This pipeline assists researchers in deriving novel hypotheses from existing literature. Given the explanandum (i.e., the conclusion) of a research paper, it identifies underlying laws, theories, and principles, and reconstructs a new, yet-to-be-verified explanation for the observed phenomenon. We evaluated DN-Hypo-Pipeline in the field of data science modeling using three highly cited papers. Statistical inference, supported by both LLM-as-judge assessment and human expert evaluation, demonstrates that our pipeline is more effective than direct generation methods. Additionally, we validated the two highest-scoring generated hypotheses by developing corresponding novel algorithms, which outperformed the baseline models presented in the original papers. Beyond application in data science, DN-Hypo-Pipeline provides a theoretical framework that not only encompasses theory-guided data science modeling methods but also reveals a more fundamental structure of the modeling process. Moreover, this approach is essentially a generalization of theory-guided modeling, offering potential for extension to other domains and across a broader range of scientific disciplines.

阅读与讨论 → 访问原文 →

06.

PLOS Medicine 2026-05-22 DOI: HASH:394c30ca91b2a159bee9b1cba56c0de9

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

作者:

Nicole A. Swartwood↗

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

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19641

Scaling Self-Play for End-to-End Driving

作者:

Luke Rowe↗Roger Girgis↗Rodrigue de Schaetzen↗Daphne Cornelisse↗Alaap Grandhi↗Felix Heide↗Eugene Vinitsky↗Christopher Pal↗Liam Paull↗

End-to-end autonomous driving models are typically trained on offline human-demonstration datasets that provide limited state coverage and often no closed-loop feedback, making them prone to compounding errors when deployed in closed-loop and brittle to long-tail agent interactions. To overcome these limitations, we propose an alternative strategy for training end-to-end driving models: large-scale self-play directly from pixels in simulation. While prior self-play approaches have shown promising transfer to real-world driving, they typically assume vectorized Bird's-Eye-View (BEV) observations that are incompatible with end-to-end policies operating directly on sensor observations. To this end, we introduce Gigapixel, a high-throughput batched driving simulator with perspective rendering, enabling scalable self-play directly from pixel observations. Rather than targeting compute-costly photorealistic sensor simulation, Gigapixel renders a simplified bounding-box world that preserves essential scene structure while achieving throughput at 50k agent steps per second. Since direct pixel-space self-play RL is prohibitively sample-inefficient at end-to-end model scale, we propose self-play DAgger training: we train pixel-based policies in self-play via on-policy distillation from a privileged RL teacher. To bridge the sim-to-real gap, we subsequently transfer the self-play trained policies to real-world sensor data through lightweight perception adaptation. Policies trained in Gigapixel and adapted to real-world sensor data achieve competitive performance on the HUGSIM and NAVSIM-v2 benchmarks without human trajectory supervision. Moreover, scaling self-play training yields proportional gains in policy performance, establishing self-play as a practical and scalable strategy for training end-to-end models.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18523

DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis

作者:

Johannes Seiffarth↗Matthias Pesch↗Lukas Scholtes↗Dietrich Kohlheyer↗Hanno Scharr↗Katharina N\"oh↗

High-throughput microfluidic live-cell imaging generates rich single-cell data. Yet semi-automated procedures for locating regions of interest (RoIs), each containing one cell population, and removing surrounding microfluidic structures from recorded images, scale with the number of RoIs. This prevents real-time image analysis and delays time-to-insight by hours to days. We introduce the Design-Aware and Real-Time capable (DART) paradigm for microfluidic cultivation chips, which aligns the CAD blueprint with the physical chip and thereby enables throughput-independent localization of all RoIs and fully automated image processing across diverse RoI geometries and chip layouts. DART establishes this alignment through embedded fiducial markers and deep-learning-based marker detection. We validate DART using the Swiss Army Knife chip, which combines eight structurally distinct RoI designs across 1164 RoI locations. DART localizes all RoIs in five minutes, removes microfluidic structures from raw microscopy images in 40 ms, and performs fully automated image analysis, including cell segmentation, in under 1.1 s per image. Together, these capabilities establish DART as an end-to-end hardware-software paradigm with real-time-capable analysis that paves the way toward closed-loop and outcome-driven smart microscopy.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.26234

Minimal surfaces, Knots, and Neural Networks

作者:

Tancredi Schettini Gherardini↗Marco Usula↗

arXiv:2605.26234v2 Announce Type: replace-cross Abstract: A recent conjecture by Joel Fine posits a relationship between the coefficients of the HOMFLY polynomial of a knot $K$ in the 3-sphere $S^3$, and the signed count of minimal surfaces in hyperbolic 4-space $\mathrm{H}^4$ meeting the sphere at infinity at $K$, with prescribed genus and self-intersection number. In this paper, we develop a novel machine learning framework based on Physics-Informed Neural Networks (PINNs) to solve the minimal surface equation in hyperbolic space. We utilise this framework to test Fine's Conjecture by constructing near-minimal surfaces bounding various families of knots in $S^3$. Furthermore, we develop an algorithmic method to find self-intersections and compute their sign. For every knot analysed, the computationally discovered minimal surfaces and their self-intersection numbers perfectly align with the predictions of Fine's Conjecture, providing empirical evidence for it.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11438

Isotropic random walks and Brownian diffusion on complex projective space

作者:

Gyula I. T\'oth↗

arXiv:2606.11438v1 Announce Type: new Abstract: We show that isotropic random walks on the complex projective space provide a canonical and analytically tractable stochastic-geometric framework for the exploration of quantum-state space. The approach combines harmonic analysis on compact rank-one symmetric spaces with stochastic pure-state evolution and yields explicit analytical expressions for transition kernels, fidelity statistics, and geometric observables associated with the Fubini–Study metric. In particular, the framework provides a solvable reference model for isotropic depolarization and Haar equilibration, reproducing Haar-random fidelity statistics and the invariant measure on projective Hilbert space without specifying a microscopic Lindblad generator. In the short-time regime, the stochastic evolution converges to Brownian diffusion generated by the Fubini–Study Laplace–Beltrami operator, while the long-time limit exhibits concentration-of-measure behaviour characteristic of high-dimensional random quantum states. We further derive analytical and asymptotic results for the first-passage-time problem, including closed-form expressions in the Brownian limit for the mean first passage time and the long-time tail of the first-passage-time distribution. For high-fidelity target states, the mean first passage time exhibits a strong dimension-dependent divergence originating from the concentration properties of the Fubini–Study geometry.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19594

Unsupervised Causal Abstractions Discovery

作者:

Th\'eo Saulus↗Simon Lacoste-Julien↗Dhanya Sridhar↗

arXiv:2606.19594v1 Announce Type: new Abstract: Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Existing applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce latents that form a causal abstraction, (2) we provide identifiability results about these latents, and (3) we propose a practical objective to learn this high-level SCM.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2603.20775

Evaluating Uplift Modeling under Structural Biases: Insights into Metric Stability and Model Robustness

作者:

Yuxuan Yang↗Dugang Liu↗Yiyan Huang↗

arXiv:2603.20775v2 Announce Type: replace Abstract: In personalized marketing, uplift models estimate the incremental effect of an intervention by modeling how customer behavior would change under alternative treatments using counterfactual analysis. However, real-world marketing data often exhibit various biases, such as selection bias, spillover effects, measurement error, and unobserved confounding. These biases can adversely affect both the accuracy of uplift estimation and the validity of evaluation metrics. Despite the importance of bias-aware assessment, there remains a lack of systematic studies evaluating how different models and metrics perform under such biased conditions. To bridge this gap, we design a systematic benchmarking framework. Unlike standard predictive tasks, real-world uplift datasets inherently lack counterfactual ground truth. This limitation renders the direct validation of evaluation metrics infeasible and prevents the precise quantification of biases. Therefore, a semi-synthetic approach serves as a critical enabler for systematic benchmarking. This approach effectively bridges the gap by retaining real-world feature dependencies while providing the ground truth needed to isolate structural biases. Our investigations reveal that (i) uplift targeting and prediction can manifest as distinct objectives, where proficiency in one does not ensure efficacy in the other; (ii) while many models exhibit inconsistent performance under diverse biases, TARNet shows notable robustness, providing insights for subsequent model design; (iii) the stability of evaluation metrics is linked to their mathematical alignment with the ATE, suggesting that ATE-approximating metrics yield more consistent model rankings under structural data imperfections. These findings suggest the need for more robust uplift models and evaluation metrics under real-world data imperfections.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15320

Conditional Multi-Event Temporal Grounding in Long-Form Video

作者:

Yuanhao Zou↗Arthad Kulkarni↗Lucas Tonanez↗Lincoln Spencer↗Guangyu Sun↗Tianxingjian Ding↗Andong Deng↗Yi Li↗Shuangjun Liu↗Yuan Li↗Dashan Gao↗Ning Bi↗…

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.07840

SAGE: Scalable AI Governance & Evaluation

作者:

Benjamin Le↗Xueying Lu↗Nick Stern↗Wenqiong Liu↗Igor Lapchuk↗Xiang Li↗Baofen Zheng↗Kevin Rosenberg↗Jiewen Huang↗Zhe Zhang↗Abraham Cabangbang↗Satej Milind Wagle↗…

arXiv:2602.07840v4 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92$\times$ lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25\% lift in LinkedIn daily active users.

阅读与讨论 → 访问原文 →

15.

medRxiv (Medicine) 2026-06-16 DOI: HASH:e8efcf00b5d6740340d806a6af3318fb

Exercise Training Improves Skeletal Muscle Insulin Sensitivity and Reprograms the Adipose Transcriptome in Heavier Monozygotic Twins

作者:

Hentila↗Ullrich↗Ojala↗Lietzen↗M. S↗Heiskanen↗M. A↗Van der Stede↗Honkala↗Helmio↗Rajander↗Eskola↗…

Exercise training improves skeletal muscle insulin sensitivity, yet its effects on white adipose tissue remain incompletely understood. We investigated how adiposity and exercise training influence insulin-stimulated glucose uptake in skeletal muscle and abdominal subcutaneous adipose tissue (ASAT), alongside adaptations in gene expression and DNA-methylation. Ten monozygotic twin pairs discordant for BMI underwent [18F]FDG-PET/CT imaging of skeletal muscle (vastus lateralis, VL) and ASAT during a euglycemic-hyperinsulinaemic clamp before and after six months of exercise training. VL and ASAT biopsies were analyzed using mRNA-sequencing and reduced representation bisulfite sequencing. Exercise training improved whole-body and VL insulin sensitivity in leaner and heavier co-twins (p

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2603.03824

In-Context Environments Induce Evaluation-Awareness in Language Models

作者:

Maheep Chaudhary↗

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

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2604.13301

Honeypot Protocol

作者:

Najmul Hasan↗

arXiv:2604.13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2604.16689

The Query Channel: Information-Theoretic Limits of Masking-Based Explanations

作者:

Erciyes Karakaya↗Ozgur Ercetin↗

arXiv:2604.16689v2 Announce Type: replace Abstract: Masking-based post-hoc explanation methods, such as KernelSHAP and LIME, estimate local feature importance by querying a black-box model under randomized perturbations. This paper formulates this procedure as communication over a query channel, where the latent explanation acts as a message and each masked evaluation is a channel use. Within this framework, the complexity of the explanation is captured by the entropy of the hypothesis class, while the query interface supplies information at a rate determined by an identification capacity per query. We derive a strong converse showing that, if the explanation rate exceeds this capacity, the probability of exact recovery necessarily converges to one in error for any sequence of explainers and decoders. We also prove an achievability result establishing that a sparse maximum-likelihood decoder attains reliable recovery when the rate lies below capacity. A Monte Carlo estimator of mutual information yields a non-asymptotic query benchmark that we use to compare optimal decoding with Lasso- and OLS-based procedures that mirror LIME and KernelSHAP. Experiments reveal a range of query budgets where information theory permits reliable explanations but standard convex surrogates still fail. Finally, we interpret super-pixel resolution and tokenization for neural language models as a source-coding choice that sets the entropy of the explanation and show how Gaussian noise and nonlinear curvature degrade the query channel, induce waterfall and error-floor behavior, and render high-resolution explanations unattainable.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13452

Examining the Cognitive Gap Between Authors and Peer Reviewers on Academic Paper Novelty

作者:

Chenggang Yang↗Chengzhi Zhang↗

Novelty is a crucial metric for assessing the quality of academic papers. Scholars strive to highlight the novel aspects of their work, particularly in the title, abstract, and introduction. Peer review, serving as the gatekeeper of scientific rigor, rigorously evaluates the novelty of papers, yet a cognitive gap may exist between author self-promotion and reviewer evaluation. To investigate this, we analyzed 15,328 academic papers published in Nature Communications from 2016 to 2021, along with their peer-review comments. We found that both reviewers and authors emphasize result-oriented innovation, with reviewers adopting a more comprehensive evaluation perspective. Furthermore, by examining promotional intensity against inherent paper novelty, we found that its effect depends on the paper's actual innovation level. Highly innovative papers benefit from stronger promotional language, receiving more positive evaluations. We also found that promotional language significantly correlates with reviewer disagreement on novelty specifically for papers of moderate innovativeness, whereas it has negligible impact for papers with either very high or very low novelty. This reveals how promotional language operates most prominently in the gray area of academic evaluation.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2605.25225

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability

作者:

David N. Olivieri↗Antonio F. P\'erez Rodr\'iguez↗

arXiv:2605.25225v2 Announce Type: replace-cross Abstract: Mechanistic interpretability often studies Transformer behavior by intervening on internal activations through activation patching, causal tracing, path patching, and steering directions. This paper develops Transformer Field Theory: a response-theoretic framework in which the residual stream of a fixed forward pass is treated as a Transformer field over layer depth and token position. In this formulation, patching becomes a localized source insertion into the Transformer field, first-order sensitivity fields predict patch effects, Green functions describe downstream propagation, and patch selection is posed as an adjoint inverse problem. Empirically, we test the theory's forward response objects in GPT-2-style autoregressive Transformers. Localized Transformer-field interventions exhibit a bounded local linear regime; first-order sensitivities predict patch effects across layer-token sites; localized sources generate structured anisotropic Transformer-field propagation; high-sensitivity sites and sliced Green operators provide reduced response descriptions; and prompt-induced Transformer-field displacements partially transfer answer behavior. These results establish sensitivities, Transformer-field responses, and sliced Green operators as practical objects for organizing patching experiments, while providing the forward mathematical basis for patch-site inference and cross-scale response transfer.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2403.13089

Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning

作者:

Mengxian Lyu↗Cheng Peng↗Xiaohan Li↗Patrick Balian↗Jiang Bian↗Yonghui Wu↗

Automatic text summarization (ATS) is an emerging technology to assist clinicians in providing continuous and coordinated care. This study presents an approach to summarize doctor-patient dialogues using generative large language models (LLMs). We developed prompt-tuning algorithms to instruct generative LLMs to summarize clinical text. We examined the prompt-tuning strategies, the size of soft prompts, and the few-short learning ability of GatorTronGPT, a generative clinical LLM developed using 277 billion clinical and general English words with up to 20 billion parameters. We compared GatorTronGPT with a previous solution based on fine-tuning of a widely used T5 model, using a clinical benchmark dataset MTS-DIALOG. The experimental results show that the GatorTronGPT- 20B model achieved the best performance on all evaluation metrics. The proposed solution has a low computing cost as the LLM parameters are not updated during prompt-tuning. This study demonstrates the efficiency of generative clinical LLMs for clinical ATS through prompt tuning.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11869

Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production

作者:

Marc Alier Forment↗Juanan Pereira↗Francisco Jos\'e Garc\'ia-Pe\~nalvo↗Mar\'ia Jos\'e Casa\~n Guerrero↗

arXiv:2606.11869v1 Announce Type: cross Abstract: Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry their own brand and audit trail. What separates them from the general-purpose tier is fit, not capability: each is built for one job, by the engineer who will maintain it. No published practice sets out how to build one end to end. The pieces are everywhere (function-calling APIs, the Model Context Protocol, code agents to pair with), but the practice that chains them lives in podcasts, blogs, and leaked system prompts. This paper writes that practice down as a methodology, Agents All the Way Down: two preconditions crossed once and kept, then three practices repeated for the agent's life. The preconditions are (P1) Substrate, the LLM as a software component, framed as tools, then system, then messages under prompt-caching; and (P2) Building blocks: function calling, MCP, CLI orchestration, the liteshell pattern, the agent loop, skills, characters, hooks, and scaffolding. The practices are (P3) prototype with a general-purpose agent; (P4) harvest, fold, and ship the result as a CLI, the Turtle pattern; and (P5) agent-tests-agent, in which a general-purpose agent drives it through behavioural scenarios, a complement to classical testing, not a replacement. The working loop is P3 to P4 to P5 and back, and one corollary falls out for free: multi-agent orchestration is just CLI composition. The methodology is framework-free by construction. It was distilled from the AAC, a custom agent for the open-source LAMB platform, built in about ten days by one developer with an AI pair-programmer and in production . We present it as a transferable practice, independent of any language or framework.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18783

SCR-Guided Difficulty-Aware Optimization for Infrared Small Target Detection

作者:

Yunus Sevim↗Beh\c{c}et U\u{g}ur T\"oreyin↗

Infrared small target detection remains challenging due to severe background clutter, low contrast, and weak spatial responses where geometric overlap alone is insufficient to characterize detection quality. In this work, we propose REEM (Reweighted Explicit-visibility Enhanced Modulation), a lightweight SCR-guided difficulty-aware optimization framework that incorporates Signal-to-Clutter Ratio (SCR) as a physically meaningful visibility prior during training. Instead of modifying the network architecture or directly optimizing SCR, REEM computes a ground-truth local SCR from the input image and applies a differentiable modulation to the soft-IoU learning signal, emphasizing low-visibility targets while preserving stable optimization and identical inference behavior. REEM is integrated into a U-Net-based MSHNet without introducing additional parameters, architectural modifications, or inference-time overhead. Extensive experiments demonstrate consistent improvements over the baseline, achieving higher IoU and detection probability (Pd) together with substantially reduced false alarms (FA), particularly under challenging low-visibility conditions. These results suggest that SCR-guided difficulty-aware optimization provides an effective and physically grounded complement to conventional overlap-based objectives for infrared small target detection. The code is available at https://github. com/yall-in-one/Reemm.

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2602.21544

Efficient time-series prediction on NISQ devices via time-delayed quantum extreme learning machine

作者:

Mio Kawanabe↗Saud Cindrak↗Kathy Ludge↗Jun-ichi Shirakashi↗Tetsuo Shibuya↗Hiroshi Imai↗

arXiv:2602.21544v2 Announce Type: replace Abstract: We proposed a time-delayed quantum extreme learning machine (TD-QELM) for efficient time-series prediction on noisy intermediate-scale quantum (NISQ) devices. By encoding multiple past inputs simultaneously, TD-QELM achieves shallow circuit depth independent of sequence length, thereby, mitigating noise accumulation and reducing computational complexity. Experiments using the NARMA benchmark on both noiseless simulations and IBM's 127-qubit processor demonstrate that TD-QELM consistently outperforms conventional quantum reservoir computing in prediction accuracy and noise robustness. These results highlight TD-QELM as a practical and scalable framework for time-series learning on current NISQ hardware.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17835

Perceptual compensation for tonal context in self-supervised speech models

作者:

James Kirby↗Ioana Krehan↗Michele Gubian↗

This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improvements in categorization, but failed to replicate human performance on isolated test syllables. Our findings contrast with previous reports of sensitivity to phonological structure emerging through pre-training alone, and suggest that supervised objectives may be necessary to encourage the abstraction of at least some types of phonological regularities.

阅读与讨论 → 访问原文 →