探索全球前沿学术脉络

01.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14456

QCI Connect: A Modular Full-Stack Quantum Computing Platform

作者:

Eric Bertok↗Hannes Busche↗Florian Drinkler↗David Emmanuel-Costa↗Daniel Herr↗Steffen Hien↗Thomas Keitzl↗Elisabeth Lobe↗Alexandru Paler↗Johannes Renkl↗Martin Rymarz↗Gary Schmiedinghoff↗…

arXiv:2606.14456v1 Announce Type: new Abstract: In a world of various competing quantum computing architectures, hardware-agnostic, full-stack platforms are necessary to bring the full power of quantum computing hardware to domain experts via the cloud. QCI Connect and its Software Development Kit provide a reference architecture for a full-stack platform with a modular design and open-source interface definitions, built to facilitate a community-driven application ecosystem. Here, we present its overall design and features, central interfaces, and lessons learned, both for users of the platform and as a reference guide for future developments.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11209

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

作者:

Jingpei Wu↗Xiao Han↗Weixiang Shen↗Boer Zhang↗Zifeng Ding↗Volker Tresp↗

Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Optimization (GRPO) can improve multimodal reasoning, but most approaches rely on sparse outcome-only rewards. As a result, they struggle to tell whether an incorrect answer comes from a small mistake late in the reasoning or from an unhelpful trajectory from the start. A common solution is to train a process reward model (PRM) for step-level supervision, but this typically requires large-scale high-quality chain-of-thought annotations and additional training cost. We propose ProcessThinker, a practical post-training pipeline that provides step-level process rewards without training an explicit PRM. ProcessThinker first rewrites reasoning traces into a step-tagged format for cold-start supervised fine-tuning, then applies GRPO with a standard format reward and our rollout-based process reward. Concretely, for each intermediate step, we sample multiple continuations from that step and use the empirical success rate (final-answer verification) as the step reward. This gives dense credit assignment and encourages reasoning steps that more reliably support a correct conclusion, helping reduce inconsistent or self-contradictory progress across steps – a key issue in logical reasoning. Across four challenging video benchmarks (Video-MMMU, MMVU, VideoMathQA, and LongVideoBench), ProcessThinker consistently improves over the baseline model Qwen3-VL-8B-Instruct

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19413

Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting

作者:

Huu Hiep Nguyen↗Minh Hoang Nguyen↗Dung Nguyen↗Hung Le↗

arXiv:2606.19413v1 Announce Type: new Abstract: Multimodal time series forecasting, which pairs numerical sequences with domain-relevant textual reports, promises to inject world knowledge into forecasting pipelines. However, we uncover a critical failure mode in existing frameworks that we term text collapse: the text branch converges to a content-independent transformation, contributing negligible discriminative signal regardless of the input description. We argue that text collapse is a consequence of a fundamental asymmetry in time series forecasting: the numerical input is strongly autocorrelated with the output, making the numerical backbone inherently dominant, while the text branch, despite carrying complementary and often critical information, is insufficiently utilized, leading to its systematic underexploitation. To address this, we propose REST-TS (Residual-Exclusive Supervision for Text in Time Series), which turns the asymmetry into a design principle: the numerical backbone produces its own independent numerical forecast, and the text branch is exclusively supervised to predict the structured components of the residual, the prediction gap that numbers cannot explain. Because no numerical pathway can reduce these losses, the text branch must extract genuine content from the input description. Evaluated across diverse real-world domains and backbone architectures, REST-TS achieves state-of-the-art performance and consistently demonstrates greater text-branch utilization than existing frameworks, providing strong empirical evidence that supervising the text branch on the residual compels it to extract genuine content from the input.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12160

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

作者:

Ao Sun↗

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token. Our method extracts a compact set of features such as maximum, minimum, mean, standard deviation, and slope-from the token logits across all layers, enabling effective hallucination detection without overfitting. Experiments on TruthfulQA and MMLU datasets demonstrate that CHAIR significantly improves detection accuracy, particularly in zero-shot scenarios, showcasing its robustness and generalizability. Beyond hallucination detection, CHAIR highlights the potential of using internal representations for designing advanced decoding strategies. By leveraging patterns in logits, we suggest that more sophisticated models and adaptive decoding methods could further reduce hallucinations and enhance text completion quality. CHAIR not only offers a practical solution for detecting hallucinations but also lays the groundwork for exploring richer representations in LLMs to improve their factuality and coherence.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2503.19947

Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders

作者:

Paul Koch↗J\"org Kr\"uger↗

Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support. To address this, we propose a self-supervised training approach that extends pretrained RGB encoders with a depth adapter to incorporate and align metric depth into a combined latent space without interfering with the pretrained RGB feature extraction. In combination with our sinusoidal depth encoding, the depth adapter enables generalized and robust depth density and distribution invariant feature extraction. Our depth adapters improve a wide set of generalized RGB baselines across a spectrum of relevant RGBD downstream tasks in segmentation, pose estimation, and depth completion – without the necessity of finetuning. Most importantly, we achieve 56.05 mIoU in the SUN-RGBD segmentation, while outperforming SOTA depth-aware and multi-modal encoders in our experiments. When no depth is present, one can activate our depth adapter with an empty map, use single pixel depth clues, or monocular depth estimation to include the depth aware feature extraction into subsequent downstream tasks.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2601.21817

A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

作者:

Mingyuan Xu↗Xinzi Tan↗Jiawei Wu↗Doudou Zhou↗

arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates. More data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and judge reliability from pairwise comparisons without reference labels. We establish identifiability up to natural normalizations and prove consistency and asymptotic normality of the maximum likelihood estimator, enabling confidence intervals for score differences and rank comparisons. Across multiple public benchmarks and a newly collected dataset, our method improves agreement with human preferences, achieves higher data efficiency than unweighted baselines, and produces calibrated uncertainty quantification for LLM rankings.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15575

Do we have the knowledge we need? Rethinking human-AI decision-making in corporations

作者:

Anne S. R. Marx↗Ricardo M. Avelino↗Torbj{\o}rn Netland↗Mennatallah El-Assady↗

arXiv:2606.15575v1 Announce Type: new Abstract: Organizational knowledge is fragmented across a variety of software systems, tacit expertise, and manual documents that have traditionally been designed for human consumption. As AI systems are increasingly deployed and granted decision-making roles, they require access to this knowledge. This raises two questions: how should organizations store and maintain knowledge so that it remains accessible to both humans and future AI systems, and how should agency be allocated between humans and AI across tasks with different risks and levels of uncertainty? In this position paper, we describe how organizational knowledge evolves and contribute a framework that maps task attributes and knowledge availability to recommended agency allocations and control mechanisms. We illustrate the applicability of the framework on two different manufacturing tasks: a routine operation (visual quality inspection) and a one-off strategic decision (factory location), and conclude with opportunities for future research.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11400

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

作者:

Tsung-En Lin↗Hung-Yi Lee↗

arXiv:2606.11400v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instruction-based vector steering, which constructs a steering vector by contrasting activations from differently instructed prompts while keeping the audio fixed. Through a systematic probe of LALM attention, we find that - unlike standard prompting or audio-based steering - this intervention significantly redistributes the temporal attention allocated to audio tokens, concentrating it on acoustically relevant regions. We then show that this attention shift is behaviorally meaningful: in a controlled three-event setting, reading out the temporal position of maximal steering-induced attention change recovers the location of a queried sound event without any training, attaining 60.87% and 68.72% overlap with ground-truth intervals on Qwen2-Audio and Audio Flamingo 3, far above direct prompting (31.84%, 46.75%) and random baselines (27.74%). Our results characterize a mechanistic property of instruction-based steering in LALMs and provide a training-free probe for the latent temporal structure these models encode.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.18115

HLS-GPT: A Generative Pretrained Transformer (GPT) for Continental-Scale NASA Harmonized Landsat and Sentinel-2 (HLS) Reflectance Reconstruction Across All Bands on Arbitrary Dates

作者:

Junjie Li↗Hankui K. Zhang↗David P. Roy↗

Recent deep learning methods for Landsat and Sentinel-2 reflectance time series reconstruction remain limited by restricted spectral coverage, limited geographic scalability, or patch-based designs with short temporal contexts. We present HLS-GPT, a large-scale generative pretrained Transformer model for reconstructing NASA Harmonized Landsat Sentinel-2 30 m surface reflectance for all bands, any date, and any pixel location. HLS-GPT uses a hierarchical Transformer architecture to handle the different spectral band configurations of Landsat and Sentinel-2 and operates on single-pixel 12-month time series. To capture geographic and seasonal variability, the model was trained with nine years of HLS time series from more than 0.25 million training pixels across the conterminous United States. A random cropping and masking strategy extracts 12-month periods with varying start dates across epochs, masks 50% of valid observations, and trains the model to reconstruct the masked reflectance values from the remaining observations. Evaluation using more than 62,000 independent test pixels shows robust reconstruction under diverse land surface conditions, including complex crop phenology and sparse, irregular observations. Leave-one-observation-out evaluation achieved reconstruction RMSE below 0.026 for all HLS spectral bands, with relative RMSE below 35% for visible bands and below 13% for other bands. Red-edge band errors were comparable to red and near-infrared errors despite the absence of red-edge bands on Landsat. Sensitivity analyses that randomly masked 10% to 90% of test observations showed only modest degradation when 10% to 50% of observations were masked, with all-band RMSE below 0.028. Image reconstruction over nine independent 109 by 109 km CONUS HLS tiles further demonstrates that HLS-GPT outperforms two conventional methods and the NASA-IBM Prithvi model.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11516

Single Photon Cross-Phase Shifts Can Be Enhanced by Localization in both Frequency and Time

作者:

Xinyu Jiao↗Vida-Michelle Nixon↗Kyle Thompson↗Aephraim Steinberg↗

arXiv:2606.11516v1 Announce Type: new Abstract: Single-photon optical nonlinearities face a fundamental trade-off: maximum nonlinearity requires both spectral resonance (narrow bandwidth) and high peak intensity (short duration), constraints that are incompatible due to the time-energy uncertainty relation. We demonstrate experimentally that this limitation does not need to exist in cases involving post-selection. We measure a cross-phase shift (XPS) produced by a resonant photon from a narrow-band source that is first transmitted through a cold atomic cloud and then localized in time through detection. The peak size of this XPS is greatly enhanced compared to that of Gaussian single-photon-level pulses without post-selection, benefiting from the narrow bandwidth of the resonant prepared state and the high intensity of the post-selected state simultaneously. We measure enhancements in the peak XPS of 6$\pm$1 at an optical depth (OD) of 2.4$\pm$0.1, and our results are in qualitative agreement across a range of optical depths with the recently developed weak value theory of atomic excitation [Thompson et al., APL Quantum 2, 036108 (2025)] for such post-selected photons. This work uncovers new consequences of having simultaneous knowledge of frequency and time, raising new foundational questions about how a particle behaves, and interacts with other systems, when its preparation and post-selection are non-commuting.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17113

The Critical Role of Model Selection in Causal Inference: A Comparative Analysis of Classification Models within the InferBERT Framework for Pharmacovigilance

作者:

Csaba Kiss↗Roland Molontay↗Gabriele Pergola↗

Distinguishing causal adverse drug events (ADEs) from spurious correlations remains a central challenge in pharmacovigilance. The InferBERT framework integrates transformer models with Do-calculus, but its success hinges on the underlying classification model. This study evaluates the impact of model choice in InferBERT, assessing whether simpler models suffice, if domain-specific pre-training helps, whether scaling to LLMs improves causal detection, and the effect of post-hoc calibration. We performed a comparative study on two benchmarks: Analgesics-induced Acute Liver Failure (AILF) and Tramadol-related Mortalities (TRAM). Four models were evaluated-XGBoost (baseline), ALBERT (original InferBERT), BioBERT (biomedical transformer), and Med-LLaMA (medical LLM)-using 5-fold cross-validation repeated over 20 runs. We measured accuracy, Expected Calibration Error (ECE) pre- and post-isotonic regression, and Jaccard concordance of causal terms with PRR, ROR, and EBGM; significance was tested with paired t-tests. BioBERT achieved the highest accuracy on both datasets, while Med-LLaMA underperformed despite its size and parameter-efficient fine-tuning. Domain-specific pre-training was decisive. Calibration improved ECE but had mixed effects on accuracy and causal discovery. BioBERT's superiority also yielded the strongest concordance with traditional pharmacovigilance signals. These results show that domain-specific pre-training provides a clear advantage over simpler baselines and larger LLMs. Investing in manageable, domain-aware models is more effective for computational pharmacovigilance than simply scaling model size.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2511.03211

Retrofitters, pragmatists and activists: Public interest litigation for accountable automated decision-making

作者:

Henry Fraser↗Zahra Stardust↗

arXiv:2511.03211v4 Announce Type: replace-cross Abstract: This paper examines the role of public interest litigation in promoting accountability for AI and automated decision-making (ADM) in Australia. Since ADM regulation faces political and geopolitical headwinds, effective governance will have to rely on the enforcement of existing laws. Drawing on interviews with Australian public interest litigators, technology policy activists, and technology law scholars, the paper positions public interest litigation as part of a larger ecosystem for transparency, accountability and justice with respect to ADM. The paper explores the tactics and strategies of what one participant described as 'retrofitting' old laws to ADM. These go beyond creative legal argumentation, to encompass practices of community-building, collaboration on theories of change, canny selection of clients and causes of action, and the alignment of the interests of stakeholders in litigation. Naturally, the paper also contends with the limits of these strategies, and of the Australian legal system. Where limits are, however, capable of being overcome, the paper presents findings on urgent needs: the enabling institutional arrangements without which effective litigation and accountability will falter. The paper is relevant to law and technology scholars; individuals and groups harmed by ADM; public interest litigators and technology lawyers; civil society and advocacy organisations; and policymakers.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14780

YTClickbait21K: Human-Annotated Multimodal Dataset for YouTube Clickbait Detection Across Diverse Channels and Content Categories

作者:

Md. Minhazul Islam↗Md. Tanbeer Jubaer↗Amith Khandakar↗Shovon Sarker↗Sumaiya Rahman↗Md. Masum Mia↗Mohamed Arselene Ayari↗Hamed Noori↗

Clickbait content on video-sharing platforms poses a significant challenge to information reliability, yet progress in automated detection has been constrained by the lack of large-scale, high-quality multimodal datasets. We present YTClickbait21K, a human-annotated YouTube clickbait dataset comprising 21,238 videos collected from 40 channels across 29 countries, covering diverse content categories such as news, entertainment, education, and gaming. Each sample includes structured metadata (title, description, engagement statistics) along with associated thumbnail images, enabling comprehensive multimodal analysis. To ensure annotation quality, every video was independently labeled by three annotators using a standardized decision framework that incorporates textual, visual, and cross-modal consistency cues, with final labels determined through majority voting. The dataset exhibits substantial inter-annotator agreement (k=0.65), confirming reliable labeling despite the inherent subjectivity of clickbait detection. By combining scale, annotation rigor, and multimodal richness, this dataset provides a robust benchmark for developing and evaluating machine learning models, facilitating research in cross-modal semantic understanding, and advancing automated content moderation systems.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13649

Operadic consistency: a label-free signal for compositional reasoning failures in LLMs

作者:

Nathaniel Bottman↗Yinhong Liu↗Kyle Richardson↗

Detecting LLM reasoning failures at inference time without ground-truth labels has motivated a wide range of confidence baselines, including self-consistency, semantic entropy, and P(True), built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces by composing a stated decomposition of the same query. We instantiate this idea as operadic consistency (OC), a per-question signal. Across twelve instruction-tuned LLMs (4B to 671B parameters, open-weights and closed-source) on four multi-hop QA datasets, OC is strongly correlated with accuracy on every dataset (Pearson $r \in [0.86, 0.94]$, all $p \leq 0.0004$), and is the only signal we evaluate with $r \geq 0.85$ uniformly across all four datasets. Chain-of-thought self-consistency (CoT-SC; Wang et al., 2023) matches OC on HotpotQA and DROP ($r = 0.93, 0.87$) but drops to $r \approx 0.45$ on MuSiQue and StrategyQA. At the per-question level, OC contributes information beyond CoT-SC and semantic entropy on every dataset (cluster-robust $p \leq 10^{-16}$ for the OC coefficient), and the conclusion is robust to additionally controlling for constructed decomposition-aware baselines ($p \leq 10^{-13}$). The same signal yields selective-prediction improvements (accuracy at fixed coverage) over a tuned CoT-SC baseline at the equal-cost $K = 3$ budget (AUARC lifts of +0.086 to +0.096 and AUROC lifts of +0.092 to +0.164; 95% CIs exclude zero on every cell). On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction point-estimate lift on all 16 (dataset, budget, metric) cells tested, with 95% CIs excluding zero on 12 of the 16.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2412.09023

STEAM: Squeeze and Transform Enhanced Attention Module

作者:

Rishabh Sabharwal↗Ram Samarth B B↗Parikshit Singh Rathore↗Punit Rathore↗

Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks (CNNs) but often increase parameter and computational costs. While recent approaches focus solely on efficient feature context modeling for channel attention, we aim to model both channel and spatial attention comprehensively with minimal parameters and reduced computation. Leveraging the principles of relational modeling in graphs, we introduce a constant-parameter module, STEAM: Squeeze and Transform Enhanced Attention Module, which integrates channel and spatial attention to enhance the representation power of CNNs. To our knowledge, we are the first to propose a graph-based approach for modeling both channel and spatial attention, utilizing concepts from multi-head graph transformers. Additionally, we introduce Output Guided Pooling (OGP), which efficiently captures spatial context to further enhance spatial attention. We extensively evaluate STEAM for large-scale image classification, object detection and instance segmentation on standard benchmark datasets. STEAM achieves a \(2\%\) increase in accuracy over the standard ResNet-50 model with only a meager increase in GFLOPs. Furthermore, STEAM outperforms the leading modules, ECA and GCT, in terms of accuracy while achieving a threefold reduction in GFLOPs. The code will be made available upon acceptance.

阅读与讨论 → 访问原文 →

16.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.13667

Semi-Device-Independent Certification for Nonlocality without Entanglement

作者:

Hanwool Lee↗Joonwoo Bae↗

arXiv:2606.13667v1 Announce Type: new Abstract: In this work, we investigate maximum-confidence discrimination, which encompasses minimum-error and unambiguous discrimination, for ensembles of separable states by considering global and separable measurements. We demonstrate that global measurements outperform separable ones, thereby establishing nonlocality without entanglement (NLWE) in terms of confidence in a detection event, a fine-grained state-identification strategy that maximizes the probability of a correct guess given a measurement outcome. Conversely, verifying achievable confidence in measurement outcomes can certify global measurements, namely, semi-device-independent certification of NLWE. Our results make it feasible to experimentally demonstrate NLWE using present-day quantum measurement devices, even with non-unit detection efficiencies, since maximum-confidence measurements rely only on detected measurement outcomes.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2510.02149

Reinforcement Learning with Action-Triggered Observations

作者:

Alexander Ryabchenko↗Wenlong Mou↗

arXiv:2510.02149v2 Announce Type: replace Abstract: We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a reinforcement learning framework for partial observability in which full state observations occur stochastically at each step, with probability determined by the chosen action. We derive Bellman equations tailored to this setting and establish the existence of an optimal policy. Exploiting the fact that sporadic observations reveal the full state, we provide an equivalent formulation in which agents commit to action-sequences between consecutive observations. Under the linear MDP assumption, we show that the value function over such action-sequences admits a linear representation in a finite-dimensional feature map, enabling standard regression-based methods. As an application, we derive ATST-LSVI-UCB, an optimistic algorithm achieving regret $\widetilde{O}(\sqrt{Kd^3(1-\gamma)^{-3}})$ for episodic learning with geometrically distributed horizons, where $K$ is the number of episodes, $d$ the feature dimension, and $\gamma$ the discount factor (episode continuation probability), matching the known rate for linear MDPs with full observability.

阅读与讨论 → 访问原文 →

18.

medRxiv (Medicine) 2026-06-15 DOI: HASH:e23411712c328057b3b2d74f78e2fd9a

Toward a National Registry for Inborn Errors of Immunity in Peru: A Qualitative Implementation Study

作者:

Veramendi-Espinoza↗L. E↗De la Cruz-Torralva↗Pezo-Pezo↗Vargas-Herrera↗J. R↗Neyra Quijandria↗Martina↗Sullivan↗K. E↗Huaman↗M. A↗…

Background: Peru lacks an integrated information system for patients with Inborn Errors of Immunity (IEI). Although disease registries are essential tools for data management and health planning, their success depends on implementation science approaches that account for local contextual factors. This study reports Phase I of a three-phase mixed-methods implementation project to design and develop a national IEI registry. Methods: Phase I consisted of a phenomenological qualitative study exploring stakeholder perspectives. Semi-structured focus groups and in-depth interviews were conducted with 29 key stakeholders across four groups: policy-makers, clinical experts, end-users (immunologists, residents, allied health personnel), and patient organization representatives. Interviews followed a guide structured around four a priori domains (structure, navigation, feasibility, and perception of existing systems). Discussions were conducted in Spanish, audio-recorded, transcribed verbatim, and coded using ATLAS.ti. A hybrid thematic analysis combining deductive and inductive coding was performed. Data elements proposed for the registry were triangulated with qualitative findings. Results: Thirty-six initial codes were consolidated into 15 categories, which were further integrated into four overarching themes conceptualized as pathways toward intention to use: (1) Environment, where governance, regulatory backing, and sustainable financing were identified as key enablers, while limited interoperability emerged as a structural barrier; (2) Technical Dimension, emphasizing usability, alignment with clinical workflow, and a hierarchical data architecture (demographic, clinical, therapeutic); (3) Users, highlighting clinical leadership, protected time, digital readiness, and perceived usefulness as stronger motivators than financial incentives; and (4) Patients, underscoring data protection, transparency, trust, and advocacy as essential for legitimacy and sustainability. Conclusions: A national IEI registry in Peru is perceived as necessary and feasible if implemented with strong regulatory foundations, interoperable design, robust data security, and user-centered architecture. These findings informed the development of an initial functional prototype and the operational plan for Phase II, focused on usability evaluation.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2505.24275

GradPower: Powering Gradients for Faster Language Model Pre-Training

作者:

Jinbo Wang↗Mingze Wang↗Jiaqi Zhang↗Wei Wang↗Peng Pei↗Xunliang Cai↗Weinan E↗Lei Wu↗

arXiv:2505.24275v4 Announce Type: replace Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $g=(g_i)_i$, GradPower first applies the elementwise sign-power transformation: $\varphi_p(g)=(sign(g_i)|g_i|^p)_{i}$ for a fixed $p>0$, and then feeds the transformed gradient into a base optimizer. Notably, GradPower requires only a single-line code change and no modifications to the base optimizer's internal logic, including the hyperparameters. When applied to Adam (termed AdamPower), GradPower consistently achieves lower terminal loss across diverse architectures (LLaMA, Qwen2MoE), parameter scales (66M to 2B), datasets (C4, OpenWebText), and learning-rate schedules (cosine, warmup-stable-decay). The most pronounced gains are observed when training modern mixture-of-experts models with warmup-stable-decay schedules. GradPower also integrates seamlessly with other state-of-the-art optimizers, such as Muon, yielding further improvements. Finally, we provide theoretical analyses that reveal the underlying mechanism of GradPower and highlight the influence of gradient noise.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2604.27960

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning

作者:

Adam Ishay↗Joohyung Lee↗

arXiv:2604.27960v2 Announce Type: replace Abstract: Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While neuro-symbolic methods attempt to mitigate these issues by coupling LLMs with symbolic reasoners, existing approaches typically rely on monotonic logics (e.g., SMT) that cannot represent defeasible reasoning – essential components of human cognition. We present "LLM+ASP," a framework that translates natural language into Answer Set Programming (ASP), a nonmonotonic formalism based on stable model semantics. Unlike prior "LLM+ASP" approaches that require manually authored knowledge modules, domain-specific prompts, or evaluation restricted to single problem classes, our framework operates without any per-task engineering and applies uniformly across diverse reasoning tasks. Our system utilizes an automated self-correction loop where structured feedback from the ASP solver enables iterative refinement. Evaluating across six diverse benchmarks, we demonstrate that: (1) stable model semantics allow LLMs to naturally express default rules and exceptions, outperforming SMT-based alternatives by significant margins on nonmonotonic tasks; (2) iterative self-correction is the primary driver of performance, effectively replacing the need for handcrafted domain knowledge; (3) compact in-context reference guides substantially outperform verbose documentation, revealing a "context rot" phenomenon where excessive context hinders constraint adherence.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18258

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

作者:

Sunnie S. Y. Kim↗Margit Bowler↗Leon A Gatys↗

arXiv:2606.18258v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries. Despite their prevalence, researchers and practitioners lack methods and empirical insights to make informed decisions about when and what types of human-like behaviors LLMs should exhibit. To fill this gap, we present a multi-dimensional analysis of the prevalence, potential effects, and controllability of these behaviors using LLM-as-a-judge and human evaluation. Across 21,000 multi-turn conversations from four widely used models (gpt-4o, gpt-4.1-mini, claude-sonnet-4.6, gemini-2.5-flash), we find that human-like behaviors are pervasive but vary across models and user factors (conversation goals and user profiles). In terms of perceived appropriateness, human evaluators judged self-referential and relationship-building behaviors as less appropriate from LLMs than from humans, but boundary-maintaining behaviors more appropriate from LLMs than from humans. Finally, we show that system prompting can control these behaviors, though it requires careful evaluation to avoid unintended effects. We discuss the implications of our findings and provide recommendations for responsible LLM design and evaluation.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2604.06802

Riemann-Bench: A Benchmark for Moonshot Mathematics

作者:

Suhaas Garre↗Erik Knutsen↗Sushant Mehta↗Edwin Chen↗

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.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.09287

Trajectory Geometry of Transformer Representations Across Layers

作者:

Vishal Pandey↗Gopal Singh↗Yacine Mahdid↗

arXiv:2606.09287v2 Announce Type: replace Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability. We recast the transformer forward pass as a discrete population trajectory through a high-dimensional representation manifold, drawing on geometric tools from computational neuroscience. Rather than probing for pre-specified features, we characterize trajectory geometry using five metrics computed directly in the ambient space: trajectory length, curvature, a semantic convergence index, layerwise cosine similarity, and representational stability. Across three model families (GPT-2, TinyLlama, Qwen2.5) and five controlled prompt families, we report four findings. First, semantically related prompts converge significantly in middle-to-late layers (peak CI 0.41–0.58, p

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2605.14568

Given, When, Then, Again: Mining Subscenario Refactoring Candidates in Behaviour-Driven Test Suites with ML Classifiers and LLM-Judge Baselines

作者:

Ali Hassaan Mughal↗Noor Fatima↗Muhammad Bilal↗

Context. Behaviour-Driven Development (BDD) test suites accumulate duplicated step subsequences. Three published refactoring patterns are available (within-file Background, within-repo reusable-scenario invocation, cross-organisational shared higher-level step), but no prior work automates which recurring subsequences are worth extracting or which mechanism applies. Objective. Rank recurring step subsequences ("slices") by refactoring suitability (extraction-worthy), pre-map each to one of the three patterns, and quantify prevalence across the public BDD ecosystem. Method. Every contiguous L-step window (L in [2, 18]) in a 339-repository / 276-upstream-owner Gherkin corpus is keyed by paraphrase-robust cluster identifiers and counted under three scopes. SBERT / UMAP / HDBSCAN clustering recovers paraphrase-equivalent slices. Three authors label a stratified 200-slice pool against a written rubric. An XGBoost extraction-worthy classifier trained under 5-fold cross-validation is compared with a tuned rule baseline and two open-weight Large Language Model (LLM) judges. Results. The miner produces 5,382,249 slices collapsing to 692,020 recurring patterns. Three-author Fleiss' kappa = 0.56 (extraction-worthy) and 0.79 (mechanism). The classifier reaches out-of-fold F1 = 0.891 (95% CI [0.852, 0.927]), outperforming both the rule baseline (F1 = 0.836, p = 0.017) and the better LLM judge (F1 = 0.728, p = 1.5e-4). 75.0%, 59.5%, and 11.7% of scenarios carry a within-file Background, within-repo reusable-scenario, and cross-organisational shared-step candidate, respectively; the figures are stable under a sweep of the classifier decision threshold. Conclusion. Paraphrase-robust subscenario discovery yields a corpus-wide census of BDD refactoring candidates; pipeline, classifier predictions, labelled pool, and rubric are released under Apache-2.0.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15877

Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision

作者:

Alex Bogdan↗

Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning. But on planning, contested ethics, and tasks where the model cannot check itself, more reasoning makes things worse. Both effects are documented; what has been missing is a principled account of which property decides the outcome. We argue it is meta-uncertainty: how unsure the model is about the reliability of its own evidence. When that uncertainty is high, extra reasoning stops adding signal and starts manufacturing false confidence. We prove that the policy minimizing expected free energy under uncertain precision stops integrating cues after a finite number of high-validity ones when the precision prior is heavy-tailed (Theorem 2.6.1), and under a Descending Dominance condition, is sample-wise identical to take-the-best (Theorem 2.7.4). Fast-and-frugal heuristics and active inference are, then, two descriptions of the same computation. The prediction is that on high-meta-uncertainty items, longer CoT should degrade accuracy. We score the regime per item (simulate-and-recover rho > 0.96), build FEH-79, a benchmark of Knightian frames with matched controls, and run a pre-registered study across seven models (five open-weight 3B-32B, two frontier), five CoT lengths, and 7,875 responses. The gate, fixed before any data, required a negative interaction with posterior probability above 0.95 and an accuracy drop of more than 6 points. It held. The high-regime drop is 17.3 points (95% CI [7.7, 25.5]); matched items with definite answers show no cost. The effect is regime-dependent: decisive in capable mid-to-large models, directional in the two frontier systems, absent-to-reversed in the weakest. The framework answers when CoT helps and unifies the Bayesian and fast-and-frugal traditions: less-is-more effects are evidence about the meta-uncertainty regime, not against Bayesian cognition.

阅读与讨论 → 访问原文 →