中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
medRxiv (Medicine) 2026-06-24

Genetically Proxied Interleukin-6 Inhibition and Cancer Risk: A Multi-Ancestry Drug-Target Mendelian Randomization Study of Hepatocellular Carcinoma and Colorectal Cancer

作者:
Ranjha↗M. M. A↗Munir↗

Background: Interleukin-6 (IL-6) signalling drives chronic inflammation and is therapeutically targeted by tocilizumab, an approved IL-6 receptor inhibitor. Whether genetically proxied lifelong IL-6 inhibition causally influences the risk of hepatocellular carcinoma (HCC) or colorectal cancer (CRC) remains unanswered. Prior single-variant estimates from pooled observational data are methodologically limited and may reflect confounding. Methods: A two-sample drug-target Mendelian randomization (MR) study was conducted. Four independent cis-acting protein quantitative trait loci (pQTL) variants within the IL6 and IL6R gene loci (rs2228145, rs4129267, rs7529229, rs1800795) were selected as genetic instruments , with F-statistics ranging from 32.3 to 120.5, confirming instrument strength. Outcome data were obtained from four independent genome-wide association studies: HCC from BioBank Japan (BBJ; 1,866 cases, 195,745 controls), HCC from FinnGen Release 10 (674 cases, 218,118 controls), CRC from a European meta-analysis (19,948 cases, 12,124 controls), and CRC from BBJ (7,062 cases, 195,745 controls). Causal estimates were derived using inverse variance weighted (IVW) regression as the primary method, with MR-Egger and weighted median analyses as sensitivity methods. Cochran Q statistics assessed heterogeneity and MR-Egger intercept testing assessed directional pleiotropy. Results: Genetically proxied IL-6 inhibition showed no significant causal effect on HCC risk in East Asian populations (IVW odds ratio [OR] 0.997, 95% confidence interval [CI] 0.903 to 1.101, p=0.953) or European populations (IVW OR 0.984, 95% CI 0.802 to 1.208, p=0.880). Similarly, no causal effect was observed on CRC risk in European populations (IVW OR 1.015, 95% CI 0.957 to 1.075, p=0.623) or East Asian populations (IVW OR 0.999, 95% CI 0.948 to 1.052, p=0.971). Sensitivity analyses confirmed the absence of directional pleiotropy and heterogeneity across all four analyses. Leave-one-out analyses demonstrated that no single instrument drove the null findings. Conclusions: Genetically proxied IL-6 receptor inhibition, modelling the therapeutic effect of tocilizumab, showed no causal effect on HCC or CRC risk across four independent cohorts and two ancestries. These findings do not support a role for IL-6 pathway inhibition in the prevention of these cancers and provide reassuring genetic safety evidence regarding cancer risk in patients receiving tocilizumab. Larger HCC-specific GWAS are needed to definitively evaluate modest effects in this cancer type.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-15

Can professional translators identify machine-generated text?

作者:
Michael Farrell↗

This study investigates whether professional translators without prior specialized training can reliably identify short stories generated in Italian by artificial intelligence (AI). Sixty-nine translators took part in an in-person experiment, where they assessed three anonymized short stories - two written by ChatGPT-4o and one by a human author. For each story, participants rated the likelihood of AI authorship and provided justifications for their choices. While average results were inconclusive, a statistically significant subset (16.2%) successfully distinguished the synthetic texts from the human text, suggesting that their judgements were informed by analytical skill rather than chance. However, a nearly equal number misclassified the texts in the opposite direction, often relying on subjective impressions rather than objective markers, possibly reflecting a reader preference for AI-generated texts. Low burstiness and narrative contradiction emerged as the most reliable indicators of synthetic authorship, with unexpected calques, semantic loans and syntactic transfer from English also reported. In contrast, features such as grammatical accuracy and emotional tone frequently led to misclassification. These findings raise questions about the role and scope of synthetic-text editing in professional contexts.

阅读与讨论 → 访问原文 →
03.
arXiv (quant-ph) 2026-06-25

Nonlinear Dynamics of Coherent Parametric Amplification in Multipartite two-level System under Intrinsic Decoherence

作者:
Muhammad Ibrahim↗

arXiv:2606.25860v1 Announce Type: new Abstract: In this work, we study the dynamics of global quantum discord and quantum Fisher information in a multipartite system of two-level atoms interacting with a coherent field. The model includes parametric amplification, Kerr-type nonlinearity, and intrinsic decoherence to examine how these effects control quantum correlations and parameter-estimation sensitivity. The results show that, without intrinsic decoherence, both quantities exhibit rapid oscillations with clear collapse and revival behavior. Strong Kerr nonlinearity and strong parametric amplification enhance global quantum discord, while quantum Fisher information becomes maximum under a suitable balance of Kerr nonlinearity and amplification strength. Increasing the number of atoms generally strengthens global quantum discord but does not always improve quantum Fisher information. Intrinsic decoherence damps the oscillations and drives the system toward steady-state behavior.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-17

ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

作者:
Ander Alvarez↗Santhiya Rajan↗Samuel Mugel↗Rom\'an Or\'us↗

Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and formulary tools. Standard factuality metrics usually test whether an answer is supported by pooled evidence, missing a provenance-sensitive failure mode: a claim may be supported somewhere while being attributed to the wrong source. We call this cross-source conflation. We introduce ProvenanceGuard, a source-aware verifier for MCP-grounded answers. It consumes captured MCP traces with stable tool IDs, source IDs, and raw outputs; decomposes answers into atomic claims; routes claims to source-specific evidence; checks support with NLI and a token-alignment proxy; compares stated attribution with the routed source; and returns per-claim verdicts plus an answer-level allow/block decision. Blocked answers can be repaired with retrieval-augmented answer revision and re-verified. We evaluate on 281 medical-domain MCP-agent traces. A 266-trace adjudicated subset yields 2,325 LLM-assisted claim labels split by trace; 361 held-out labels are human-verified. On the 40-trace held-out split, ProvenanceGuard achieves block F1 0.802 and source accuracy 0.858 over 260 source-eligible claims, outperforming source-blind baselines that do not emit claim-to-source IDs. On a harder multi-source benchmark it reaches block F1 0.846, while source-plus-relation accuracy drops to 0.229, showing that exact source ownership remains difficult with semantically close sources. Repair-and-reverify resolves all blocked answers in the full trace set, often via conservative fallback. In 50 controlled clinical conflation probes, ProvenanceGuard detects all injected attribution swaps with no retained wrong attribution. These results show that source attribution is an independent axis for factuality verification in MCP-based agents.

阅读与讨论 → 访问原文 →
05.
PLOS Medicine 2026-06-18

Association between initial benzodiazepine prescribing patterns and time to benzodiazepine discontinuation: A population-based retrospective cohort study

作者:
Nikki Bozinoff↗

by Nikki Bozinoff, Tanya S. Hauck, Robert A. Kleinman, Matthew E. Sloan, Beth A. Sproule, Simone N. Vigod, Jennifer Wyman, Priscila Pequeno, Tara Gomes Background Long-term benzodiazepine use has been associated with increased risk of morbidity and mortality. Preventing long-term use through safer prescribing practices has received little attention to date. We sought to better understand associations between initial prescription characteristics and duration of benzodiazepine use. Methods and findings This was a retrospective population-based cohort study of 1,820,808 adults in Ontario with incident benzodiazepine prescriptions between January 1, 2013 and December 31, 2020, with follow-up to December 31, 2021. The primary exposure was duration of the index prescription (≤7 days—referent group, 8–14 days, 15–30 days, or >30 days). Secondary exposures were: (a) duration of action of index benzodiazepine(s) prescription (short-acting, long-acting or both); (b) number of benzodiazepine dispensed on index (1 or 2+); and (c) mean daily dose of the index prescription in Diazepam Milligram Equivalents (DMEs). The primary outcome was time to benzodiazepine discontinuation in days. Multivariable models were adjusted for age, sex, anxiety, insomnia, and substance use disorders as well as other important comorbidities and socio-demographic characteristics. The median age at index was 53 years (Interquartile Range (IQR) 38–67), and 62.6% were women. The median time to discontinuation in women was 16 days (IQR: 6–29) while the median time to discontinuation in men was 19 days (IQR: 6–29). Lorazepam was the most commonly prescribed benzodiazepine on index (63.9%), followed by clonazepam (17.3%) and diazepam (5.8%). In multivariable Cox Proportional Hazards Models, longer index prescriptions were associated with a lower likelihood of benzodiazepine discontinuation (adjusted Hazard Ratio (aHR) 0.54 (95% Confidence Interval (CI) [0.54,0.54]) for 8–14 days; aHR 0.26 (95% CI [0.25,0.26] for 15–30 days and aHR 0.14 (95% CI [0.14,0.14]) for >30 days, compared to ≤7 days, respectively). Being prescribed two or more benzodiazepines versus 1 was also associated with a reduced likelihood of discontinuation (aHR 0.59 (95% CI [0.57,0.61])), as was being prescribed long-acting benzodiazepines (aHR 0.80 (95% CI [0.80,0.80])) or a combination of short and long acting benzodiazepine (aHR 0.84 (95% CI [0.80,0.88])) versus short-acting benzodiazepines alone. Mean daily doses of >5 to ≤10 DME and >10 to ≤20 DME were associated with an increased likelihood of discontinuation (aHR 1.03 (95% CI [1.03,1.03]); aHR: 1.03 (95% CI [1.03,1.04])), whereas doses >20 DME were associated with a reduced likelihood of discontinuation (aHR 0.98 (95% CI [0.97,0.98])) compared with ≤5 DME. Findings may be subject to bias from unmeasured confounding. Conclusion This large population-based cohort study found that prescribing shorter courses of benzodiazepines, use of a single benzodiazepine, use of a short-acting agent, were associated with reduced likelihood of long-term benzodiazepine use. Findings suggest that simple changes to prescribing practices could reduce prolonged benzodiazepine use and the morbidity and mortality associated with long-term use of these medications.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.AI) 2026-06-25

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

作者:
Antonis Antoniades↗Deepak Nathani↗Ritam Saha↗Alfonso Amayuelas↗Ivan Bercovich↗Zhaotian Weng↗Vignesh Baskaran↗Kunal Bhatia↗William Yang Wang↗

arXiv:2606.25198v1 Announce Type: new Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-based agents need to go beyond just writing code, to mastering the exploration of simultaneously performant, diverse and novel ideas. To this end, we introduce Heuresis, a framework that abstracts the research pipeline into a set of general and composable primitives, enabling open-ended scientific exploration in machine learning research. We implement six search strategies: a greedy baseline, two archive-based (MAP-Elites, Go-Explore), one evolutionary (Islands), and two divergent (Curiosity, Omni), and evaluate them across three axes (Quality, Diversity, and Novelty) on three domains (LLM Pretraining, On-Policy RL, and Model Unlearning), totalling 3,222 scored runs. We find that completely novel ideas are rare. No idea across our scored runs is rated as "Original", and only a few achieve only "Minor Similarity" to prior work. Moreover, novel ideas never approach the highest-performing known-recipe scores. Across all six strategies and three domains, only one such idea lands in the top-10 by quality. We also observed agents resorting to a variety of reward-hacking techniques during execution (40 confirmed fabrications across 1,628 scored runs), and detecting them was necessary to keep the search faithful to the task. Our results show that while current search and Quality-Diversity strategies enable us to steer where the generated ideas land on the quality, diversity, and novelty axes, they do not expand the quality-novelty frontier. Bridging this gap is the open challenge towards the ultimate goal of perpetual, autonomous scientific progress. Code is available at github.com/a-antoniades/Heuresis.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-16

Multi-Granular Node Pruning for Causal Circuit Discovery

作者:
Muhammad Umair Haider↗Hammad Rizwan↗Hassan Sajjad↗A. B. Siddique↗

arXiv:2512.10903v2 Announce Type: replace Abstract: Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited to coarse-grained units such as attention heads or MLP blocks, overlooking finer structures like individual neurons. We propose a node-level pruning framework for circuit discovery that addresses both scalability and granularity limitations. Our method introduces learnable masks across multiple levels of granularity, from entire blocks to individual neurons, within a unified optimization objective. Granularity-specific sparsity penalties guide the pruning process, allowing a comprehensive compression in a single fine-tuning run. Empirically, our approach identifies circuits that are smaller in nodes than those discovered by prior methods; moreover, we demonstrate that many neurons deemed important by coarse methods are actually irrelevant, while still maintaining task performance. Furthermore, our method has a significantly lower memory footprint, 5-10x, as it does not require keeping intermediate activations in the memory to work.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-16

Q-Learning with Fine-Grained Gap-Dependent Regret

作者:
Haochen Zhang↗Zhong Zheng↗Lingzhou Xue↗

arXiv:2510.06647v2 Announce Type: replace-cross Abstract: We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain coarse and fail to fully capture the structure of suboptimality gaps. We address this limitation by establishing fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms. In the UCB-based setting, we develop a novel analytical framework that explicitly separates the analysis of optimal and suboptimal state-action pairs, yielding the first fine-grained regret upper bound for UCB-Hoeffding (Jin et al., 2018). To highlight the generality of this framework, we introduce ULCB-Hoeffding, a new UCB-based algorithm inspired by AMB (Xu et al.,2021) but with a simplified structure, which enjoys fine-grained regret guarantees and empirically outperforms AMB. In the non-UCB-based setting, we revisit the only known algorithm AMB, and identify two key issues in its algorithm design and analysis: improper truncation in the $Q$-updates and violation of the martingale difference condition in its concentration argument. We propose a refined version of AMB that addresses these issues, establishing the first rigorous fine-grained gap-dependent regret for a non-UCB-based method, with experiments demonstrating improved performance over AMB.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-17

Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators

作者:
Yuji Takubo↗Maximilian Adang↗Mac Schwager↗Simone D'Amico↗

arXiv:2606.17317v1 Announce Type: cross Abstract: Real-time trajectory generation for on-orbit robotic servicing is challenging due to the nonlinear coupling between spacecraft bus motion, manipulator dynamics, visibility cone, and trajectory-level safety constraints. This paper studies learning-based warm-starting for sequential convex programming (SCP) in the terminal approach of a space manipulator toward a tumbling target. The proposed framework decomposes the problem into a system center-of-mass translational planning stage and a coupled attitude–manipulator torque-allocation stage, and applies a causal transformer warm-start to the latter, which constitutes the dominant computational bottleneck. Linear and flow matching action decoders are compared under different action-chunking and training dataset sizes, and the resulting warm-starts are evaluated under both cost-optimal and feasibility projection using SCP. Across 300 held-out scenarios, the learned warm-start reduces the second-stage SCP iteration count by up to 28% and the runtime by 23% while preserving the final control-cost distribution. When the learned warm-starts are used for nonconvex feasibility projection, they nearly halve the runtime relative to cost-optimal SCP, while avoiding the catastrophic high-cost tail behavior observed when initialized heuristically. These results indicate that sequence-model warm-starts can improve both the computational efficiency and trajectory robustness of optimization-based terminal guidance for space manipulation.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.AI) 2026-06-11

Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation

作者:
Amir El-Ghoussani↗Michele De Vita↗Ronald Naumann↗Valiseios Belagiannis↗

arXiv:2606.11990v1 Announce Type: cross Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or large labeled datasets to train task-specific sequence models. In this work, we introduce a lightweight learning approach, in which we leverage a frozen pretrained time-series foundation model (TSFM) and combine it with a small regression head for RUL estimation from multivariate sensor streams. More specifically, we use Chronos-2 as a frozen backbone to extract context window features and train a lightweight regression neural network for RUL prediction. Experiments on real-world industrial sensor data from two device types show that Chronos-2 features consistently improve over recurrent, convolutional, Transformer-based, and gradient-boosting baselines under the same preprocessing and evaluation protocol. We further analyze the impact of context length and find that performance improves significantly with longer histories, indicating that TSFM representation offer a practical and data-efficient alternative for RUL estimation in industrial settings.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.LG) 2026-06-17

A tensor network approach for chaotic time series prediction

作者:
Rodrigo Mart\'inez-Pe\~na↗Rom\'an Or\'us↗

arXiv:2505.17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge. Reservoir computing, a neuromorphic-inspired approach, has emerged as a powerful tool for this task. It exploits the memory and nonlinearity of dynamical systems without requiring extensive parameter tuning. However, selecting and optimizing reservoir architectures remains an open problem. Next-generation reservoir computing simplifies this problem by employing nonlinear vector autoregression based on truncated Volterra series, thereby reducing hyperparameter complexity. Nevertheless, the latter suffers from exponential parameter growth in terms of the maximum monomial degree. Tensor networks offer a promising solution to this issue by decomposing multidimensional arrays into low-dimensional structures, thus mitigating the curse of dimensionality. This paper explores the application of a previously proposed tensor network model for predicting chaotic time series, demonstrating its advantages in terms of accuracy and computational efficiency compared to conventional echo state networks. Using a state-of-the-art tensor network approach enables us to bridge the gap between the tensor network and reservoir computing communities, fostering advances in both fields.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-11

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

作者:
Kyle Zheng↗Han Zhang↗Renliang Sun↗Chenchen Ye↗Wei Wang↗

arXiv:2605.02411v2 Announce Type: replace Abstract: A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static retrieval from the initial query alone cannot bridge this gap: the agent's understanding of what it needs evolves during execution, but its tool set does not. We identify this retrieval interface, not planning, as the binding constraint on end-to-end agent performance, and introduce FitText, a training-free framework that makes retrieval dynamic by embedding it directly in the agent's reasoning loop. FitText treats retrieval as test-time evolution of hypotheses: the agent generates natural-language pseudo-tool descriptions (revisable beliefs about the tool it needs), refines them iteratively using retrieval feedback, and explores diverse alternatives through stochastic generation. Memetic Retrieval adds evolutionary selection pressure over candidate descriptions, guided by a tool memory that avoids redundant search. On ToolRet (three domains), FitText's reformulation strategies improve NDCG@5 by 2.7 to 10.6 points over static query retrieval across all base models; on StableToolBench (16,464 APIs) with GPT-5.4-mini, Memetic reaches an 84.3% pooled pass rate, a 26.7-point absolute gain over static query retrieval.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-19

Benchmarking Agentic Review Systems

作者:
Dang Nguyen↗Wanqing Hao↗Yanai Elazar↗Chenhao Tan↗

A new class of agentic review systems are emerging as a remedy to the pressure placed on peer review systems by AI-assisted research, but it is unclear how they should be evaluated. We evaluate two open-source systems (OpenAIReview and coarse), one proprietary system (Reviewer3), and a zero-shot baseline, across six LLMs spanning frontier and efficient models. First, we study whether AI reviews on ICLR/NeurIPS papers track with papers' quality as approximated by external signals such as citations and acceptance decisions. Every system performs above chance in pairwise accuracy, and the best is OpenAIReview + GPT-5.5 at 83.0%. Second, to test whether systems can catch errors with known ground truth, we construct a perturbation benchmark that injects four categories of errors into papers across eight arXiv subject classes and measure detection recall. The strongest configuration (OpenAIReview + GPT-5.5) catches 71.6% of injected errors, leaving substantial room for improvement. The union of detections across six models reaches 83.3% recall, suggesting different models detect different errors and better harness design can potentially increase performance. Beyond these benchmarks, we study a public deployment of OpenAIReview with real users. Votes on its comments skew positive at 1.44 to 1, and the most common complaints are about false positives and minor nitpicks. Together, by evaluating full review systems backed by state-of-the-art models on real research papers, we show that while AI reviews still have room for improvement, they can already track human quality judgments well, catch important errors, and earn positive feedback from real users.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.CL) 2026-06-15

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

作者:
Teng Chen↗Sheng Xu↗Feixiang Guo↗Xiaoyu Wang↗Qingqing Gu↗Hongyan Li↗Luo Ji↗

Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose Rabtriever, which independently encodes queries and documents, while providing comparable cross query-document comprehension capabilities to rerankers. We start from training a LLM-based generative reranker, which puts the document prior to the query and prompts the LLM to generate the relevance score by log probabilities. We then employ it as the teacher of an on-policy distillation framework, with Rabtriever as the student to reconstruct the teacher's contextual-aware query embedding. To achieve this effect, Rabtriever is first initialized from the teacher, with parameters frozen. The Joint-Embedding Predictive Architecture (JEPA) paradigm is then adopted, which integrates a lightweight, trainable predictor between LLM layers and heads, projecting the query embedding into a new hidden space, with the document embedding as the latent vector. JEPA then minimizes the distribution difference between this projected embedding and the teacher embedding. To strengthen the sampling efficiency of on-policy distillation, we also add an auxiliary loss on the reverse KL of LLM logits, to reshape the student's logit distribution. Rabtriever optimizes the teacher's quadratic complexity on the document length to linear, verified both theoretically and empirically. Experiments show that Rabtriever outperforms different retriever baselines across diverse rationale-based tasks, including empathetic conversations and robotic manipulations, with minor accuracy degradation from the reranker. Rabtriever also generalizes well on traditional retrieval benchmarks such as MS MARCO and BEIR, with comparable performance to the best retriever baseline.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-17

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

作者:
Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-24

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

作者:
Zixin Ding↗Shaghayegh Emam↗Giovanna Salvi↗Cecilia Tosciri↗Abhijith Gandrakota↗Jennifer Ngadiuba↗Nhan Tran↗Christian Herwig↗David W. Miller↗Yuxin Chen↗

arXiv:2606.23993v1 Announce Type: cross Abstract: High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (triggering) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48\% ($H_T$) and 28\% (AD), with a cumulative gain of up to 2\% in signal efficiency on those in-tolerance intervals. Transferring from simulation to real collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56\% ($H_T$) and 28\% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the first demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO\_LHC.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CL) 2026-06-12

Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

作者:
Xinxin Li↗Huiyao Chen↗Meishan Zhang↗Yunxin Li↗Zulong Chen↗Zhibo Ren↗Xiaoqing Dong Baotian Hu↗Min Zhang↗

Automatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conversation-level contextual evidence. Existing ASR correction methods often rely on the current hypothesis or concatenate raw dialogue history. In such contexts, sparse correction evidence can be difficult to locate amid redundancy and noise. Addressing these challenges, we propose an ontology memory-augmented ASR correction framework for long text-speech interleaved conversations. The framework organizes preceding interaction history into a dynamically updatable ontology memory, where entities, terminology, surface variants, potential ASR confusions, and semantic relations are stored as retrievable nodes for context-grounded correction. To evaluate this setting, we construct RAMC-Corr, a dataset derived from MAGIC-RAMC for long-range ASR correction with grounded context. Experiments on RAMC-Corr show that our method improves over direct correction in 9 out of 10 paired backbone-setting combinations and encourages more selective and evidence-grounded corrections for context-dependent ASR errors.

阅读与讨论 → 访问原文 →
18.
medRxiv (Medicine) 2026-06-22

MinderCare: protocol for a mixed-methods evaluation of a digitally enabled dementia care service.

作者:
Jeyasingh-Jacob↗Tecilla↗Cro↗Lai↗Frigerio↗Joby↗Chavarro Novoa↗Fabusoro↗Rasulo↗James↗Amade Cassimo↗Hariss↗…

Introduction and aims Dementia is a growing public health challenge affecting millions of people worldwide. It is a progressive condition that increases the risk of infections, falls, hospital admissions, dependence in activities of daily living, safety issues such as wandering, care home transfers, and death. New ways of supporting people living with dementia (PLWD) at home are urgently needed. We describe the MinderCare study which evaluates a digitally enabled care model that integrates low-burden sensor-based remote monitoring within a nurse-led clinical service. Methods and analysis In this mixed-methods study, we will recruit 100 people with confirmed or suspected dementia living at home and deploy the Minder remote monitoring system for at least 12 months. A detailed characterisation of the cohort will be obtained, including cognition, frailty, participant and carer wellbeing, functioning, and quality of life. The feasibility, acceptability, sustainability, and resource requirements of the service will also be assessed. Low-cost sensors provide information about behaviour, environment and physiology from the home. Machine-learning algorithms have been used to develop digital biomarkers of infection, sleep, night-time behaviours, daily activities and routines, and the effects of clinical events and treatment. These will be assessed through clinical reports of sensor-derived data that include anomaly alerts provided to the clinical teams. Algorithms will be assessed for their clinical utility and acceptability. The comparative-effectiveness component will be designed as a target trial emulation using linked electronic health-record data to construct a time-indexed external usual-care control cohort. The primary comparative outcome will be Days Alive and Out of Hospital (DAOH) over 12 months from the activation-index date, with healthcare utilisation, costs, institutionalisation and mortality assessed as secondary outcomes. DAOH and estimated MinderCare effects will also be examined across prespecified strata of baseline inpatient utilisation. Ethics and dissemination Ethical approval has been granted by the North East Newcastle and North Tyneside 2 Research Ethics Committee, and the study has received confirmation of capacity and capability by the Imperial College Healthcare NHS Trust. Study findings will be disseminated to patients, health and social care professionals, and policymakers through peer-reviewed publications and conference presentations. Study registration number: ISRCTN14997677 and NIHR portfolio CPMSID 63023.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CL) 2026-06-16

QK-Normed MLA: QK normalization without full key caching

作者:
Yizhou Han↗Yao Zhao↗Jun Zhou↗Longfei Li↗Ruoyu Sun↗

Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Attention (MLA). MLA achieves efficient decoding by caching low-dimensional latent states instead of full keys, whereas post-projection QK RMSNorm appears to require the fully projected key for every cached token. We show this apparent incompatibility is an implementation artifact, not an architectural constraint. RMSNorm decomposes into a static affine weight and a dynamic scalar RMS statistic. The static key-side weight can be absorbed into the MLA query-side projection; the dynamic key statistic reduces to one inverse-RMS scalar per token and KV group. The resulting formulation is exactly equivalent to explicit post-projection QK RMSNorm in exact arithmetic and preserves MLA's latent decode path. In our 400M runs trained for up to 100B tokens, QK-Normed MLA achieves lower training loss and better downstream accuracy than QK clipping, while H800 decode benchmarks show less than 2% latency overhead up to 256k context. These results make QK normalization a practical stabilization option for MLA models without requiring full-key caching.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.LG) 2026-06-16

GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization

作者:
Yaohui Cai↗Vesal Bakhtazad↗Cunxi Yu↗Zhiru Zhang↗

arXiv:2602.20427v2 Announce Type: replace Abstract: Efficient operator scheduling is a fundamental challenge in software compilation and hardware synthesis. While recent differentiable approaches have sought to replace traditional ones like exact solvers or heuristics with gradient-based search, they typically rely on categorical distributions that fail to capture the ordinal nature of time and suffer from a parameter space that scales poorly. In this paper, we propose a novel differentiable framework, GauS, that models operator scheduling as a stochastic relaxation using Gaussian distributions, which fully utilize modern parallel computing devices like GPUs. By representing schedules as continuous Gaussian variables, we successfully capture the ordinal nature of time and reduce the optimization space by orders of magnitude. Our method is highly flexible to represent various objectives and constraints, which provides the first differentiable formulation for the complex pipelined scheduling problem. We evaluate our method on a range of benchmarks, demonstrating that Gaus achieves Pareto-optimal results.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-25

An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz

作者:
Lea Roxanne Muth↗Marian Margraf↗

arXiv:2606.25608v1 Announce Type: cross Abstract: This paper presents a novel approach to perform semi-automated BSI IT-Grundschutz certification using a MultiLarge Language Model system (MLS) with Hybrid RetrievalAugmented Generation (HybridRAG). Facing the challenges of the Network and Information Security Directive 2 (NIS2) directive, a shortage of specialists, and high implementation costs, our MLS architecture aims to increase efficiency, reduce costs, and support certifiers in maintaining the quality of security concepts while meeting the increased demand for certifications of newly affected companies. The system combines Large Language Models (LLMs) and Knowledge Graphs (KGs) to support different phases of the certification process, including protection needs assessment, modeling, IT-Grundschutz check, measure consolidation, and subsequent realization. Our architecture addresses the growing demand for security concepts and offers an approach to handle the digital security challenges introduced by NIS2.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CV) 2026-06-16

Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models

作者:
Amy Rafferty↗Rishi Ramaesh↗Ajitha Rajan↗

Deep learning models for chest X-ray diagnosis are constrained by limited coverage of clinically meaningful concept combinations in publicly available training datasets. While synthetic image generation has been explored to increase data diversity, existing methods rarely enforce clinical or anatomical constraints, limiting utility for improving model reliability. We propose CARPA, a clinically aware and anatomically grounded framework for synthetic chest X-ray generation that applies targeted perturbations to clinical concept vectors while preserving anatomical structure. By producing anatomically faithful synthetic images with controlled concept insertions and deletions, CARPA expands clinically relevant concept coverage. We evaluate CARPA across seven backbone architectures by fine-tuning models on synthetic subsets and testing on a held-out MIMIC-CXR benchmark. Compared to prior concept perturbation approaches, fine-tuning on CARPA-generated images consistently improves precision-recall performance, reduces predictive uncertainty, and improves model calibration. Structural and semantic analyses demonstrate high anatomical fidelity, strong concept alignment, and low semantic uncertainty. Evaluation by two expert radiologists further confirms realism and clinical agreement. Together, these results show that anatomically grounded concept perturbations enable more effective use of synthetic data, improving both performance and reliability of chest X-ray classification models and supporting safer clinical deployment.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-12

C-QUERI: Congressional Questions, Exchanges, and Responses in Institutions Dataset

作者:
Manjari Rudra↗Daniel Magleby↗Sujoy Sikdar↗

Questions in political interviews and hearings serve strategic purposes beyond information gathering including advancing partisan narratives and shaping public perceptions. However, these strategic aspects remain understudied due to the lack of large-scale datasets for studying such discourse. Congressional hearings provide an especially rich and tractable site for studying political questioning: Interactions are structured by formal rules, witnesses are obliged to respond, and members with different political affiliations are guaranteed opportunities to ask questions, enabling comparisons of behaviors across the political spectrum. We develop a pipeline to extract question-answer pairs from unstructured hearing transcripts and construct a novel dataset of committee hearings from the 108th–117th Congress. Our analysis reveals systematic differences in questioning strategies across parties, by showing the party affiliation of questioners can be predicted from their questions alone. Our dataset and methods not only advance the study of congressional politics, but also provide a general framework for analyzing question-answering across interview-like settings.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.LG) 2026-06-16

Scalable and Interpretable Representation Alignment with Ordinal Similarity

作者:
Diogo Soares↗Pankhil Gawade↗Andrea Dittadi↗Ewa Szczurek↗

arXiv:2606.16379v1 Announce Type: new Abstract: Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they lack interpretability due to shifting baselines, lack robustness to outliers, and are computationally intractable for large datasets, forcing reliance on heuristic approximations. To address this, we develop an ordinal-similarity framework, instantiated by the Triplet (TSI) and Quadruplet (QSI) Similarity Indices, which measure alignment by quantifying the consistency of ordinal relationships. We theoretically demonstrate this formulation is inherently interpretable, robust to outliers, and computationally efficient. Finally, we establish a formal equivalence between TSI and local neighborhood alignment, measured by Mutual Nearest Neighbors. Empirically, we validate these properties and show that ordinal similarity offers a scalable approach to measuring alignment, enabling practitioners to better understand and design representations.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.AI) 2026-06-24

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

作者:
Xiao Zhou↗Siyue Zhang↗Yilun Zhao↗Jinbiao Wei↗Tingyu Song↗Arman Cohan↗Chen Zhao↗

arXiv:2606.24551v1 Announce Type: new Abstract: Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with differences in tasks, initial states, verifiers, and permitted actions. We introduce a matched execution-layer benchmark of 440 desktop tasks across 18 applications and 12 workflow categories, where screen-only GUI agents and skill-mediated CLI agents receive identical goals, states, and final-state verifiers while being restricted to modality-native actions. In this controlled setting, the strongest GUI agent reaches a 59.1% full pass rate, outperforming the strongest original-skill CLI agent at 48.2%; however, verifier-guided skill augmentation raises CLI success to 69.3%, showing that much of the CLI deficit comes from incomplete skill coverage rather than model capability alone. These results suggest that GUI and CLI expose different execution bottlenecks: GUI agents are limited by reliable grounded interaction over long-horizon workflows, whereas CLI agents are limited by the coverage and scalability of their skill interfaces.

阅读与讨论 → 访问原文 →