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.
Nature (Science) 2026-06-09

Scientists have a bad case of AI FOMO, <i>Nature</i> poll reveals

作者:
Mohana Basu↗

Almost half of the scientists who responded said that they feel broadly negative towards artificial intelligence, but they think that some tools are better than others. Almost half of the scientists who responded said that they feel broadly negative towards artificial intelligence, but they think that some tools are better than others.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-16

Trust-Region Diffusion Policies for Massively Parallel On-Policy RL

作者:
Huy Le↗Onur Celik↗Denis Blessing↗Tai Hoang↗Claas A Voelcker↗Axel Brunnbauer↗Felix Richter↗Michael Volpp↗Gerhard Neumann↗

arXiv:2606.15260v1 Announce Type: cross Abstract: Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizations. Diffusion models provide a more expressive policy class and have shown strong performance on challenging control problems, yet most diffusion-based RL methods are designed for offline or off-policy training. In this work, we ask whether diffusion policies can be trained effectively in the massively parallel, on-policy regime. To this end, we introduce Trust-region Diffusion Policies (TruDi), which enables diffusion policies for on-policy RL with massively parallel simulations. This setting is particularly challenging because the data distribution changes quickly across updates, making stable training with complex policies difficult. TruDi addresses this by integrating a trust-region optimization rule to enforce a KL-divergence constraint over the entire diffusion trajectory. Empirically, we evaluate TruDi on a diverse set of 4 massively parallel RL benchmarks comprising a total of 73 tasks. Across these tasks, TruDi consistently outperforms or is on-par with strong baselines on standard tasks and achieves clear gains on more challenging humanoid control tasks, establishing a strong new baseline for massively parallel on-policy RL.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.LG) 2026-06-18

Latent-Conditioned Parameterized Quantum Circuits as Universal Approximators for Distributions over Quantum States

作者:
Quoc Hoan Tran↗Koki Chinzei↗Yasuhiro Endo↗Hirotaka Oshima↗

arXiv:2605.28690v3 Announce Type: replace-cross Abstract: Many applications in quantum simulation, quantum chemistry, and quantum machine learning require not a single quantum state but an ensemble of states characterizing the heterogeneity of a target system. Preparing such ensembles state-by-state is prohibitive in both variational and fault-tolerant settings, thereby motivating a generative modeling approach. We introduce latent-conditioned parameterized quantum circuits (LPQCs), a hybrid quantum-classical framework in which classical neural networks map a latent variable sampled from a prior distribution to the parameters of a parameterized quantum circuit. We prove that LPQCs are universal approximators for probability measures over density operators in the 1-Wasserstein distance, extending classical universal approximation theorems to the quantum-distribution setting. We additionally introduce a multimodal latent prior and a mixture-of-experts circuit architecture, and show empirically that the latent-conditioned parameterization alleviates the barren plateau problem during optimization, a behavior for which we provide rigorous partial guarantees. Numerical experiments validate the framework on a synthetic multi-cluster ensemble of mixed quantum states and on a QM9-derived ensemble of 3-D molecular structures. In these tasks, LPQC outperforms recent quantum generative baselines and matches the generation quality of a classical neural-network baseline, while requiring an output dimension that grows only linearly with the number of qubits rather than exponentially. By leveraging classical expressivity in the latent space, LPQCs offer a tractable route to quantum generative modeling.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.LG) 2026-06-19

The Hidden Cost of Approximation in Online Mirror Descent

作者:
Ofir Schlisselberg↗Uri Sherman↗Tomer Koren↗Yishay Mansour↗

arXiv:2511.22283v2 Announce Type: replace Abstract: Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms in optimization, machine learning and sequential decision-making. The OMD iterates are defined as solutions to optimization subproblems which, oftentimes, can be solved only approximately, leading to an inexact version of the algorithm. Nonetheless, existing OMD analyses typically assume an idealized error free setting, thereby limiting our understanding of performance guarantees that should be expected in practice. In this work we initiate a systematic study into inexact OMD, and uncover an intricate relation between regularizer smoothness and robustness to approximation errors. When the regularizer is uniformly smooth, we establish a tight bound on the excess regret due to errors. Then, for barrier regularizers over the simplex and its subsets, we identify a sharp separation: negative entropy requires exponentially small errors to avoid linear regret, whereas log-barrier and Tsallis regularizers remain robust even when the errors are only polynomial. Finally, we show that when the losses are stochastic and the domain is the simplex, negative entropy regains robustness-but this property does not extend to all subsets, where exponentially small errors are again necessary to avoid suboptimal regret.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CV) 2026-06-16

BadWorld: Adversarial Attacks on World Models

作者:
Linghui Shen↗Mingyue Cui↗Xingyi Yang↗

Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-truth future videos and cannot predict subsequent user controls. We introduce BadWorld, a label-free adversarial framework tailored for autoregressive VWMs that systematically overcomes both constraints. First, to bypass the need for future supervision, we propose a self-supervised velocity attack that directly disrupts the early denoising dynamics of the model. Second, to ensure the attack generalizes across unpredictable user actions, we formulate a trajectory-adaptive bi-level optimization that actively mines hard control sequences to forge control-agnostic perturbations. Evaluated on representative VWMs with continuous and discrete controls, BadWorld exposes severe structural fragility. Visually indistinguishable adversarial images reliably trigger catastrophic degradation in future rollouts, leading to incomplete denoising, structural collapse, and control inconsistency. These findings reveal critical risks for deploying VWMs in safety-critical systems while highlighting a practical mechanism for privacy protection.

阅读与讨论 → 访问原文 →
06.
Nature (Science) 2026-06-09

How ice forms is a mystery — now scientists are cracking the case

作者:
Mark Buchanan↗

Theories about how ice crystals grow in cooling liquids are wildly inaccurate when compared with experimental data, but studies are starting to illuminate the earliest moments in freezing. Theories about how ice crystals grow in cooling liquids are wildly inaccurate when compared with experimental data, but studies are starting to illuminate the earliest moments in freezing.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.LG) 2026-06-19

QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem

作者:
Merijn Moody↗Zier Mensch↗Miranda C. N. Cheng↗Peter G. Bolhuis↗Max Welling↗

arXiv:2606.19947v1 Announce Type: cross Abstract: Reliable quantum control in the presence of decoherence requires policies that combat the effect of environmental noise on the controlled dynamics. Open quantum systems under continuous monitoring generate classical measurement records whose drift depends on the noise experienced by the system; the records of two evolutions sharing the same decoherence channels differ only in this drift, so Girsanov's theorem yields a closed-form, differentiable estimator of the KL divergence between their trajectory distributions. We instantiate this estimator with two physically motivated reference measures, yielding two regularizers that both drive the system toward states where the effects of decoherence are minimal: the Wiener KL (KL_W), which is empirically more effective under certain conditions on the noise model, and the drift-variance regularizer (R_DV), which works for all noise models. Both are qualitatively distinct from existing penalties on control fluence or smoothness: they penalize the observable consequences of control on the decoherence channels rather than the control amplitude itself. The regularizers outperform unregularized gradient-based and reinforcement-learning baselines across a range of open quantum systems – including single- and multi-qubit benchmarks and a multi-qubit chain calibrated to a published snapshot of the IBM Kingston processor – along several axes of evaluation: final-state fidelity, robustness to mismatch in the assumed noise model (gains grow from +17 pp at training noise to +27 pp under 2.5x noise mismatch), and occupation of forbidden states. The regularizers reduce infidelity by up to 50%, with ~16% gains on the calibrated IBM Kingston chain.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-15

Utility-Constrained Policy Optimization

作者:
Mehrdad Moghimi↗Bernardo Avila Pires↗

arXiv:2606.14029v1 Announce Type: new Abstract: Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints. This can be problematic: For example, CMDPs allow for optimal solutions that, in order to satisfy the risk-neutral constraints, mix infrequent catastrophic behaviors and frequent, overly conservative ones. Moreover, prior empirical results suggest that enforcing stricter, risk-sensitive constraints can improve performance even under risk-neutral evaluation. The natural framework to incorporate risk-sensitive constraints is utility-constrained MDPs (UCMDPs), but no practical solutions for this problem existed. In this work, we introduce a simple yet powerful methodology for UCMDPs and constrained RL. Besides allowing for risk-sensitive constraints, our framework does not require us to fix constraint limits in advance of training the agent, provided that a sensible range is known. This increases policy flexibility and, in practice, allows for adjustments to these limits at no extra training cost. Besides benefiting from the generality of the framework, our agent shows strong performance in practice, consistently matching or outperforming existing baselines in several Safety Gymnasium benchmark tasks.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-18

Optimal scenario design for climate emulation

作者:
Christopher B. Womack↗Shahine Bouabid↗Andrei Sokolov↗Popat Salunke↗Glenn Flierl↗Sebastian D. Eastham↗Noelle E. Selin↗

arXiv:2606.19302v1 Announce Type: cross Abstract: As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training datasets themselves can be optimized to improve generalization. We introduce a method to create datasets that produce emulators capable of generalizing to new, structurally different scenarios absent from the training data. We use a differentiable Simple Climate Model (SCM) to calculate the sensitivity of emulator loss to perturbations in the training data, iteratively updating the training data to maximize emulator skill. For an SCM, training on one scenario optimized in this fashion outperforms an emulator trained on six standard ScenarioMIP pathways. We achieve this higher predictive skill despite training on a smaller dataset, finding that our emulator successfully isolates distinct physical behaviors of different climate forcing agents (e.g., greenhouse gases vs. aerosols) without single-forcing runs. We then demonstrate that scenarios optimized using an SCM, when used to drive an intermediate-complexity climate model, produce a training dataset that yields a more skillful emulator than training on ScenarioMIP outputs. Our results suggest that, in the compute-constrained environment of running full-scale climate models, generating a small number of dynamically rich scenarios provides greater marginal value for emulation and characterizing system responses than expanding the suite of traditional emissions pathways.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CL) 2026-06-18

Steerable Cultural Preference Optimization of Reward Models

作者:
Minsik Oh↗Advit Deepak↗Sophie Wu↗Douwe Kiela↗Ekaterina Shutova↗

It is essential for large language model (LLM) technology to serve many different cultural sub-communities in a manner that is acceptable to each community. However, research on LLM alignment has so far predominantly focused on predicting a unified response preference of annotators from certain regions. This paper aims to advance the development of alignment models with a more global outlook, that are able to accurately represent the preferences of subcommunities and do not exhibit excessive bias towards any of them. We focus on the development of reward models for this purpose and present a novel reward model training algorithm (SCPO) that can incorporate diverse cultural preferences in a balanced manner. Our method results in performance increases of the minority reward model of up to 7 points over the baseline model across two datasets, PRISM and GlobalOpinionQA, and across 7 countries. SCPO is up to 280% more training data-efficient than full-data finetuning of reward models. In addition, we perform analysis of bias by separately evaluating on the preference of subcommunities and show that excessive bias is mitigated via our weighting method. Our code is available at https://github.com/minsik-ai/Steerable-Cultural-Preference

阅读与讨论 → 访问原文 →
12.
arXiv (CS.LG) 2026-06-16

Decomposing one-class support vector machine into an ensemble of one-data support vector machines

作者:
Toshitaka Hayashi↗Dalibor Cimr↗Hamido Fujita↗Richard Cimler↗

arXiv:2606.16002v1 Announce Type: new Abstract: One-class classification (OCC) is a classification problem in which the training data contains only one class. The one-class support vector machine (OCSVM) is one of the most competitive OCC algorithms. However, OCSVM has scalability issues with large-scale datasets. This paper proposes the acceleration strategy of OCSVM. The idea is to decompose the dataset into samples and train OCSVM models for single data points. Subsequently, ensemble learning is applied to combine all models to compute the OCSVM model for the dataset. In addition, further acceleration is achieved through a data-reduction strategy with an OCSVM model trained on the average of the training samples. The experiment compared the proposal and traditional OCSVM using the Python package. The proposed strategy is faster than traditional OCSVM, while achieving similar classification results. Moreover, the proposed strategy can create one-to-one correspondence between samples and models. Source code is uploaded at https://github.com/ToshiHayashi/ODSVM

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-12

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

作者:
Jiacheng Chen↗Xinyu Zhang↗Shunkai Zhang↗Yanmohan Wang↗Lin Li↗Tiancheng Qin↗Qin Wang↗Zhengmao Zhu↗Tianle Li↗Jingyang Li↗Zehan Li↗Binyang Jiang↗…

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

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

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

作者:
Octavio Pappalardo↗

arXiv:2601.19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing their own goals. The core challenge lies in how to effectively generate, select, and learn from such goals. Our focus is on broad distributions of downstream tasks where solving every task zero-shot is infeasible. Such settings naturally arise when the target tasks lie outside of the pre-training distribution or when their identities are unknown to the agent. In this work, we (i) optimize for efficient multi-episode exploration and adaptation within a meta-learning framework, and (ii) guide the training curriculum with evolving estimates of the agent's post-adaptation performance. We present ULEE, an unsupervised meta-learning method that combines an in-context learner with an adversarial goal-generation strategy that maintains training at the frontier of the agent's capabilities. On XLand-MiniGrid benchmarks, ULEE pre-training yields improved exploration and adaptation abilities that generalize to novel objectives, environment dynamics, and map structures. The resulting policy attains improved zero-shot and few-shot performance, and provides a strong initialization for longer fine-tuning processes. It outperforms learning from scratch, DIAYN pre-training, and alternative curricula. Code is available at: https://github.com/Octavio-Pappalardo/ulee-jax

阅读与讨论 → 访问原文 →
15.
arXiv (quant-ph) 2026-06-11

Large Fluctuations in Open Quantum Systems

作者:
V. Yu. Mylnikov↗S. O. Potashin↗A. Kamenev↗

arXiv:2606.11822v1 Announce Type: new Abstract: We study statistics of atypical measurement outcomes in the steady states of driven open quantum systems. In equilibrium, the probability distribution over the phase space, as encoded in, e.g., the Wigner function, is analytic in the phase-space coordinates. We show that this property is generically lost in driven dissipative systems: their {\it large-deviation function} develops lines and surfaces across which its derivatives are discontinuous. As an illustrative example, we consider a parametrically driven Kerr oscillator coupled linearly and/or nonlinearly to a dissipative bath. Rare fluctuations in the amplitude and phase of the induced oscillations are governed by semiclassical instanton trajectories of the corresponding Keldysh-Lindblad action. We demonstrate that a given fluctuation can be realized through multiple distinct instanton trajectories. The competition between these trajectories leads to abrupt switching of the dominant instanton and, consequently, to non-analytic features in the large-deviation function.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-11

LaQual: An Automated Framework for LLM App Quality Evaluation

作者:
Yan Wang↗Xinyi Hou↗Junjun Si↗Yanjie Zhao↗Weiguo Lin↗Haoyu Wang↗

arXiv:2508.18636v2 Announce Type: replace-cross Abstract: Representing a new paradigm in software distribution, LLM app stores are rapidly emerging, offering users diverse choices for content generation, coding assistance, education, and more. However, current ranking and recommendation mechanisms in LLM app stores predominantly rely on static metrics, such as user interactions and favorites, making it challenging for users to efficiently identify high-quality apps. At the same time, current academic research focuses on specific vertical fields and lacks a general, automated evaluation framework applicable to the diverse LLM app ecosystem. To address the above challenges, we present LaQual, an automated framework for LLM app quality evaluation. LaQual integrates three key stages: (1) LLM app labeling and hierarchical classification for precise scenario mapping; (2) static indicator evaluation using time-weighted user engagement and functional capability indicators to filter low-quality apps; and (3) dynamic scenario-adapted evaluation, where an LLM generates scenario-specific evaluation metrics, scoring criteria, and tasks for comprehensive quality evaluation. Experiments on a mainstream LLM app store demonstrate the effectiveness of LaQual. Its automated scores show high consistency with human judgments. Through effective screening, LaQual can reduce the candidate LLM app pool by 66.7% to 81.3%. User studies further validate its significant outperformance over baseline systems, particularly in comparison efficiency (mean 5.45 vs. 3.30) and value of explanatory information (4.75 vs. 2.25). These results demonstrate that LaQual provides a scalable, objective, and user-centric solution for high-quality discovery and recommendation of LLM apps in real-world scenarios.

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

LSTM based IoT Device Identification

作者:
Kahraman Kostas↗

arXiv:2304.13905v2 Announce Type: replace-cross Abstract: While the use of the Internet of Things is becoming more and more popular, many security vulnerabilities are emerging with the large number of devices being introduced to the market. In this environment, IoT device identification methods provide a preventive security measure as an important factor in identifying these devices and detecting the vulnerabilities they suffer from. In this study, we present an end-to-end machine learning pipeline that identifies IoT devices in the Aalto university dataset (IoT devices captures) using Long Short-Term Memory (LSTM) networks. Raw network packet captures (PCAP) are processed into 25 engineered features, which are then arranged as sliding-window time-series sequences. We systematically evaluate sequence lengths from 2 to 20, reporting that performance improves approximately linearly up to length 6 and thereafter in a wave-like pattern, reaching its peak at length 18. On the final held-out test set with the optimal configuration, the model achieves an accuracy of 79.85% and a macro-averaged F1-score of 75.70% across 27 device classes.

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

Antimicrobial-resistant E. coli in human, animal and environmental reservoirs in rural Bangladeshi households with young children

作者:
Tazin↗Hossain↗M. S↗Haque↗Rahman↗M. H↗Tabassum↗Anderson↗Hanif↗Barratt Heitmann↗G. R↗Miah↗…

In low-income countries, ESBL-producing Escherichia coli (ESBL-EC) is frequently detected in humans, animals and household environments, indicating widespread exposure to antimicrobial resistance (AMR). Established risk factors such as antibiotic use do not explain the high community carriage of AMR in all settings; identifying the dominant exposure pathways can inform interventions against AMR. We aimed to investigate (i) animal-human-environment sharing of AMR by assessing associations between the abundance of ESBL-EC in the household environment, domestic animal feces and young children's stool and (ii) household factors associated with ESBL-EC abundance in these reservoirs. We enrolled 112 households from the CRADLE trial in rural Bangladesh. We enumerated ESBL-EC in drinking water, food, child hand rinses, outdoor soil, indoor floor swabs, chicken and cow feces, and stool from children aged 6 months. We recorded indicators of sanitation, animal ownership/management, human and animal antibiotic use, and child exposure behaviors using structured questionnaires and spot checks. The highest prevalence of ESBL-EC was in child stool (95.6%) and animal feces (82.3-96.9%), followed by soil (48.2%) and floors (36.6%); < 10% of food, child hands and drinking water harbored ESBL-EC. The abundance of ESBL-EC in child stool was not associated with its abundance in any sampled matrix; the abundance in chicken but not cow feces showed positive correlations with soil, floors, child hands, and drinking water (correlation coefficients: 0.19-0.39, p-values < 0.05). Higher-quality latrines (improved, pour-flush, with slab) were associated with lower ESBL-EC abundance across matrices; unsafe animal management (animals roaming or spending the night inside the home) was associated with higher abundance. Child antibiotic use and exposure behaviors (soil ingestion, time spent on floor) were not associated with ESBL-EC abundance in child stool. We observed high AMR colonization among young children and domestic animals in rural Bangladesh not explained by traditional fecal-oral exposure pathways. Future studies should explore additional pathways and assess whether sanitation and animal management improvements can reduce AMR.

阅读与讨论 → 访问原文 →
20.
medRxiv (Medicine) 2026-06-16

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 →
21.
arXiv (math.PR) 2026-06-19

Establishing an $\Omega(\sqrt{d})$ complexity lower bound for PDMP samplers and how to break it: a sub-$\sqrt{d}$ algorithm for Gaussian-tailed targets

作者:
Augustin Chevallier↗

arXiv:2606.19909v1 Announce Type: cross Abstract: Despite the theoretical appeal of their non-reversibility, to date, no Piecewise Deterministic Markov Process (PDMP) samplers have been developed that scale better than $\mathcal{O}(\sqrt{d})$ in computational complexity with respect to the target dimension $d$. We prove that this is a fundamental limitation by establishing an $\Omega(\sqrt{d})$ lower bound on the algorithmic complexity of PDMP samplers in a standard setup. By relaxing the assumption that the target density must remain invariant at all continuous times, we then demonstrate how to bypass this barrier. Specifically, we introduce a novel PDMP sampling scheme and show that it achieves an empirical complexity of $\mathcal{O}(d^\alpha)$, where $\alpha \in [0.2, 0.3]$ for Gaussian-tailed targets. In addition, this PDMP scheme is locally adaptive in both trajectory length and distance between velocity updates.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-15

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

作者:
Di Cao↗Dongjie Fu↗Hai Yu↗Siqi Zheng↗Xu Tan↗Tao Jin↗

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

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

IVIE: A Neuro-symbolic Approach to Incremental and Validated Generation of Interactive Fiction Worlds

作者:
Micaela Vaucher↗Santiago Silveira↗Santiago G\'ongora↗Luis Chiruzzo↗

Computational creativity in Interactive Fiction faces a fundamental tension: Large Language Models (LLM) may produce creative narratives but struggle with world coherence, while symbolic systems ensure consistency but lack creative flexibility. We present IVIE (Incremental & Validated Interactive Experiences), a neuro-symbolic approach to generating complete and playable interactive fiction worlds from scratch. Building upon PAYADOR's neuro-symbolic framework, IVIE implements a four-stage incremental generation pipeline that delegates creative decisions–setting and character creation, puzzle design–to LLMs while grounding the world state through symbolic validation. The system generates worlds with interconnected locations, functional items, non-player characters, and coherent puzzles, all structured around a central goal-oriented architecture. Human evaluation shows the approach generates immersive, thematically coherent worlds with high player engagement. Results seem to indicate that the neuro-symbolic approach successfully balances flexibility with narrative coherence: symbolic validation grounds LLM generation without eliminating generative freedom. However, challenges remain: LLM inconsistencies occasionally bypass puzzle constraints, and objective validation gaps allow some structurally impossible goals. We identify key design considerations for future neurosymbolic interactive storytelling systems, particularly regarding LLM capabilities and their limitations.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.AI) 2026-06-12

An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics

作者:
Zhe Liu↗Huanbo Jin↗Zhaohui Du↗Zhe Wang↗He Xu↗Peijia Li↗Jiaming Gu↗Quan Lu↗Qi Wang↗Bin Ji↗Ting Xiao↗

arXiv:2606.12936v1 Announce Type: cross Abstract: Wet-lab robots can improve the reproducibility, throughput, and safety of biomedical experiments, but scaling their learning requires customizable simulators for safe and reproducible task generation, open editable laboratory assets, and efficient pipelines that turn limited demonstrations into usable training data. We present Pipette, an embodied simulation platform, benchmark, and data-efficient augmentation framework for wet-lab robot learning. Pipette releases over 43 open-source and re-editable wet-lab assets, together with an extensible asset-building pipeline. A key component of Pipette is its simulation-based data augmentation pipeline, replaying human demonstrations in simulation, applies lighting, camera, speed, and action perturbations, and filters generated episodes with automatic task success checks, rapidly expanding usable training data from limited manual demonstrations. We further introduce an 11-task wet-lab embodied benchmark covering sample handling, culture-ware manipulation, device operation, and precision placement. With only 30 demonstrations per task, ACT achieves 65.5% average success rate, while simulation augmentation improves SmolVLA from 44.1% to 74.7% and {\pi}0 from 40.4% to 46.5%, validating the effectiveness of Pipette for data-efficient VLA training and evaluation. Pipette also supports natural-language-driven scene construction and task registration, lowering the barrier for non-expert users to define new wet-lab robotic tasks.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.AI) 2026-06-19

Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing

作者:
Kianoush Aqabakee↗Leonardo Stella↗

arXiv:2606.20087v1 Announce Type: new Abstract: Additive manufacturing process optimization requires precise parameter control to minimize defects such as porosity. Traditional reinforcement learning (RL) approaches using discrete action spaces suffer from slow convergence and susceptibility to local optima, limiting their effectiveness for high-precision manufacturing tasks. This study addresses these limitations by employing a continuous action space combined with a novel architecture that integrates a multi-head attention mechanism with the Soft Actor-Critic (SAC) algorithm. The attention-based feature extractor enhances the agent's ability to capture subtle variations in low-dimensional input features, enabling more effective exploration-exploitation balance for navigating value spaces with local minima. We validate our approach on porosity prediction and process parameter optimization in laser powder bed fusion, demonstrating faster convergence and higher final reward values compared to standard RL methods including DQN, PPO, TD3, and vanilla SAC. The proposed methodology achieves a convergence value of 322.79 within 14 episodes, outperforming existing approaches while maintaining stability throughout training.

阅读与讨论 → 访问原文 →