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.
arXiv (CS.AI) 2026-06-18

Two-Phase Bilevel Search for the Moving-Target Traveling Salesman Problem with Moving Obstacles

作者:
Allen George Philip↗Anoop Bhat↗Sivakumar Rathinam↗Howie Choset↗

arXiv:2606.18730v1 Announce Type: cross Abstract: The Moving-Target Traveling Salesman Problem (MT-TSP) seeks a minimum cost trajectory for an agent that departs from a static depot, visits a set of moving targets, each within one of their assigned time windows, and returns to the depot. In this article, we study the Moving-Target Traveling Salesman Problem with Moving Obstacles (MT-TSP-MO), a generalization of the MT-TSP where the agent trajectory must avoid moving obstacles. We present a Mixed-Integer Conic Programming (MICP) formulation that can be solved using off-the-shelf solvers, as well as a fast and scalable Two-Phase Bilevel Search (TPBS) algorithm that computes high-quality feasible solutions for the problem. We evaluate our approaches against an existing baseline algorithm on a broad range of problem instances with up to 40 targets and 40 obstacles. The results demonstrate that both the proposed methods significantly outperform the baseline with respect to success rates, solution costs, and computation time.

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

If These Walls Could Talk: Critical Play with Large Language Models in Museums

作者:
Anders Sundnes L{\o}vlie↗

arXiv:2606.15565v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being used in museums to as role playing chatbots which let visitors talk to simulated versions of people and artefacts from the past. While such installations can be playful and engaging, they are also problematic because LLMs cannot be trusted to speak truthfully. I identify a fundamental dilemma for the use of LLMs in museum chatbots: LLMs cannot be trusted to tell the truth, and efforts to make them more reliable may ruin that which is attractive about the bots in the first place - their ability to engage in life-like conversation. In response, I propose designing for critical play with LLM-based bots: Designing for playful interactions with bots that are unreliable but still able to represent the past in an adequate and engaging manner - as fictional characters representing historical narratives, styles of discourse, diverse perspectives, humor and satire.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-16

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

作者:
David Huang↗Jaewon Chang↗Avidan Shah↗Prateek Mittal↗Chawin Sitawarin↗

The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection classifiers. When new jailbreaks emerge that bypass these classifiers, Rapid Response generates synthetic variants for training, helping the model generalize from the new attacks and quickly adapt. We reveal that prompt injection can infiltrate this pipeline to deliver poisoned samples into the classifier's training set, enabling two attack objectives: (I) targeted poisoning attacks that create false positives on harmless samples by categorizing them as a jailbreak, with a specific desired feature (e.g., certain formatting, subject, or keyword), (II) concept-based backdoor attacks that induce false negatives on jailbreak inputs, generalizing even to jailbreaks from attack strategies the defender explicitly trained against, when the backdoor trigger is present. Importantly, our threat model restricts adversaries to modifying only jailbreak samples (not benign data or labels), a constraint unexplored by prior work that makes the second objective particularly challenging. We address this with Omission Attack, which exploits a new phenomenon: when training on concept-absent unsafe samples, the classifier misassociates that concept's presence with the safe label. Both attacks cause substantial and in some cases near-complete label flipping at only a 1% poisoning rate, achieving up to 100% false positive rates and up to 96% false negative rates.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-18

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

作者:
Du Yin↗Hao Xue↗Jinliang Deng↗Yang Yang↗Shuang Ao↗Arian Prabowo↗Flora Salim↗

arXiv:2606.10466v2 Announce Type: replace-cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmentation, we propose UPLOTS, a Unified, Prompt-guided Language model framework fOr constrained Time-Series Generation across diverse domains. Instead of building task-specific models, UPLOTS leverages a single pre-trained transformer backbone guided by learned constraint prompts, enabling on-demand generation with precise pattern control. One key innovation is our dynamic multi-dataset loss re-weighting and prompt-to-pattern mapping, which allows UPLOTS to internalize diverse temporal structures during training and conditionally generate them at inference. We evaluate UPLOTS on four real-world benchmarks and multiple constraint settings, including peak-period, calendar, load-level, and volatility patterns. Additional held-out constraint-combination and downstream forecasting experiments further demonstrate that UPLOTS generalizes beyond the original peak-pattern setting and improves data augmentation under scarce real-data regimes. Our code and baselines are available at anonymous github repo: https://anonymous.4open.science/r/UPLOTS-6C36.

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

Interplay of insurance and financial risks in a non Levy-Renewal environment

作者:
Dimitrios G. Konstantinides↗Charalampos D. Passalidis↗

arXiv:2606.15596v1 Announce Type: new Abstract: In this paper we consider a multivariate risk model, with common counting process and common process of logarithmic returns for the investment portfolio. We assume that the claim-vectors, the counting process and the logarithmic returns of the investment portfolio satisfy a weak dependence structure. Further, we consider that the counting process represents an inhomogeneous renewal process, and the logarithmic returns represent a cadlag process with independent but not necessarily stationary increments. Under these conditions we provide an asymptotic expression for the infinite-time entrance probability of the discounted aggregate claims into some rare set xA, where A denotes a set from a general set family, crucial for the actuarial practice, when the common distribution of the claim vectors belong to a multivariate heavy-tailed distribution class. This result, is derived under a moment condition for the financial risks, and underlines the multivariate linear single big jump principle. When we restrict the distribution class of the claim-vectors to multivariate regular variation, we find more explicit asymptotic expressions, weakening the moment conditions on the financial risks. The asymptotic formulas, derived through double dependence solution, become more direct and practical in applications. With respect to the technical part, due to non Levy-Renewal framework, the classical Kesten-Goldie theorems are not applicable, nor their extensions. The way we make the discretization of the process of the discounted aggregate claims permits to derive uniform asymptotics with respect to the number of summands, that facilitate the approximation of the infinite sums of the main results.

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

Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research

作者:
Andr\'es Abeliuk↗Cinthia Sanchez Macias↗Valentina Alarc\'on↗\'Alvaro Madariaga↗Claudia Lopez↗

Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. We propose Situated Interaction Auditing (SIA), a user-centered framework for studying how user profile signals – implicit sociodemographic markers, writing style, and stated identity – systematically shape LLM response quality, content, and tone. We demonstrate the framework through a case study that intersects gender and socioeconomic status signals across multiple task domains and outline a research agenda for SIA as a new mission for natural language processing.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CL) 2026-06-17

Are you speaking my languages? On spoken language adherence in multimodal LLMs

作者:
Hyungwon Kim↗Kandarp Joshi↗Lillian Zhou↗Pavel Golik↗Petar Aleksic↗

While Large Language Model (LLM) based Automatic Speech Recognition (ASR) enables seamless multilingual use, models often misidentify the output language, compromising transcription fidelity and downstream application quality. To preserve flexibility and code-switching capabilities, we propose a soft prompting approach that hints at potential spoken languages without strictly constraining the output. We formally define this challenge as a lack of language adherence, introduce a novel metric to quantify violations, and evaluate three mitigation strategies: (1) zero-shot prompting for robust guidance under uncertainty, (2) supervised fine-tuning (SFT) to improve prompt adherence, and (3) Chain-of-Thought (CoT) reasoning to enforce adherence during decoding. We present a comparative analysis of these methods across multiple languages, evaluating effectiveness in reducing the language violation while maintaining overall ASR performance. Finally, we discuss trade-offs to guide strategy selection under various compute constraints.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-15

From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing

作者:
Hugo Daumain↗Driss Matrouf↗Khaled Khelif↗Mickael Rouvier↗

arXiv:2606.14639v1 Announce Type: cross Abstract: Recent advances in speech generation have significantly improved the naturalness of synthetic speech, making spoofing detection increasingly challenging. A key limitation of current anti-spoofing systems is their limited robustness to unseen synthesis methods. In this work, we transform a self-supervised speech representation model into a Mixture-of-Experts (MoE) architecture to improve generalization. Feed-forward blocks in selected encoder layers are replaced by multiple expert networks controlled by a layer-wise gating mechanism, allowing experts to capture complementary acoustic patterns while preserving the representations learned during self-supervised pretraining. We further analyze the architectural choices affecting the performance of this MoE conversion and investigate the activation behavior of the experts. The proposed approach is evaluated on 14 spoofing datasets and reduces the macro EER from 5.46% to 4.81%, corresponding to 11.9% relative improvement over the baseline.

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

Starter-Iterator Neural Operator: A Unified Architecture for High-Fidelity Forward and Inverse PDE Problems

作者:
Kuilin Qin↗Lianfang Wang↗Xu Sun↗Jiwei Jia↗Yu Wang↗Yong Wang↗Yuping Duan↗

arXiv:2606.18305v1 Announce Type: cross Abstract: Operator learning is an emerging interdisciplinary field that integrates machine learning with scientific computing. By mapping infinite-dimensional function spaces, this approach provides an efficient surrogate modeling framework for high-dimensional partial differential equations (PDEs). Compared to traditional numerical solvers, it achieves a superior trade-off between computational complexity and approximation accuracy, demonstrating significant advantages in many-query tasks such as real-time prediction and parameter sweeps. Given the stringent accuracy requirements of both forward simulation and inverse inference, as well as the precision bottlenecks of existing operator learning methods in handling complex boundaries or long-term evolution, we propose the Starter-Iterator Neural Operator (SINO). Our framework reinterprets the initialization strategies and iterative formats of traditional iterative methods through neural networks, establishing an efficient approach for spectral-spatiotemporal collaborative modeling. Specifically, the frequency-domain initialization module captures globally stable low-frequency features, while the time-domain learning module focuses on optimizing local solution residuals, thereby effectively overcoming the inherent limitations of conventional single-domain modeling approaches. Extensive experiments on typical dynamical systems such as the Navier-Stokes equations and acoustic wave equations, as well as practical applications including super-resolution imaging and weather forecasting, demonstrate that SINO achieves outstanding performance in numerical accuracy, generalization capability, and robustness.

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

Temporal modulation as a resource: enhanced frequency estimation in continuous variable systems

作者:
Ningxin Kong↗Qiongyi He↗Matteo G. A. Paris↗

arXiv:2606.15108v1 Announce Type: new Abstract: Frequency estimation, a cornerstone of quantum metrology, has been significantly enhanced by advanced quantum sensing strategies. However, most protocols rely either on static or time-independent encoding mechanisms, inherently limiting their achievable precision scaling, or on control strategies requiring changing the Hamiltonian and/or implementing feedback mechanisms. To overcome this, we investigate a simpler dynamical encoding protocol where the quantum oscillator is driven by a general continuous temporal frequency modulation $\Omega(t) = \omega_0 f(t)$. We analytically demonstrate that for a given modulation profile $f(t)$ and its corresponding time-integral $F(t)$, the quantum Fisher information (QFI) scales as $\mathcal{O}(F(t)^2)$. This enhancement stems from the fact that temporal encoding fundamentally alters the mechanism of dynamical phase accumulation. Crucially, when evaluated under the energy and evolution-time constraints, this framework reveals a genuine precision enhancement over the conventional time-independent baseline. By analyzing explicit polynomial and exponential modulations, we establish that arbitrary precision scaling can be deterministically engineered, with ultimate bounds that are asymptotically saturable via optimal homodyne detection. Our framework provides a universal paradigm for exploiting time-dependent quantum control in next-generation sensors.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-15

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

作者:
Tan Zhu↗Tong Yao↗Kananart Kuwaranancharoen↗Amit Singh↗Yushang Lai↗Deepa Mohan↗Shankara Bhargava↗

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is crucial: existing methods suffer from inaccurate credit assignment and lack convergence guarantees. We propose Graph-based Target Back-Propagation (GTBP), a context adaptation framework for agentic workflows modeled as directed acyclic graphs. GTBP propagates local target outputs backward through the workflow graph and uses target–output discrepancies to guide a stage-wise prompt update mechanism. Theoretically, we show that GTBP's stage-wise prompt updates become stable over iterations, and that a sufficiently capable LLM optimizer can decrease the overall objective. Empirically, GTBP consistently outperforms strong baselines across three benchmarks while maintaining comparable computational cost.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-18

Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation

作者:
Tianyu Wang↗Ying Wang↗Zhihao Liu↗Xi Vincent Wang↗Lihui Wang↗

arXiv:2606.18315v1 Announce Type: cross Abstract: Sequential output generation with large-scale Transformer and diffusion decoders pays a memory cost that grows with sequence length, plus iterative per-step computation. Replacing them with small feed-forward decoders restores efficiency but produces unstructured latent representations that limit closed-loop control: phase-conditioned action generation and cross-step latent carry-over both require a latent geometry with stable basins. This article proposes Ghost Attractor Networks, a theoretically derived dynamical decoder whose latent evolves under a learned potential with drift and produces a basin-attractor structure by construction. Three desiderata (multi-modality, decoder-level single-pass switching, and constant memory) motivate the potential-drift form, and mode transitions arise as saddle-node bifurcations with ghost-attractor escape. A hierarchical phase-space decomposition separates first-order basin convergence from second-order proprioceptive refinement. Empirically, a Ghost trained end-to-end with a behavioral-cloning and contrastive objective exhibits the predicted gradient-flow contraction in its potential, with the gradient norm decaying by 67 percent across five integration steps on 1430 held-out samples. Ghost is evaluated as a robotic action decoder. A 2.3-million-parameter Ghost matches the offline accuracy of a 1.07-billion-parameter Diffusion Transformer at 462 times fewer parameters and 32 times lower latency, and beats five alternative 2M-parameter decoders (MLP, Neural ODE, CVAE, Transformer, 1-step Diffusion) on offline mean squared error by 5.9 to 29 percent. On the LIBERO-10 closed-loop benchmark, phase conditioning on Ghost's basin-structured latent yields a 13.5 percentage-point success-rate gain over a feed-forward MLP baseline, and persistent-latent ensembling reaches a 95.7 percent final success rate.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.LG) 2026-06-16

How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle

作者:
Zongfang Liu↗Jinghui Zhang↗Zijian Ma↗Guangyi Chen↗Xin Yuan↗

arXiv:2606.15716v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the full expert pool, making one-shot expert pruning a practical approach for reducing memory usage. Although effective, existing criteria are largely heuristic, and no single criterion is universally optimal. Thus, establishing a principle for selecting pruning criteria suited to different deployment objectives remains an important yet largely underexplored problem in one-shot expert pruning. To this end, we introduce a unified formulation for one-shot MoE expert pruning organized around three factors: routing frequency, gate weighting, and activation strength. The formulation yields a criteria selection principle: task-agnostic pruning should favor routed-token-averaged, gate-free activation-based criteria, whereas task-specific pruning can benefit from retaining routing-frequency and gate-weight information. Beyond this principle, the formulation also provides a systematic view of existing heuristic criteria and gives rise to two new task-agnostic criteria, Mean Activation Norm (MAN) and Mean Squared Activation Norm (MSAN). Across four representative MoE models and 16 diverse benchmarks, MAN and MSAN are consistently strong in the task-agnostic setting, obtain the top-two average ranks, and improve average performance by up to 8.8 points over the strongest baseline.

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

Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation

作者:
Ziyu Zhang↗Chunyu Qiang↗Xiaopeng Wang↗Yuxin Guo↗Kang Yin↗Wenjie Tian↗Jingbin Hu↗Tianlun Zuo↗Zhao Guo↗Teng Ma↗Yuzhe Liang↗Chen Zhang↗…

arXiv:2606.07015v2 Announce Type: replace-cross Abstract: While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To bridge this gap, we propose UniSinger, the first end-to-end framework unifying speaker cloning song generation and accompaniment co-generation SVC. Building on the multimodal diffusion transformer, we construct a unified speaker embedding space transferring speaker representation from SVC to song generation, endowing fine-grained cross-task timbre control. To mitigate multi-task optimization conflicts, we design a curriculum learning strategy using task-specific modality masking to guide the model to gradually master the generative mechanisms among semantic content, vocal timbre, and accompaniment. Experiments show state-of-the-art performance on both tasks and realizes complementary benefits, offering new possibilities for intelligent music production.

阅读与讨论 → 访问原文 →
17.
Nature (Science) 2026-06-18

Daily briefing: The proteins that protect us from deadly mutations

作者:
Flora Graham↗

Proteins that ‘buffer’ the effects of mutations could help to treat diseases such as cancers. Plus, goats can follow human voices and the battle over a key ocean observatory project in the United States. Proteins that ‘buffer’ the effects of mutations could help to treat diseases such as cancers. Plus, goats can follow human voices and the battle over a key ocean observatory project in the United States.

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

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

作者:
Hongwei Yao↗Yiming Liu↗Yiling He↗Bingrun Yang↗

arXiv:2605.11047v2 Announce Type: replace-cross Abstract: Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines risk-conditioned evaluation, multi-objective trajectory scoring, reward-guided beam search, and reflection-based deep probing to identify high-value compromised contexts. We construct a 42-case benchmark spanning six vulnerability classes and seven operational scenarios, and evaluate nine target models using attack and utility grading scores. Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion, demonstrating that final-response evaluation is insufficient. The findings highlight the need for execution-centric security evaluation of agentic AI systems. Our code is released at: https://github.com/ZJUICSR/DeepTrap

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

DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation

作者:
Xifeng Xue↗Xiaokang Wang↗Zirui Li↗Ming-Ming Cheng↗Guolei Sun↗

Recent vision token pruning methods effectively preserve model performance under moderate token budgets but become unstable under ultra-low token budget. Our analysis shows that as the pruning budget decreases, accuracy degradation is often accompanied by larger feature distribution shifts. Critically, the degree of this distribution shift strongly correlates with performance degradation. To better characterize this phenomenon, we introduce a lightweight distribution consistency metric to estimate the distribution shift between retained and full tokens. Motivated by these observations, we propose a two-stage pruning framework consisting of Anchor-Context Graph Recovery (ACGR) and Text-Aware Token Cluster Selection (TATCS). Specifically, ACGR transfers contextual information before token removal, while TATCS dynamically re-selects representative tokens when severe distribution shift is detected. Extensive experiments demonstrate that our method achieves superior and more stable performance under ultra-low token budget. Notably, it retains 92.1% of the upper-bound average performance on LLaVA-1.5-7B with only 16 visual tokens.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-15

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR

作者:
Henri-Leon Kordt↗Theresa Pekarek Rosin↗Jae Hee Lee↗Stefan Wermter↗

Despite advances in large-scale Automatic Speech Recognition (ASR), disfluent speech remains challenging, as state-of-the-art systems are often optimized to omit disfluencies, leading to information loss and hallucinations. Prior work has focused on verbatim transcription and the integration of disfluency markers, but adapting models on limited datasets can lead to catastrophic forgetting of general-domain knowledge. We address this gap by leveraging continual learning (CL) with explicit disfluency tokens. We first introduce these tokens into a pretrained ASR model to establish stable token mechanisms, and then continue training on additional datasets with varying disfluency distributions. Through a detailed analysis of model dynamics during training, we identify a trade-off between marker learning and ASR performance, and a consistent cross-attention head mechanism shared across CL methods.

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

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems

作者:
Yifei Wang↗Hancheng Ye↗Yechen Xu↗Cong Guo↗Chiyue Wei↗Qinsi Wang↗Dongting Li↗Tingjun Chen↗Hai "Helen" Li↗Danyang Zhuo↗Yiran Chen↗

arXiv:2604.26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops, and a spatial shift from chat-scale, GPU-only execution to repository-scale, GPU-CPU co-located execution. Consequently, coordinating heterogeneous resource demands of agentic execution has emerged as a critical system challenge. We design and implement MARS, an efficient and adaptive co-scheduling system that globally coordinates heterogeneous agentic workloads under coupled GPU-CPU resource pressure. By establishing holistic visibility across GPU inference and CPU tool execution via a unified information stream, an external control plane in MARS decouples admission from execution to prevent heterogeneous resource oversubscription. An internal agent-centric scheduler further minimizes the end-to-end critical path by prioritizing latency-sensitive continuations and adaptively retaining KV cache state only when warm resumption yields a latency benefit. Our evaluations show that MARS reduces end-to-end latency by up to 5.94x while maintaining nearly maximal system throughput. We further integrate MARS as the serving backend for the OpenHands coding agent framework, demonstrating its real-world effectiveness by accelerating end-to-end task completion time by up to 1.87x. Our source code is publicly available at https://github.com/Afterglow231/MARS_preview .

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-11

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

作者:
Leyi Pan↗Shuchang Tao↗Yunpeng Zhai↗Lingzhe Zhang↗Zhaoyang Liu↗Bolin Ding↗Aiwei Liu↗Lijie Wen↗

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology privilege-induced style drift, which destabilizes training or causes response length to shrink. To address this, we propose RLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing the style shift that conditioning on a hint tends to induce regardless of correctness, and yielding a signal that is more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to the broader cross-model on-policy distillation setting.

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

Beyond the Smile: A Hybrid Convolutional VAE for Crypto Volatility Surfaces

作者:
Sadanand Singh↗Allam Reddy↗Manan Chopra↗

arXiv:2606.16961v1 Announce Type: new Abstract: We present a convolutional variational autoencoder for cryptocurrency implied-volatility surfaces, together with a deployable predictor that combines it with a quadratic smile re-fit through a deterministic per-tenor routing rule. Trained on 6,034 fully-filled hourly Binance Options surfaces of BTC and ETH spanning May-October 2023 and parameterised on a common $6 \times 7$ tenor-delta grid, the model attains a hidden-cell surface-completion RMSE in the 0.94-1.56 vol-point range across both markets and mask rates 10-50%. The hybrid predictor attains 0.83 vol points at 50% masking against 7.00 for the smile re-fit alone, an eightfold reduction obtained at no additional inference cost. Under structurally-correlated hole patterns that emulate the withdrawal of an entire tenor of strikes, the smile re-fit incurs 9.6-13.1 vol points of error while the learned model remains at 1.5-1.9, isolating a regime in which the generative model is the only viable predictor. Joint training on BTC and ETH improves the in-distribution model on both markets by 9-27% relative to the better-performing single-symbol counterpart, indicating a substantially shared vol-surface manifold across the two largest cryptocurrencies over the observation window. The hybrid is calendar- and butterfly-arbitrage-free at the listed strikes, a property that the parametric smile re-fit alone fails at high mask rates. The per-snapshot reconstruction error of the trained model flags the late-October ETF-anticipation rally and the August $17$, $2023$ flash crash as elevated-error periods without supervision. All training and evaluation infrastructure is released to support reproducible follow-on work.

阅读与讨论 → 访问原文 →
25.
medRxiv (Medicine) 2026-06-15

Reaching out-of-school girls with HPV vaccination: A qualitative evaluation in six low- and middle-income countries using the RE-AIM framework

作者:
Zhang↗Rosser↗Wysong↗M. D↗Surkan↗P. J↗Rosen↗J. G↗Limaye↗R. J↗Park↗

Background Infection with human papillomavirus (HPV), the primary cause of cervical cancer, disproportionately affects women in low- and middle-income countries (LMICs). While school-based vaccination of adolescent girls against HPV is highly effective, this strategy systematically excludes out-of-school (OOS) girls. Using the RE-AIM framework, we explored strategies to reach OOS girls with HPV vaccination across six African and Asian LMICs. Methods We conducted semi-structured key informant interviews with 32 vaccination program stakeholders from Cambodia, Cameroon, Kenya, Malawi, Mozambique, and Uganda between May and September 2024. Interviews explored countries implementation successes, challenges, and strategies to reach OOS girls with HPV vaccination and sustainability considerations. Data were analyzed using a hybrid team-based thematic analysis approach guided by the RE-AIM framework. Results Community outreach-based strategies, typically integrated into routine immunization outreach, were identified as the most effective approach to reach OOS girls with HPV vaccination. Targeted strategies, such as locating outreach clinics in community venues frequented by OOS girls (e.g., churches, markets) enhanced implementation. Perceived effectiveness of these strategies varied across participants, and formal assessment of effectiveness was constrained by the absence of disaggregated vaccination coverage data by school enrollment status. Some subpopulations of OOS girls (i.e., girls in nomadic or migrant communities, urban OOS girls) were not readily reached through standard outreach approaches, prompting implementation of adapted and tailored strategies for these subpopulations. Costs associated with conducting outreach in harder-to-reach areas were major barriers to reaching OOS girls, presenting challenges to the sustainability and cost-effectiveness of these approaches. Conclusions Routine community outreach platforms were widely perceived as most effective for reaching OOS girls. Strengthening disaggregated monitoring systems, adapting outreach for harder-to-reach subpopulations of OOS girls, and financing delivery models for tailored outreach strategies will be critical to improving equitable HPV vaccine coverage among OOS girls.

阅读与讨论 → 访问原文 →