探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19558

Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

作者:

Milo\v{s} Nikoli\'c↗Ali Hadi Zadeh↗Enrique Torres Sanchez↗Andreas Moshovos↗

Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality. We test this practice on a 28-quant cohort of Qwen3.6-35B-A3B and a 41-quant cohort of Devstral-Small-2-24B, evaluated across a suite of downstream benchmarks. We find that KLD is strongly correlated with benchmark score over the full cohort ($\rho=-0.72$ on Qwen and $\rho=-0.86$ on Devstral, both with $p

阅读与讨论 → 访问原文 →

02.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.12301

An iterative Ising decoder for quantum error correction codes

作者:

Yuanqi Liu↗Weilei Zeng↗Peixiang Li↗Yantong Liu↗Guangyao Huang↗Yingwen Liu↗Dongyang Wang↗Junjie Wu↗Lingling Lao↗

arXiv:2606.12301v1 Announce Type: new Abstract: The Ising framework maps the decoding problem in quantum error correction onto ground-state optimization of a classical Hamiltonian, in which $X$-$Z$ error correlations enter as cross terms. Under phenomenological depolarizing noise, the exact joint formulation contains up to 8-body interactions for the toric code and 10-body for the $6.6.6$ color code. These high-order terms degrade solver convergence, inflate runtime, and raise the auxiliary spin overhead when embedding into native 2-body Ising hardware. In this work, we propose the iterative low-order decoding (ILOD) algorithm, which alternates between $X$- and $Z$-type sub-Hamiltonians, approximating cross-type correlations through Bayesian priors that reweight each type's couplings using the other type's inferred error configuration. This halves the maximum body count of interaction terms in the Hamiltonian, accelerating the solver, restoring convergence at larger code distances, and reducing the total spin count for 2-body embedding by a factor of $2.5$. For the toric code, ILOD attains a threshold of $4.73%$ versus $4.83%$ for the joint formulation, with the empirical runtime ratio scaling as $(0.81)^d$. For the $6.6.6$ color code, their thresholds agree within statistical uncertainty for small code distances, and ILOD remains convergent for larger distances where the joint formulation fails to converge despite a larger annealing budget.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12578

MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction

作者:

Mohammadreza Riyazat↗Vian Lelo↗Rameen Jafri↗Yumna Khan↗Abeer Badawi↗

Mechanism-level drug-drug interaction (DDI) prediction requires identifying which enzyme or pharmacodynamic axis is implicated, in which direction, and with which evidence – not merely whether two drugs interact. We introduce a reproducible mechanism-level DDI labelling and evaluation protocol with a structured 7-family/147-subtype taxonomy, leakage-safe cold-split protocols, and auditable reasoning metrics for evaluating pharmacological prediction beyond flat interaction classification. We propose a pipeline that produces a 7B reasoning MARD (Mirror-Augmented Reasoning Distillation), combining three training innovations: a single-token KL divergence on direction tag that ties the model's prediction, per-loss PRM-weighted DPO with programmatic hard negatives, and a leakage-safe mechanism-aware retrieval channel. Process-reward step labels are automatically verifiable against DrugBank-structured fields, requiring no human or LLM judges. On the April-2026 DrugBank release, our MARD-7B is the only system in a 32-system comparison whose accuracy survives drug-pair novelty, beating the best baseline by +13.9 pp and GPT-4o by +6.7 pp at ~1% of frontier API cost. Further analysis reveals an anti-memorisation signature where accuracy improves on rarely seen drugs, suggesting that gain comes from structured pharmacological reasoning rather than drug-frequency memorisation. We release corpus, DDI-PRM, retrieval index, and training code.

阅读与讨论 → 访问原文 →

04.

medRxiv (Medicine) 2026-06-24 DOI: HASH:2b1a267f06392a834196919f7ac6cc2a

Pre-activity glycemic prediction prioritizes post-meal movement

作者:

Shilo↗Sapir↗Lutsker↗Talmor-Barkan↗Godneva↗Diament↗Matabuena↗Segal↗Rossman↗

Post-meal activity can attenuate glucose excursions; however, the exact magnitude of this effect remains unquantified, and guidance is rarely personalized to the meal occasion. We linked Human Phenotype Project diet logs, continuous glucose monitoring and wearable step counts to test whether glycemic risk estimated before activity occurs can prioritize post-meal movement. An activity-blind PPGR model trained on 391,214 PPGR-valid meals from 9,561 participants generated pre-activity meal scores. Among 55,949 step-linked meals from 1,627 adults without diabetes, higher 0-120-min post-meal steps were associated with lower within-participant PPGR (-53.0 mg/dL*min per 1 s.d. higher log steps; 95% CI, -64.2 to -41.7), with larger adjusted PPGR iAUC contrasts at 1,501-2,500 observed steps (-154.4 mg/dL*min versus 0-50 steps). Associations were stronger among participants with higher glycemic-adiposity burden and after meals with higher predicted PPGR. A held-out pre-activity step-response ranking concentrated larger inverse step-PPGR associations (-79.1 top versus -15.0 mg/dL*min bottom quintile), providing a testable strategy for prediction-guided, post-meal movement prompts.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19668

Code-Switching Reveals Language Anchoring in Multilingual LLMs

作者:

Jeonghyun Park↗Seunghyun Yoon↗Yonghyun Jun↗Hwanhee Lee↗

Multilingual Large Language Models (MLLMs) are increasingly expected to handle Code-Switched (CS) inputs, yet mixing languages frequently degrades performance relative to source- or target-language monolingual counterparts. To understand this degradation, we use grammar-forced CS as a controlled diagnostic setting for locating CS representations relative to their source and target counterparts. We introduce Anchor Bias, a geometric measure that quantifies language anchoring, whether a CS hidden state aligns closer to its source or target language counterpart. Across diverse MLLMs, Anchor Bias reveals a consistent grammar-frame effect: source-framed CS stays source-anchored, whereas target-framed CS shifts target-ward and shows larger Question Answering (QA) degradation. Motivated by this representational pattern, we propose CANVAS (Contextual Anchor-based Neural Vector Alignment Steering), an inference-time intervention that extracts a source-side canvas from the input and softly steers target-language hidden states toward the source anchor during prefill. CANVAS consistently recovers QA F1 across MLLMs and CS conditions, showing that internal anchoring signals provide an actionable target for mitigating CS inference failures.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17222

Quantum Enchanced Multi-Scale CNN with Bi-directional Mamba for Crop Field Analysis

作者:

Mohammad Salman Khan↗Ehsan Atoofian↗Saad B. Ahmed↗

Hyperspectral image (HSI) crop analysis is essential for precision agriculture because it captures rich spectral and spatial information for accurate crop monitoring and assessment. However, HSI classification remains challenging due to high spectral dimensionality, spatial complexity, class imbalance, and limited labeled samples. To address these challenges, this paper proposes a BiSpectral Mamba-based framework that combines multi-scale convolutional feature extraction, spectral attention, bidirectional state-space modeling, and quantum-inspired learning. A multi-scale CNN backbone first extracts hierarchical spatial-spectral representations through feature fusion across multiple resolutions. A spectral attention mechanism then emphasizes informative bands while suppressing redundant and noisy channels. The refined features are processed by a BiSpectral Mamba module that captures long-range dependencies in both forward and backward directions by modeling hyperspectral feature maps as sequential tokens. In addition, class-weighted optimization and feature fusion strategies are incorporated to improve training stability and mitigate class imbalance. Experimental evaluation on the UAVHSI-Crop dataset demonstrates the effectiveness of the proposed framework, achieving an overall accuracy of 84.83%. The results show that integrating convolutional, attention-based, and state-space modeling components enables robust spatial-spectral feature learning for crop classification. The proposed framework also shows potential for broader agricultural and remote sensing applications, including crop disease detection, yield prediction, and soil moisture estimation, while highlighting the effectiveness of structured state-space and quantum-inspired architectures for hyperspectral image analysis.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16462

Learning aligned EEG representations with subject-specific encoders

作者:

Bruna J. Lopes↗Gabriel Schwartz↗Sylvain Chevallier↗Raphael Y. de Camargo↗Bruno Aristimunha↗

arXiv:2606.16462v1 Announce Type: cross Abstract: Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether task supervision and architecture alone can learn subject-aligned representations. We replace a shared EEG encoder with subject-specific encoders followed by a common classifier, and compare this hybrid model with standard EEGNet, AttentionBaseNet, and CTNet baselines with Euclidean Alignment (EA) on four motor-imagery datasets. EA improves shared encoders by recentering subject covariances, but the hybrid encoder largely internalises this role: validation-loss curves and latent-distance analyses change little when EA is removed. Subject-specific heads increase class distinctiveness and place each subject close to its own latent manifold, improving most subjects while leaving a method-sensitive subset. These results support subject-specific encoders as a learned alignment mechanism for EEG decoding and identify head selection for unseen subjects as the remaining bottleneck.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2505.12843

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

作者:

Kangwen Zhao↗Jianfeng Cai↗Jinhua Zhu↗Ruopei Sun↗Dongyun Xue↗Wengang Zhou↗Li Li↗Houqiang Li↗

arXiv:2505.12843v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to maximize reward scores without genuinely aligning with human preferences. A significant example of such reward hacking is length bias, where reward models usually favor longer responses irrespective of actual response quality. Previous works on tackling length bias have notable limitations, these approaches either mitigate bias without characterizing the bias form, or simply assume a linear length-reward relation. To accurately model the intricate nature of length bias and facilitate more effective bias mitigation, we propose FiMi-RM (Bias Fitting to Mitigate Length Bias of Reward Model), a framework that autonomously learns and corrects underlying bias patterns. Our approach consists of three stages: First, we warm up by training a standard reward model which inherently contains length bias. Next, we deploy a lightweight fitting model to capture the non-linear relation between length and reward. Finally, we incorporate this learned relation into the reward model, effectively decoupling length from reward while preserving preference modeling capabilities. Experimental results demonstrate that FiMi-RM achieves a more balanced length-reward distribution. Furthermore, when applied to alignment algorithms such as Direct Preference Optimization (DPO) and Best-of-N (BoN), our debiased reward model improves length-controlled win rate and reduces verbosity without compromising its performance.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2501.07761

Impatient Bandits: Optimizing for the Long-Term Without Delay

作者:

Kelly W. Zhang↗Thomas Baldwin-McDonald↗Kamil Ciosek↗Lucas Maystre↗Daniel Russo↗

arXiv:2501.07761v2 Announce Type: replace-cross Abstract: Increasingly, recommender systems are tasked with improving users' long-term satisfaction. In this context, we study a content exploration task, which we formalize as a bandit problem with delayed rewards. There is an apparent trade-off in choosing the learning signal: waiting for the full reward to become available might take several weeks, slowing the rate of learning, whereas using short-term proxy rewards reflects the actual long-term goal only imperfectly. First, we develop a predictive model of delayed rewards that incorporates all information obtained to date. Rewards as well as shorter-term surrogate outcomes are combined through a Bayesian filter to obtain a probabilistic belief. Second, we devise a bandit algorithm that quickly learns to identify content aligned with long-term success using this new predictive model. We prove a regret bound for our algorithm that depends on the Value of Progressive Feedback, an information-theoretic metric that captures the quality of short-term leading indicators that are observed prior to the long-term reward. We apply our approach to a podcast recommendation problem, where we seek to recommend shows that users engage with repeatedly over two months. We empirically validate that our approach significantly outperforms methods that optimize for short-term proxies or rely solely on delayed rewards, as demonstrated by an A/B test in a recommendation system that serves hundreds of millions of users.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.12755

Certifying Nonclassical Proper-Time Histories with a Quantum Clock

作者:

Shuai Zeng↗

arXiv:2606.12755v1 Announce Type: new Abstract: Quantum clocks can acquire relativistic phases from motional or gravitational proper-time differences, but reduced clock dephasing alone does not certify nonclassical proper-time histories. We formulate this distinction as a channel-certification problem. First, we show that any two-level single-time dephasing signal, including one generated by an effective quantum proper-time label, admits a classical random proper-time representation. We then define the convex set of classical mixtures of experimentally specified proper-time histories and prove a Choi-rank separation criterion for conditioned coherent history recombination. A two-branch Ramsey protocol gives explicit bright- and dark-port population witnesses outside this classical set. The certification is operational and relative to the specified history set: it rules out classical mixtures of the same implemented proper-time histories, not arbitrary classical protocols with different histories or controls.

阅读与讨论 → 访问原文 →

11.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2511.17228

Intrinsic preservation of plasticity in continual quantum learning

作者:

Yu-Qin Chen↗Shi-Xin Zhang↗

arXiv:2511.17228v2 Announce Type: replace Abstract: Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually lose their ability to learn from new data. Here we show that quantum learning models naturally overcome this limitation, preserving plasticity over long timescales. We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms, including supervised learning and reinforcement learning, and diverse data modalities, from classical high-dimensional images to quantum-native datasets. Although classical models exhibit performance degradation correlated with unbounded weight and gradient growth, quantum neural networks maintain consistent learning capabilities regardless of the data or task. We identify the origin of the advantage as the intrinsic physical constraints of quantum models. Unlike classical networks where unbounded weight growth leads to landscape ruggedness or saturation, the unitary constraints confine the optimization to a compact manifold. Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups, offering a robust pathway for building adaptive artificial intelligence and lifelong learners.

阅读与讨论 → 访问原文 →

12.

PLOS Computational Biology 2026-06-23 DOI: HASH:4383fad5758df55addcde28b8b235773

A novel biclustering algorithm for mining m⁶A co-methylation patterns based on beta-binomial distribution and data screening strategy

作者:

Zhaoyang Liu↗

by Zhaoyang Liu, Yuteng Xiao, Dao Xiang, Hao Shi, Kaijian Xia Studies have shown that m6A plays a key role in different life processes such as RNA metabolism, physiology and pathology. However, due to the complexity of life processes, its specific regulatory details are still not revealed. The computational approach based on co-methylation pattern mining of m6A sequencing data can assist in revealing its mechanism and save time and economic cost, however, the current algorithms suffer from the problems of insufficient robustness to low signal-to-noise data and unreliable performance. Based on this, this paper proposes an enhanced beta-binomial distribution biclustering algorithm (EBBM) based on data screening strategy. This algorithm is based on the framework of Bayesian, adopts Gibbs sampling method for parameter inference, and introduces the data screening strategy in the process of parameter inference, which effectively removes the problem that the low signal-to-noise data in the original sequencing data of m6A affects the reliability of the clustering results. The simulation experiment results show that this algorithm can effectively deal with the interference of low signal-to-noise data and accurately mine the co-methylation patterns pre-planted in the data, which is significantly better than the current mainstream biclustering algorithm. In real human m6A sequencing data with 32 samples, this algorithm mined two effective co-methylation patterns, which were enriched to different biological processes, such as negative regulation of phosphorylation and peptidyl lysine methylation, etc. The scoring results of GEO_Score indicate that the results of this algorithm are more biologically meaningful than the clustering results of current mainstream m6A co-methylation pattern mining algorithms.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.21850

ACC: Compiling Agent Trajectories for Long-Context Training

作者:

Qisheng Su↗Zhen Fang↗Shiting Huang↗Yu Zeng↗Yiming Zhao↗Kou Shi↗Ziao Zhang↗Lin Chen↗Zehui Chen↗Lijun Wu↗Feng Zhao↗

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph traversal over extended contexts. Training Qwen3-30B-A3B with ACC achieves 68.3 on MRCR (+18.1) and 77.5 on GraphWalks (+7.6), results comparable to Qwen3-235B-A22B, while preserving general capabilities on GPQA, MMLU-Pro, AIME, and IFEval. Further mechanism analysis reveals that the ACC-trained model exhibits task-adaptive attention restructuring and expert specialization.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.13750

Tantalum as a base material for superconducting integrated circuits

作者:

Evgeniy V. Zikiy↗Nikita S. Smirnov↗Stanislav A. Kotenkov↗Ilya A. Stepanov↗Julia A. Agafonova↗Daria A. Moskaleva↗Aleksei R. Matanin↗Anton I. Ivanov↗Dmitry O. Moskalev↗Julia A. Kurochkina↗Aleksander V. Andriyash↗Ilya A. Rodionov↗…

arXiv:2606.13750v1 Announce Type: new Abstract: The performance of superconducting integrated circuits for quantum applications is fundamentally limited by material-related losses. Tantalum, as an emerging material for next-generation quantum circuits, has attracted considerable attention in recent years after demonstrating breakthrough performance in both superconducting microwave resonators and qubits. Concurrently, a growing body of work is devoted to the operation of tantalum-based circuits and related fabrication techniques. This interest is further stimulated by tantalum thin films polymorphism resulting in a variety of its crystalline structure, superconducting properties, coherence, etc. Furthermore, tantalum circuits exhibit distinctive features in cryogenic experiments, which have not been observed in aluminum- or niobium-based ones. In this review, we summarize the recent research of tantalum thin films growth and phase selection mechanisms on various substrates, key aspects of fabrication and performance of superconducting circuit, including a material first-principles theoretical study. In conclusion, we address a number of open issues, including the role of \b{eta}-phase impurities, the effect of hydrofluoric acid solutions on chain characteristics, and the anomalous behavior of {\alpha}-tantalum chains at cryogenic temperatures.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2510.06596

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation

作者:

Ayush Zenith↗Arnold Zumbrun↗Neel Raut↗Jing Lin↗

The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. We introduce the Synthetic Dataset Quality Metric (SDQM) to assess data quality for object detection tasks without requiring model training to converge. This metric enables more efficient generation and selection of synthetic datasets, addressing a key challenge in resource-constrained object detection tasks. In our experiments, SDQM demonstrated a strong correlation with the mean average precision (mAP) scores of YOLO11, a leading object detection model, whereas previous metrics only exhibited moderate or weak correlations. In addition, it provides actionable insights into improving dataset quality, minimizing the need for costly iterative training. This scalable and efficient metric sets a new standard for evaluating synthetic data. The code for SDQM is available at https://github.com/ayushzenith/SDQM

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20045

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

作者:

Fanfu Xue↗En Yu↗Yantian Shen↗Zhikun Hu↗Hongjun Wang↗Yang Yang↗Xindi Wang↗Jiande Sun↗

arXiv:2606.20045v1 Announce Type: cross Abstract: UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce UAV-VLN-FOV, a target-visible navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a vision-language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and geometric details for target grounding. It also updates the target-relative direction online during closed-loop navigation, allowing the agent to maintain spatial alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive UAV-VLN baselines, achieving a 13.82\% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach navigation. The source code and benchmark are available at https://github.com/xuefanfu/3DG-VLN.

阅读与讨论 → 访问原文 →

17.

Nature (Science) 2026-06-10 DOI: HASH:e4c1272dad4cfb7b682baffe07ca1b30

Giant crustacean of the deep sea steals a trick from bacteria

作者: 未知作者

Organisms called bathynomids boast a bacterial gene that helps them to regulate their metabolism in the cold depths. Organisms called bathynomids boast a bacterial gene that helps them to regulate their metabolism in the cold depths.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.26091

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

作者:

Andrei Liviu Nicolicioiu↗Mohammad Pezeshki↗Aaron Courville↗

arXiv:2606.26091v1 Announce Type: cross Abstract: On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback. We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten (i.e., generating more rollouts fails to improve accuracy). We trace this to compounding biases in the design of self-distillation with sampled demonstrations. The teacher scores each student rollout while conditioned on a sampled correct rollout, channeling its feedback through the model's own biases. We theoretically analyze the optimal self-distillation policy and show that it tilts the base distribution by a pointwise conditional mutual information score between the student's rollout and the correct rollout used as context. Unlike the ideal optimal on-policy reinforcement learning (RL), which preserves probability ratios among equally correct rollouts, self-distillation can amplify existing probability gaps, concentrating mass on already-dominant modes. On a controlled graph path-finding task and science question-answering benchmarks, self-distilled models match or exceed RL on average performance but exhibit substantially lower functional and semantic diversity, failing on out-of-distribution settings that require diverse strategies.

阅读与讨论 → 访问原文 →

19.

medRxiv (Medicine) 2026-06-22 DOI: HASH:ed728a2f9afdcee4182735a8d9d86371

Virtual Responsive Neurostimulation Implantation: From Intracranial Connectivity to Optimized Lead Placement

作者:

Feys↗Walsh↗K. G↗Nix↗K. C↗Josyula↗Sinha↗Lavelle↗S. B↗Wagenaar↗Michalak↗Morrell↗…

Responsive neurostimulation (RNS) is an implanted device that delivers direct brain stimulation for drug-resistant focal epilepsy. Individual responses are highly variable, and no validated framework exists to predict outcome or guide lead placement before implantation. We hypothesized that this variability is partly explained by lead placement in relation to patterns of functional connectivity in brain networks. Fourty-nine patients with drug-resistant focal epilepsy who underwent pre-implantation intracranial EEG (iEEG) and RNS implantation across three independent epilepsy centers were retrospectively studied. We developed a composite functional connectivity score, based on simple Spearman correlation, combining the standard deviation and kurtosis of interictal iEEG connectivity distributions to predict the response outcome in a training cohort (HUP, n=18) and validated in two independent cohorts (NYU, n=17; UCSF, n=14). We accounted for a spatial mismatch between iEEG and RNS electrodes with a distance-based correction. The score was extended to generate patient-specific 3D maps of predicted RNS efficacy across 200 simulated, or virtual RNS, lead configurations. Accuracy of the score in predicting clinical outcome was 72% at the group level, 61% at the individual patient level, and, after distance-based optimization, 100% in patients with RNS electrodes placed close to location of iEEG electrodes. Applied to the validation cohort, the same score reached 68% accuracy (71% balanced accuracy, 55% sensitivity, 88% specificity). The spatial combination of the scores at different SEEG contacts localization gives a spatial score for each patient. Responders showed significantly higher spatial scores than non-responders, supporting that actual RNS lead placement in responders was located in map-identified favorable regions. Interictal iEEG functional connectivity predicts individual RNS response across independent epilepsy centers, and patient-specific 3D maps derived from this biomarker could prospectively guide lead implantation toward favorable network regions, opening a promising avenue toward network-informed RNS surgical planning.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15527

Selective Synergistic Learning for Video Object-Centric Learning

作者:

WonJun Moon↗Jae-Pil Heo↗

Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder. As these two distinct maps exhibit different properties, a recent dense alignment strategy attempted to reconcile this discrepancy by enforcing agreement across all spatio-temporal patches via contrastive learning. However, this indiscriminate alignment inadvertently propagates the inherent weaknesses of each module, such as noisy encoder predictions and blurred decoder boundaries. Moreover, computing dense similarities across all pairs incurs a computational cost quadratic in the total number of spatio-temporal patches, severely limiting scalability. Motivated by this, we propose Selective Synergistic Learning (SSync). Instead of exhaustive patch-to-patch alignment, SSync prevents error propagation by selectively distilling only the most reliable cues: leveraging the encoder strictly for boundary refinement and the decoder for interior denoising. This is realized via a pseudo-labeling with linear complexity, eliminating the need for quadratic spatial comparisons. Also, to prevent the reinforcement of architectural biases like slot redundancy, we introduce a transitive pseudo-label merging that consolidates overlapping slots based on spatio-temporal activation consistency. Extensive studies demonstrate that SSync improves decomposition quality and serves as a versatile, plug-and-play module while also exhibiting exceptional robustness to slot configurations. Code is available at github.com/wjun0830/SSync.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2601.19612

Safe Exploration via Policy Priors

作者:

Manuel Wendl↗Yarden As↗Manish Prajapat↗Anton Pollak↗Stelian Coros↗Andreas Krause↗

arXiv:2601.19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing suboptimal yet conservative policies (e.g., obtained from offline data or simulators) as priors. Our approach, SOOPER, uses probabilistic dynamics models to optimistically explore, yet pessimistically fall back to the conservative policy prior if needed. We prove that SOOPER guarantees safety throughout learning, and establish convergence to an optimal policy by bounding its cumulative regret. Extensive experiments on key safe RL benchmarks and real-world hardware demonstrate that SOOPER is scalable, outperforms the state-of-the-art and validate our theoretical guarantees in practice.

阅读与讨论 → 访问原文 →

22.

medRxiv (Medicine) 2026-06-10 DOI: HASH:a59fe620cb332ac13235e3e8d3bff00b

Human-centred design approaches to health facility design: Evidence from perinatal care settings in Ethiopia and Bangladesh

作者:

Luna-Muse↗Chowdhury↗Sharif↗Olaya↗S. P↗Figueroa↗J. M↗Shao↗Brose↗Jassat↗Barker↗

While significant progress has been made in perinatal outcomes over recent decades in low- and middle-income countries (LMICs), maternal and newborn quality improvement initiatives often fail to account for the spatial conditions in which they are implemented. Health systems are increasingly deploying evidence-based care models into built environments that are not optimally structured to meet the needs of its patient population. As the principal users, patients and health care workers can offer pragmatic insights about improving these structural designs. Our objective was to gather insights from patients, providers, and companions about how the physical design of their health facilities influenced their experience receiving or delivering perinatal care. We conducted a prospective observational study using a human-centred design (HCD) approach to analyse perceptions of the quality of perinatal care across two low resource settings: Ethiopia and Bangladesh. Using engagement and assessment tools, we conducted interviews, focus groups, facility walk-throughs, co-design workshops, and infrastructural assessments with patients, companions, providers, and Ministry of Health representatives. Descriptive statistics and thematic analysis were used to identify key learnings and develop recommendations. Across both countries, participants identified the need for facility layouts that better support privacy, mobility during labour, alternative birth positions, companion involvement, cultural and religious practices, sanitation, and provider visibility. Based on these insights, we developed six recommendations to better align health facility infrastructure with maternal and newborn care delivery needs. Our findings suggest that investments in health facility infrastructure may improve care experiences and help enable respectful, safe, and evidence-based maternal and newborn care. Alongside targeted spatial improvements, government authorities responsible for health facility planning should incorporate participatory design processes to ensure infrastructure reflects the needs of patients, companions, and providers and supports high-quality care delivery.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2602.04550

Locally Gentle State Certification for High Dimensional Quantum Systems

作者:

Cristina Butucea↗Jan Johannes↗Henning Stein↗

arXiv:2602.04550v3 Announce Type: replace Abstract: Standard approaches to quantum statistical inference rely on measurements that induce a collapse of the wave function, effectively consuming the quantum state to extract information. In this work, we investigate the fundamental limits of locally-gentle quantum state certification, where the learning algorithm is constrained to perturb the state by at most $\alpha$ in trace norm, thereby allowing for the reuse of samples. We analyze the hypothesis testing problem of distinguishing whether an unknown state $\rho$ is equal to a reference $\rho_0$ or $\epsilon$-far from it. We derive the minimax sample complexity for this problem, quantifying the information-theoretic price of non-destructive measurements. Specifically, by constructing explicit measurement operators, we show that the constraint of $\alpha$-gentleness imposes a sample size penalty of $\frac{d}{\alpha^2}$, yielding a total sample complexity of $n = \Theta(\frac{d^3}{\epsilon^2 \alpha^2})$. Our results clarify the trade-off between information extraction and state disturbance, and highlight deep connections between physical measurement constraints and privacy mechanisms in quantum learning. Crucially, we find that the sample size penalty incurred by enforcing $\alpha$-gentleness scales linearly with the Hilbert-space dimension $d$ rather than the number of parameters $d^2-1$ typical for high-dimensional private estimation.

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.16945

Counterdiabatic Raman Atom Optics for Compact High-Sensitivity Gravimetry

作者:

Asad Ali↗Hamid Arian Zad↗Saif Al-Kuwari↗Muhammad Irtiza Hussain↗Muhammad Talha Rahim↗Hashir Kuniyil↗Tim Byrnes↗James Q. Quach↗Saeed Haddadi↗

arXiv:2606.16945v1 Announce Type: new Abstract: Large-momentum-transfer (LMT) atom interferometry provides a route toward enhanced inertial sensitivity in compact quantum sensors, but its scalability is limited by the accumulation of pulse-transfer errors across long Raman pulse sequences. We investigate theoretically the use of stimulated Raman shortcut-to-adiabatic passage (STIRSAP) for high-fidelity LMT atom optics in a Mach–Zehnder interferometer geometry. The counterdiabatic correction is encoded directly into the Raman pulse envelopes, eliminating the need for auxiliary microwave or radio-frequency control fields. Numerical simulations based on an effective Raman model show that $1~\mu\mathrm{s}$ STIRSAP pulses achieve single-pulse transfer fidelities of $F_\pi = 0.99902$ while maintaining negligible pulse-time overhead even at high momentum order. We analyze the resulting tradeoff between interferometric phase enhancement and compound contrast decay and identify an unconstrained shot-noise optimum near $n\approx270$. The analysis further shows that practical operation at extreme LMT order is constrained by wave-packet separation, vibration noise, Doppler detuning, and accumulated systematic effects rather than by pulse duration itself. These results establish superadiabatic Raman control as a promising approach for scalable high-fidelity atom optics and clarify the physical limitations governing compact high-order atom interferometers.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16993

DreamX-World 1.0: A General-Purpose Interactive World Model

作者:

DreamX Team↗Yancheng Bai↗Rui Chen↗Xiangxiang Chu↗Rujing Dang↗Hao Dou↗Bingjie Gao↗Qiwen Gu↗Siyu Hong↗Jiachen Lei↗Geng Li↗Jifan Li↗…

DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photorealistic, game-style, and stylized domains. Our data engine combines camera-accurate Unreal Engine rendering, action-rich gameplay recordings, and real-world videos with recovered camera geometry. For camera control, we introduce E-PRoPE, a lightweight variant of projective positional encoding that retains PRoPE's projective camera geometry while applying camera-aware attention to spatially reduced tokens. We convert a bidirectional video generator into a few-step autoregressive world model using causal forcing, DMD-style distillation, and long-rollout training. Training on self-generated long-horizon contexts exposes the model to its own generated history and reduces the style and color drift that accumulates across autoregressive chunks. Memory-Conditioned Scene Persistence retrieves earlier views through camera-geometry-based retrieval, while residual recycling makes the conditioning path less sensitive to imperfect memory latents. Event Instruction Tuning adds composable event control, and reinforcement learning alignment recovers camera control and visual quality after distillation. With mixed-precision DiT execution, residual reuse, 75\%-pruned VAE decoding, and asynchronous pipeline parallelism, DreamX-World 1.0 reaches up to 16\,FPS on eight RTX\,5090 GPUs. On our 5-second basic evaluation, DreamX-World 1.0 achieves a camera-control score of 73.75 and an overall score of 84.76, outperforming HY-WorldPlay 1.5 and LingBot-World in overall score, which achieve 80.79 and 80.45, respectively.

阅读与讨论 → 访问原文 →