Author Correction: A broadly protective antibody targeting gammaherpesvirus gB
该条目无摘要(多为勘误、社论或新闻类内容,出版方未提供摘要)
Academic Intelligence · Curated Daily
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。
该条目无摘要(多为勘误、社论或新闻类内容,出版方未提供摘要)
arXiv:2511.04250v2 Announce Type: replace Abstract: We study space-bounded communication complexity for unitary implementation in distributed quantum processors, where we restrict the number of qubits per processor to ensure practical relevance and technical non-triviality. We model distributed quantum processors using distributed quantum circuits with nonlocal two-qubit gates, defining the distributed communication complexity of a unitary as the minimum number of such nonlocal gates required for its realization, up to permutations of data qubit positions. Our contributions are twofold. First, for general $n$-qubit unitaries, we improve upon the trivial $O(4^n)$ communication bound. Considering $k$ pairwise-connected processors (each with $n/k$ data qubits and $m$ ancillas), we prove the communication complexity satisfies $O\left(\max\{4^{(1-1/k)n - m}, n\}\right)$ – for example, $O(2^n)$ when $m=0$ and $k=2$ – and establish the tightness of this upper bound. We further extend the analysis to approximation models and general network topologies. Second, for special unitaries, we show that both the Quantum Fourier Transform (QFT) and Clifford circuits admit linear upper bounds on communication complexity in the exact model, outperforming the trivial quadratic bounds applicable to these cases. In the approximation model, QFT's communication complexity reduces drastically from linear to logarithmic, while Clifford circuits retain a linear lower bound. These results offer fundamental insights for optimizing communication in distributed quantum unitary implementation, advancing the feasibility of large-scale DQC systems.
Background: Hypertensive disorders of pregnancy (HDP) may first be diagnosed antepartum, during labor, or postpartum. We utilized untargeted large-scale proteomics to identify pathways associated with HDP based on timing of onset. Methods: We performed a nested case-control study comparing differential protein expression, from the SomaScan 7K platform, based on timing of onset of HDP versus controls (referent) using first-trimester samples from the NuMoM2b-Heart Health Study, a multi-site cohort that followed nulliparous individuals from the first trimester. Associations of proteins with timing of onset of HDP, adjusted for co-variates, were assessed using logistic regression q value-based false discovery rates and pathway enrichment and differential expression analysis were conducted. Results: Of 1628 individuals included, 678 had HDP, of which 67% manifested antepartum (AP), 29% intrapartum (IP), and 3% postpartum (PP). After adjusting for co-variates, compared to controls, 698 proteins, 39 proteins, and 144 proteins were differentially expressed in those with HDP according to AP, IP, PP onset, respectively. There was little overlap in individual protein expression based on timing of HDP. Pathway enrichment and graphical summary analyses suggested distinct processes. Specifically, there was downregulation of angiogenic proteins in AP HDP, downregulation of immune-related proteins in IP HDP, and upregulation of complement activation promoting fibrotic changes leading to cardiac dysfunction in PP HDP. Conclusion: There are differences in first-trimester protein expression based on whether HDP first manifests AP, IP or PP. This raises the possibility that there may be distinct mechanistic phenotypes that could uniquely inform diagnostic and therapeutic targets for HDP.
Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical claim verification, but cost and opacity limit scalable use. We fine-tune three small LLMs: Phi-3-mini (3.8B), Qwen2.5-3B, and Mistral-7B, via QLoRA on SciFact and HealthVer, providing the first study of QLoRA models against GPT-4o and fine-tuned BioLinkBERT encoders. Mistral-7B QLoRA surpasses both GPT-4o and GPT-5 (up to 12% F1 gain) at a fractional cost using just 1,008 training examples. We conduct extensive in-domain and cross-domain evaluation: models trained on SciFact tested on HealthVer and vice versa, at matched sizes to isolate dataset structure from data quantity. We identify a previously unreported structural artifact in SciFact that inflates in-domain scores, and show through bidirectional out-of-domain evaluation that training on structurally sound data enables robust cross-domain transfer. We plan to release all code and adapter checkpoints.
arXiv:2606.13379v1 Announce Type: new Abstract: Memristors provide a new chance for resource-efficient computation of neural models for natural language processing by enabling analog execution of vector-matrix-multiplication. Yet, computations on these devices are currently subject to larger distortion, both in weight programming and execution. In this work, we identify large output values of transformed positional encodings to cause major degradation within analog-to-digital conversion (ADC) as part of memristor-based computation. By adjusting the proportion of weight and precision bits of the ADC of specific memristor layers, we reduce the degradation of the execution by ~50% relative, while keeping the estimated energy consumption stable. Additionally, we investigate scenarios where the ADC cannot be modified. In that case the degradation can be reduced by ~30% relative after removing encoding-related linear transformations.
arXiv:2511.04389v2 Announce Type: replace Abstract: Protocols for quantum measurement are an essential part of quantum computing. Measurements are no longer confined to the final step of computation but are increasingly embedded within quantum circuits as integral components of noise-resilient algorithms. However, each observable typically requires a distinct measurement basis, often demanding a different circuit configuration. As the number of such configurations typically grows with the number of qubits, measurements constitute a major bottleneck. Focusing on electronic structure calculations in crystalline systems, we propose a measurement protocol that restricts the required measurement configurations to an absolute minimum of just three, independent of the number of qubits. This makes it one of the few known protocols that do not scale with qubit number. In particular, we derive the measurement protocol from the symmetries of tight-binding (TB) Hamiltonians and implement it within the Orthogonal-Ansatz Variational Quantum Eigensolver (OA-VQE) algorithm. We demonstrate its performance on three systems, namely a two-dimensional CuO$_2$ square lattice (3 qubits), bilayer graphene with hexagonal (Honeycomb) lattice (4 qubits) and three-dimensional diamond lattice (10 qubits). Beyond tight-binding systems, the protocol can be extended to enable efficient initial state preparation for many-body Hamiltonians, such as multi-orbital Hubbard models in a momentum space.
Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs. We study this question through feature stability: for each SAE feature, we estimate the probability that a similar feature reappears in an independently trained SAE. This yields a scalable per-feature signal that separates stable from unstable features. In a large-scale study across seeds, models, layers, dictionary sizes, and SAE variants, we find a pronounced functional asymmetry: stable features carry most of the reconstruction- and prediction-relevant signal, while unstable features have weak marginal impact and are dominated by low-frequency surface-form triggers in both activation statistics and automatic explanations. Geometrically, unstable features are individually non-reproducible but concentrate in reproducible lower-rank subspaces, suggesting that seed dependence often reflects basis ambiguity within a shared region of activation space rather than pure noise. A controlled synthetic model makes this mechanism explicit, showing that low-rank ground-truth features can be recovered at the subspace level while remaining non-identifiable as individual SAE latents across seeds. Finally, by pooling unique cross-seed features, we construct more stable SAEs while preserving explained variance in this setting. Together, these results show that unstable features are not merely failed or noisy latents: they have weak individual functional impact, but reflect reproducible low-dimensional structure that standard SAEs resolve differently across seeds.
arXiv:2606.06452v3 Announce Type: replace Abstract: We present a rigorous theoretical framework for symmetry breaking and quantum irreversibility arising from stochastic Ito field reversal within a cubic-quintic nonlinear Schrodinger equation (CQ-NLSE) formalism. Starting from three physically motivated considerations, forward and backward nonlinear stochastic differential equations are derived via the Ito calculus. Kinematic time-reversal is shown to be fundamentally incompatible with the Ito stochastic structure, yielding the universal asymmetry-coupling parameter of 2/3. An energy-driven collapse operator proportional to the product of noise strength, local probability density, and excitation energy squared is introduced, amplifying the collapse in high-density, high-excitation regions. Exactly bright soliton solutions are obtained for a quasi-one-dimensional BEC of attractive Li-7 atoms, with forward and backward amplitude ratio of 1.870. Heat map analysis of the parameter planes reveals that the forward collapse operator grows monotonically in time while the backward counterpart decays, achieving a ratio approximately 1030, sharply distinguishing this framework from conventional symmetric collapse models.
arXiv:2606.14707v1 Announce Type: cross Abstract: AI training and deployment consume substantial electricity, but carbon outcomes remain weakly integrated into routine model development decisions. This paper presents Green AI Carbon Optimizer with two primary contributions: (i) a carbon aware cloud region recommendation method for training workloads, and (ii) a power law forecasting pipeline for global AI energy demand. For location recommendation, we combine regional grid carbon intensity, renewable share, and data center Power Usage Effectiveness (PUE) into a unified scoring model across 100+ regions from major cloud providers. For a reference workload (8*A100, 100h), estimated emissions in our sampled regions range from 7.74kg to 272.00kg CO2. Selecting the best region instead of the worst corresponds to a 97.2% reduction relative to the worst case. Ablation shows that ranking by renewable share alone can select regions with higher CO2 emissions than rankings that include grid carbon intensity. For forecasting, we fit a power law relation between parameter count and training energy using 26 anchor models. We combine this fit with scenario assumptions on model growth, hardware efficiency, and training frequency, and evaluate sensitivity to inference ratio and ecosystem scaling. Across scenarios, projected 2030 demand ranges from 7TWh to 1,436TWh under the stated assumptions, highlighting the importance of deployment choices, model scaling discipline, and transparent energy reporting.
We present an automated approach to distinguish between ply instances in semantic segmentation masks of high-resolution carbon-fiber reinforced polymer micrographs. Interpreting the segmentation mask as a graph with pixels as vertices, enables us to use a shortest-path algorithm yielding the ply-separating paths. Thereby, we bridge the gap between semantic segmentation and ply instance segmentation using global information. We successfully apply our approach on high-resolution micrographs featuring a broad range of characteristics like artificially added gaps in single or multiple plies, different stacking sequences and ply traversing cracks. Assigning each fiber pixel to a ply based on the calculated paths, allows for a comprehensive, quantitative ply analysis with respect to its microstructural properties like the local fiber volume fraction as well as locally resolved ply and interleaf layer thickness. These insights help to reveal manufacturing-induced inhomogeneities, draw conclusions on manufacturing parameters and link mechanical properties to underlying microstructural imperfections.
arXiv:2510.22266v3 Announce Type: replace-cross Abstract: Identifying the factors that influence student performance in basic education is a central challenge for formulating effective public policies in Brazil. This study introduces a multi-level machine learning approach to classify the proficiency of 9th-grade and high school students using microdata from the System of Assessment of Basic Education (SAEB). Our model uniquely integrates four data sources: student socioeconomic characteristics, teacher professional profiles, school indicators, and principal management profiles. A comparative analysis of four ensemble algorithms confirmed the superiority of a Random Forest model, which achieved 90.2% accuracy and an Area Under the Curve (AUC) of 96.7%. To move beyond prediction, we applied Explainable AI (XAI) using SHAP, which revealed that the school's average socioeconomic level is the most dominant predictor, demonstrating that systemic factors have a greater impact than individual characteristics in isolation. The primary conclusion is that academic performance is a systemic phenomenon deeply tied to the school's ecosystem. This study provides a data-driven, interpretable tool to inform policies aimed at promoting educational equity by addressing disparities between schools.
This brief work discusses potential superspreading events that may occur during the World Cup in Mexico. The study is particularly focused on the city of Guadalajara due to a large recent outbreak in January and February and insufficient vaccine coverage prior to 2026. Keywords: Superspreading; measles outbreak; branching process; individual reproduction number; World Cup
arXiv:2606.19925v1 Announce Type: new Abstract: We investigate the asymptotic behavior of solutions to a class of fully coupled forward-backward stochastic differential equations with time-delayed generators. Such systems arise naturally in stochastic models with memory effects and constitute a significant extension of the classical fully coupled FBSDE framework. The presence of delay introduces additional analytical difficulties due to the dependence of the coefficients on the past trajectories of the solution processes and the resulting non-Markovian structure. Under suitable assumptions on the coefficients, we study the asymptotic properties of a perturbed delayed FBSDE driven by a small noise parameter. We first establish the convergence in distribution of the associated solution processes as the perturbation parameter tends to zero. We then prove almost sure convergence towards the solution of the corresponding deterministic limiting system. As a consequence of these asymptotic results, we derive a large deviation principle for the solution processes. Our results extend the asymptotic analysis of Cruzeiro, Gomes and Zhang (2014) from the classical fully coupled FBSDE setting to the delayed framework, and complement existing works on weakly coupled delayed forward-backward systems. They provide, to the best of our knowledge, the first large deviation principle for fully coupled forward-backward stochastic differential equations with delayed generators.
arXiv:2512.22350v2 Announce Type: replace-cross Abstract: We demonstrate a three-dimensional magneto-optical trap (MOT) of a metal hydride molecule, CaH. We are able to scatter $\sim$$10^{4}$ photons with vibrational loss covered up to vibrational quantum number $\nu=2$. This allows us to laser slow the molecular beam near zero velocity with a "white-light" technique and subsequently load it into a radio-frequency MOT. The MOT contains $230(40)$ molecules, limited by beam source characteristics and predissociative loss of CaH. The temperature of the MOT is below one millikelvin. The predissociative loss mechanism could, in turn, facilitate controlled dissociation of the molecule, offering a possible route to optical trapping of hydrogen atoms for precision spectroscopy.
Objectives: To estimate hyperlipidemia medication order prevalence and associated variables in U.S. skilled nursing facility (SNF) residents. Design: Retrospective, observational study. Setting and Participants: Electronic Health Record data from 447,080 SNF residents with a hyperlipidemia diagnosis identified in PointClickCare's Life Sciences clinical database (January-April 2025) were reviewed. Methods: The presence and absence of medication orders for hyperlipidemia treatments recommended by the American Heart Association were assessed. Descriptive analyses summarized demographic and clinical characteristics, and a modified Poisson regression model was used to estimate risk ratios for having a medication order, adjusting for demographic, clinical, and facility characteristics. Results: Overall, 83.3% of residents diagnosed with hyperlipidemia had at least one hyperlipidemia medication order. Statins were ordered by 96.2% of active order residents, while other medication classes i.e., omega-3 fatty acids, cholesterol absorption inhibitors, fibrates were less common (
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.
arXiv:2410.04666v3 Announce Type: replace Abstract: We introduce an embedding of the Klein-Gordon equation into a pair of coupled equations that are first-order in time. The existence of such an embedding is based on a positivity property exhibited by the Klein-Gordon equation. These coupled equations provide a more satisfactory reduction of the Klein-Gordon equation to first-order differential equations in time than the Schrodinger equation. Using this embedding, we show that the ``negative probabilities" associated with the Klein-Gordon equation do not need to be resolved by introducing matrices as Dirac did with his eponymous equation. For the case of the massive Klein-Gordon equation, the coupled equations are equivalent to a forward Schrodinger equation in time and a backward Schrodinger equation in time, respectively, corresponding to a particle and its antiparticle. We show that there are two positive integrals that are conserved (constant in time) in the Klein-Gordon equation and thus provide a concrete resolution of the historical puzzle regarding the previously supposed lack of a probabilistic interpretation for the field governed by the Klein-Gordon equation. A significant consequence is that the Schrodinger equation is given a relativistic formulation, which does not require creation and annihilation operators, i.e. quantum fields. Physically, this corresponds to a theory in which the positive and negative energy parts do not directly interact, hence there will be no annihilation events–for example, particle-antiparticle collisions which do not result in photon emission. Thus, one practical consequence of this relativistically consistent theory is a simple explanation for dark matter.
arXiv:2606.20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training. However, existing approaches materialize both attention distributions before computing the KL reduction, incurring $O(N_QN_K)$ memory and IO costs that become prohibitive at long context lengths. We present StreamKL, the first fused GPU primitive for attention KL divergence that eliminates this quadratic materialization. StreamKL derives a novel online formulation for the coupled two-distribution KL reduction, enabling a single one-pass forward kernel that streams query-key tiles through on-chip SRAM. For the backward pass, StreamKL recomputes attention probabilities tile-by-tile, avoiding storage of quadratic intermediates. We further design and implement efficient GPU kernels with dedicated optimizations. Experiments show StreamKL delivers up to $43\times$ and $14\times$ speedups over baseline methods in the forward and backward passes, respectively. Most importantly, StreamKL reduces the extra HBM footprint of attention distillation from $O(N_QN_K)$ to $O(1)$, enabling long-context distillation on a single GPU.
Faithful and robust pronoun use is important for fair and coherent generations, yet large language models largely fail when multiple referents use different pronouns. To study the interplay of reasoning, repetition, and bias in this task, prior work relies exclusively on behavioural approaches, which may not reflect a model's internal workings. Therefore, we provide a mechanistic, model-internal perspective on pronoun fidelity, testing whether three mechanisms – group entity binding (G), recency bias (R), and stereotypical bias (S) – are causally implemented across several SOTA language models. Using Boundless Distributed Alignment Search, we find all three coexist as causal subspaces distributed across network depth. No single mechanism fully explains model behaviour, but a combination of the three consistently accounts for 91-99.5%. An attention head analysis further reveals two competing copying routes; group binding and stereotype share a localized concept-level route that retrieves a bound occupation-pronoun unit, while recency uses a distributed token-level route that repeats surface forms. In sum, pronoun fidelity arises from competition between simultaneously active causal subspaces.
Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring traditional handcrafted methods and emphasizing contemporary deep learning approaches across various modalities, including RGB images, depth images, 3D point clouds, LiDAR scans, medical images, and vision-language interactions. Traditional methods, leveraging detectors like Harris corners and descriptors such as SIFT and ORB, demonstrate robustness under moderate intra-modality variations but struggle with significant modality gaps. Contemporary deep learning-based methods, exemplified by detector-free strategies like CNN-based SuperPoint and transformer-based LoFTR, substantially improve robustness and adaptability across modalities. We highlight modality-aware advancements, such as geometric and depth-specific descriptors for depth images, sparse and dense learning methods for 3D point clouds, attention-enhanced neural networks for LiDAR scans, and specialized solutions like the MIND descriptor for complex medical image matching. Cross-modal applications, particularly in medical image registration and vision-language tasks, underscore the evolution of feature matching to handle increasingly diverse data interactions.
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of benchmarks that simultaneously provide realistic patient simulation, clinician-verified diagnostic labels, and support for dynamic multi-turn consultation. We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. At its core is LingxiDiag-16K, a dataset of 16,000 EMR-aligned synthetic consultation dialogues designed to reproduce real clinical demographic and diagnostic distributions across 12 ICD-10 psychiatric categories. Through extensive experiments across state-of-the-art LLMs, we establish key findings: (1) although LLMs achieve high accuracy on binary depression–anxiety classification (up to 92.3%), performance deteriorates substantially for depression–anxiety comorbidity recognition (43.0%) and 12-way differential diagnosis (28.5%); (2) dynamic consultation often underperforms static evaluation, indicating that ineffective information-gathering strategies significantly impair downstream diagnostic reasoning; (3) consultation quality assessed by LLM-as-a-Judge shows only moderate correlation with diagnostic accuracy, suggesting that well-structured questioning alone does not ensure correct diagnostic decisions. We release LingxiDiag-16K and the full evaluation framework to support reproducible research at https://github.com/Lingxi-mental-health/LingxiDiagBench.
Effective visuo-tactile integration is critical for robotic dexterous manipulation, especially when visual observations are unreliable or occluded. However, robustly aligning sparse, heterogeneous tactile measurements with dense visual representations remains a fundamental challenge. Most existing approaches require policies to learn cross-modal correspondences implicitly from limited demonstrations, without leveraging geometric priors. As a result, they are often data-inefficient and generalize poorly when visual observations are degraded. To address this limitation, we propose a framework that explicitly grounds physical contacts in the image domain. Using robot forward kinematics and camera calibration, we project tactile sensor locations directly onto the RGB image plane. We then render force-modulated Gaussian saliency maps to model spatial uncertainty arising from kinematic and calibration errors. By integrating these 2D spatial anchors through a zero-initialized conditioning architecture, our method injects physical contact priors into standard visual backbones while preserving pre-trained visual representations. We evaluate our method on six dexterous manipulation tasks in both simulation and the real world under severe visual occlusions. Real-world experiments show that explicit RGB-S grounding in the image domain improves real-world occluded manipulation success rates by $26.7$ percentage points over the strongest implicit visuo-tactile baseline, suggesting its improved spatial reasoning and robustness to occlusion. Project page: touch-as-saliency.github.io
Background and Objectives: Alkaline Ionized Water (AIW) is considered among the highest quality healthy drinking water worldwide and is widely discussed for its various health benefits. Hydron Alkaline Ionized Water (HAIW) is produced through electrolysis, resulting in a stable pH of approximately 9.5 with a negative Oxidation Reduction Potential (ORP), making it an antioxidant beverage. The objective of this study was to evaluate the safety of HAIW and its effects on digestion, sleep, energy, and overall quality of life in healthy participants compared to Packaged Drinking Water (PDW). Materials and Methods: A randomized, controlled, double blind, prospective clinical study was conducted in which a total of 24 healthy participants between the age group of 21 to 40 years were randomized in a 1:1 ratio to either HAIW Group or Packaged Drinking Water Group with equal gender distribution. Participants were hospitalized for 7 days and asked to consume at least 3 litres of the assigned water daily. Primary outcomes were safety-related laboratory parameters and adverse event monitoring. Secondary outcomes included assessment of digestion (appetite, digestion, bowel habits), urine parameters, sleep quality, freshness after waking, fatigue, energy/stamina/strength, quality of life, and global assessment Results: All 24 participants completed the study with no dropouts. Baseline demographics were comparable between the two groups. Assessment of primary safety-related laboratory parameters including Complete Blood count, liver function tests, renal function tests, blood sugar, Electrocardiogram and serum electrolytes showed non-significant change from baseline to 7 days and remained within normal limits in both groups, with non-significant difference between groups (p>0.05). HAIW showed significantly better improvement in appetite, digestion, and bowel habits from Day 2 onwards compared to Packaged drinking water. Sleep quality and freshness after waking up showed significant improvement from Day 3 and Day 2 respectively in the HAIW and PDW group, with significantly better improvement in HAIW group. Fatigue scores showed significant reduction at Day 6 and 7 in both groups with non-significant difference between groups. A total of 5 adverse events were reported (3 in HAIW, 2 in PDW), all unrelated to study products and were mild in nature. Global assessment showed excellent to good overall safety and tolerability in both groups. Conclusion: HAIW was well tolerated by all participants without any adverse effects. All laboratory safety parameters remained within normal range. HAIW demonstrated significant improvements in digestive function (appetite, digestion, bowel habits), sleep quality, and freshness after waking as compared to PDW. The study concludes that HAIW can be safely consumed. HAIW improves digestive and sleep-related functions.
Artificial intelligence is not replacing human intuition in these fields, but reimagining how questions are asked, explored and understood. Artificial intelligence is not replacing human intuition in these fields, but reimagining how questions are asked, explored and understood.
LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unlearning as learning a refusal behavior, but their on-policy optimization repeatedly samples from the same forget and retain/boundary prompts throughout training. We identify a critical inefficiency in this process: easy cases quickly converge and provide little useful gradient signal, while hard cases near the forget/retain boundary continue to produce low-reward rollouts that are discarded after a single use. To address this issue, we propose ReRULE, an off-policy replay enhancement for reinforcement unlearning. ReRULE stores low-reward hard-case rollout groups in a replay buffer during early GRPO training and reuses them in later stages through importance-sampled off-policy updates, redirecting computation toward boundary cases that still require learning. Theoretically, we show that ReRULE yields a tighter hard-case convergence bound than pure on-policy RULE. Empirically, ReRULE improves MUSE-Books Retain Quality from 46.3 to 56.2 while adding only 5–11% training time across benchmarks. Its limited improvement on the simpler TOFU setting further supports the intended conditional behavior: replay is most beneficial when the hard/easy disparity is pronounced.