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。

01.
medRxiv (Medicine) 2026-06-22

Climatic Drivers of Malaria risk in Children Under Five: A Large-Scale Analysis of individual-level data for 350,000 children in 26 Sub-Saharan African Countries

Background Malaria risk is influenced by climatic conditions, and children under five are particularly vulnerable due to their limited acquired immunity. We investigate the association between climatic factors and malaria risk in 350,000 children aged 5-59 months in sub-Saharan Africa over 18 years. Methods We included children aged 5-59 months with malaria tests from Demographic and Health Surveys (DHS) in 26 sub-Saharan African countries between 2006 and 2023. We linked these data to high-resolution climate exposures: temperature, precipitation, soil moisture, actual evapotranspiration and specific humidity. We fitted a mixed-effect logistic regression model incorporating Distributed Lag Non-linear Models (DLNM) over 1-6 month lag window for each exposure, controlling for seasonality and long-term trends. We examined effect modification by maternal education, household wealth, residential type, water source, sanitation facility, child age and sex, use of insecticide-treated bed nets (ITNs), and the age of the household head. Results Malaria prevalence was 19.5%. Malaria risk was highest at 24 degrees (OR: 1.45, 95% CI: [1.36, 1.54]), followed by a decline at higher temperatures. This elevated risk was mainly driven by short-term exposures (1-2 months). Precipitation increased risk up to 59 ~ 120 mm (1.10, [1.07, 1.12]), after which heavier rainfall reduced risk, particularly at short- to medium-term lags (1-4 months). Soil moisture was associated with increasing risk up to ~80 mm (1.11, [1.08, 1.14]), with a plateau at higher levels. Evapotranspiration showed a strong, near-linear positive association with malaria risk. Higher specific humidity levels (>14 g/kg) presented a lower risk, reaching a 45% reduction at 17 g/kg (0.55, [0.49, 0.61]), with the strongest protective effects at short-term lags (1-2 months). Elevated malaria risk at low and moderate average temperatures was particularly evident among children who did not sleep under an ITN net. Conclusion Malaria risk in children under five is strongly shaped by climatic factors, with complex and delayed associations. The findings provide evidence to guide targeted interventions and early-warning strategies for vulnerable populations.

02.
arXiv (CS.AI) 2026-06-12

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

arXiv:2606.13316v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods often encourage unnecessarily long reasoning rollouts, which can degrade reasoning coherence and exhaust the available context budget. Existing approaches to long-context organization often depend on external mechanisms to organize rollouts, rather than enabling the model to manage its own reasoning trajectory. To address this limitation, we propose ReSum, a novel RLVR framework that enables LLMs to compress and organize their reasoning trajectories through self-summarization. Our pilot studies show that self-summarization stabilizes generation by lowering token-level entropy, and that introducing a ``summarization'' phrase can substantially mitigate errors propagated from an incorrect rollout prefix. Motivated by these findings, ReSum adopts a summarization-aware adaptive rollout mechanism that contrastively evaluates whether self-summarization benefits the ongoing reasoning process. Specifically, when the model spontaneously triggers self-summarization, ReSum masks the summarization phrase to create a contrastive branch; for non-summarization positions, it instead randomly injects the phrase to create a matched branch. We further design a summarization-aware advantage to enable finer-grained comparison between contrastive rollout trajectories. Extensive experiments show that ReSum improves performance at an average of 4\% while reducing rollout length by 18.6\%.

03.
arXiv (quant-ph) 2026-06-11

Single Photon Cross-Phase Shifts Can Be Enhanced by Localization in both Frequency and Time

arXiv:2606.11516v1 Announce Type: new Abstract: Single-photon optical nonlinearities face a fundamental trade-off: maximum nonlinearity requires both spectral resonance (narrow bandwidth) and high peak intensity (short duration), constraints that are incompatible due to the time-energy uncertainty relation. We demonstrate experimentally that this limitation does not need to exist in cases involving post-selection. We measure a cross-phase shift (XPS) produced by a resonant photon from a narrow-band source that is first transmitted through a cold atomic cloud and then localized in time through detection. The peak size of this XPS is greatly enhanced compared to that of Gaussian single-photon-level pulses without post-selection, benefiting from the narrow bandwidth of the resonant prepared state and the high intensity of the post-selected state simultaneously. We measure enhancements in the peak XPS of 6$\pm$1 at an optical depth (OD) of 2.4$\pm$0.1, and our results are in qualitative agreement across a range of optical depths with the recently developed weak value theory of atomic excitation [Thompson et al., APL Quantum 2, 036108 (2025)] for such post-selected photons. This work uncovers new consequences of having simultaneous knowledge of frequency and time, raising new foundational questions about how a particle behaves, and interacts with other systems, when its preparation and post-selection are non-commuting.

04.
arXiv (CS.AI) 2026-06-19

Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

arXiv:2605.22748v2 Announce Type: replace-cross Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

05.
arXiv (CS.CL) 2026-06-17

Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Health Questionnaire-9 (PHQ-9) support symptom monitoring at scale, but real-world completion rates are low, introducing response bias and systematic missingness. Passive approaches that infer severity from routinely generated data could close this gap. We address this by predicting PHQ-9 total scores directly from transcripts of conversations between users and an AI mental health application, requiring only conversation text and no additional clinical data. We fine-tune a Qwen3.5-27B backbone with a regression head, augment 3,111 ground-truth labels with pseudolabels generated by a reasoning model (Claude Opus) and iteratively trained intermediate models, for a combined dataset of 6,283 users. On a held-out test set of 842 users, our best model achieves MAE = 2.6, RMSE = 4.0, Pearson r = 0.80, and AUC = 0.91 at the PHQ-9 >= 10 clinical threshold. We also find AUC > 0.87 at every severity threshold from PHQ-9 >= 3 to PHQ-9 >= 24, demonstrating that the model captures depression severity across the full clinical spectrum. This work opens the door to passive, continuous symptom monitoring in AI mental health platforms, without requiring users to complete self-report measures.

06.
arXiv (CS.CV) 2026-06-11

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

09.
arXiv (CS.CL) 2026-06-11

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this representative vector, such that its dot-product with token can better reflect token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a matrix. Based on this principle, we propose a router redesign with Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this alignment facilitates more effective MoE models.

10.
arXiv (CS.CL) 2026-06-16

A Self Consistency Based Reranking for Narrative Question Answering

Narrative question answering (NQA) is a challenging task in natural language processing that requires models to understand long textual contexts, capture relationships across events, and generate coherent responses. Despite recent advances in pretrained language models, most existing approaches rely on a single decoding output during inference, making them sensitive to generation variability and often resulting in incomplete or inconsistent answers .To address this limitation, we propose a self-ensemble Self-Consistency-Based reranking framework for narrative question answering. The proposed method generates multiple candidate answers for each story-question pair and selects the final answer based on semantic agreement among the generated responses. This allows the model to explore diverse answer formulations while improving robustness through consensus-based selection without requiring modifications to the underlying architecture .The framework combines pretrained and fine-tuned language generation with multi-answer inference and similarity-based reranking. We evaluate the proposed approach on the NarrativeQA dataset using multiple models, including FLAN-T5 (Base and Small) and Pegasus-Large, under both baseline and fine-tuned settings .Experimental results demonstrate that the proposed method consistently improves performance across all models. In particular, FLAN-T5-Base achieves the best overall performance, improving from 82.32% to 86.66% (+4.34%) when combined with self-ensemble inference. Additionally, the largest improvement is observed with Pegasus-Large, which increases from 72.50% to 87.07% (+14.57%), highlighting the effectiveness of the proposed strategy.

11.
arXiv (CS.AI) 2026-06-12

Muse Spark Safety & Preparedness Report

arXiv:2606.12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

12.
bioRxiv (Bioinfo) 2026-06-15

DAQplugin: Deep Learning based Real-time Model Evaluation Plugin for ChimeraX

Although an increasing number of protein structures are determined by cryogenic electron microscopy (cryo-EM), protein structure modeling frequently suffers from residue misassignments and sequence register shifts, particularly in regions with ambiguous density. Here, we present DAQplugin, a ChimeraX plugin that performs real-time evaluation of protein models against cryo-EM density maps using the deep-learning-based residue-wise model quality (DAQ) score. Unlike existing validation tools that are typically applied after model construction, DAQplugin enables real-time deep-learning-based validation during model building and refinement. To our knowledge, DAQplugin is the first tool that provides real-time deep-learning based validation of protein models for cryo-EM map within an interactive modeling environment. In addition to identifying potential modeling errors, DAQplugin also provides guidance for correcting sequence register shifts by suggesting alternative residue placements along the backbone. The computation in this plugin is designed to run efficiently on general CPUs without requiring GPU hardware. Using DAQplugin, users can perform deep-learning-based validation on standard laptops during interactive model building, model-map fitting, and refinement. DAQplugin is able to facilitate more accurate interpretation of cryo-EM density maps and improve the reliability assessment of protein structure models.

13.
arXiv (CS.LG) 2026-06-19

Interactive Pareto navigation for deep multi-task learning

arXiv:2606.19521v1 Announce Type: new Abstract: In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a novel framework, Preference Pareto Exploration (PPE), which enforces the decision maker's preferences while accounting for the geometry of the Pareto set in an interactive exploration process. PPE is based on a predictor-corrector method that performs predictor steps tangential to the manifold of Pareto-optimal solutions, following the decision maker's preference. The subsequent corrector step results in a new trade-off reflecting this preference. To avoid explicit Hessian computations when characterizing the tangent space of the manifold, we employ a Krylov subspace method that relies solely on matrix-vector products. These products can be efficiently obtained via automatic differentiation, ensuring both efficiency and robustness throughout the optimization process. The method's functionality and performance are demonstrated using both toy problems and examples from deep learning.

14.
arXiv (CS.AI) 2026-06-16

Infant Spontaneous Movement Noise Improves Exploration in Deep RL

arXiv:2606.16590v1 Announce Type: cross Abstract: Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise can improve exploration efficiency by producing smooth trajectories with better coverage of the state space. We inquire whether action noise inspired by infant spontaneous movements can also improve exploration in deep RL. We find that the power spectral densities of babies' end-effector velocities follow a colored noise process where the spectral exponent increases with age. Inspired by this developmental pattern, we introduce a mechanism that progressively increases the temporal auto-correlation of exploration noise during RL training, matching the infant statistics. Experiments across several RL environments show that infant-inspired noise produces structured exploratory behavior and can improve learning efficiency compared to conventional exploration strategies. These findings suggest that human motor and cognitive development can provide useful guidance for designing learning mechanisms in artificial agents. Our code is available at https://github.com/trieschlab/baby-noise-rl.

15.
arXiv (CS.AI) 2026-06-18

Robust Regularized Policy Iteration under Transition Uncertainty

arXiv:2603.09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate and derives an efficient policy iteration procedure based on a robust regularized Bellman operator. We provide theoretical guarantees by showing that the proposed operator is a $\gamma$-contraction and that iteratively updating the surrogate yields monotonic improvement of the original robust objective with convergence. Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines including percentile-based methods on the majority of environments while remaining competitive on the rest. Moreover, RRPI exhibits robust performance by aligning lower $Q$-values with high epistemic uncertainty, which prevents the policy from executing unreliable out-of-distribution actions.

16.
arXiv (CS.LG) 2026-06-16

Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees

arXiv:2606.16610v1 Announce Type: cross Abstract: Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood. In this work, we provide refined and novel convergence guarantees for Brownian motion based DFMs, focusing on the discretization error. Our analysis is conducted under the Kullback-Leibler (KL) divergence and the 2-Wasserstein distance. Under finite-moment conditions and a mild score integrability assumption, we derive KL convergence bounds with improved dimensional dependence compared to prior work, achieving, up to our knowledge, state-of-the-art scaling under minimal conditions. We further extend the analysis to the 2-Wasserstein distance: under an additional first-order score integrability assumption and a weak log-concavity condition, we obtain convergence guarantees with dimensional dependence consistent with the KL case.

17.
Nature (Science) 2026-06-08

Fifty years since a simple equation described the chaos of biology

An exploration of chaos theory in population dynamics showed that unpredictable systems can often be modelled using surprisingly simple mathematics. An exploration of chaos theory in population dynamics showed that unpredictable systems can often be modelled using surprisingly simple mathematics.

18.
arXiv (CS.LG) 2026-06-11

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

arXiv:2606.11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initialization, often itself a pretrained or previously aligned model. Quadratic-regularized MD, including GD and Mahalanobis geometries, is well-known to be stable for convex smooth objectives. We show a sharp contrast: once the regularizer is non-quadratic, MD can be exponentially more sensitive to initialization than GD, even with a well-conditioned regularizer in Euclidean norm. We give a three-dimensional construction with a convex, smooth objective and a strongly convex, smooth, well-conditioned regularizer where an initial $\varepsilon$ perturbation is quickly amplified to $\min\{polylog^{-1}(1/\varepsilon), \varepsilon e^{\Omega(\eta T)}\}$ after $T$ iterations of MD with step size $\eta$. For canonical KL-regularized MD on the simplex, we show that even linear objectives can amplify an initial $\varepsilon$ perturbation exponentially fast in high-dimensional or near-boundary regimes. Finally, we show that adding a Bregman regularization term toward an anchor point can stabilize the dynamics while largely preserving the optimization guarantees, and that the choice of anchor is crucial: anchoring at the initialization only partially mitigates the instability, whereas anchoring at a fixed point yields a more stable mechanism.

19.
Nature (Science) 2026-06-10

Lignin to adipic acid in a high-yield chemical and biological redox process

Viable manufacturing pathways to produce bio-based chemicals from renewable feedstocks, such as lignin derived from plant biomass, are needed to decarbonize the chemicals manufacturing sector. Converting the recalcitrant lignin polymer to valuable bioproducts remains a longstanding challenge in biorefining, with the highest reported single-product yield from lignin currently around 20 wt% (refs. 1–4). Most existing lignin depolymerization strategies target aryl–ether bond cleavage, which can produce aromatic monomers in yields of only about 30 wt%, and still as complex mixtures with C–C-linked dimers and oligomers5,6. The recalcitrance of these C–C linkages between aromatic moieties fundamentally limits single-product yields from lignin, prompting the development of strategies to efficiently cleave these C–C bonds3,7–9. Here we show how reductive processing of lignin from poplar accesses a hydrocarbon mixture of alkyl-aromatic monomers and oligomers that is privileged for oxidative conversion to monomeric aromatic carboxylic acids, comprising mostly benzoic acid and phthalic acid isomers in up to 73 wt% monomer yields, using a Co/Mn/Br catalyst. The soil bacterium Pseudomonas putida KT2440 was engineered to convert this mixture of aromatic carboxylic acids to muconolactone, a precursor to bio-based nylons, enabling final adipic acid yields up to 26 wt% (gram adipic acid per gram lignin) with a maximum theoretical yield of 57 wt%. This pairing of reductive and oxidative steps with lignin resembles processes in petrochemical refining and shows how lignin may be converted into a single, valuable bioproduct in high yields. A chemical and biological redox process that resembles processes in petrochemical refining is used to convert lignin from poplar into a single, valuable bioproduct, adipic acid, in high yields.

20.
arXiv (CS.LG) 2026-06-19

SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with Application to GPU Data

arXiv:2606.20451v1 Announce Type: cross Abstract: Competing risks are commonly observed in engineering fields and can bring challenges to time-to-event data modeling when the application scenarios are complicated. Recently, deep neural networks have received great attention for prediction with competing risks, due to their flexibility and high learning capability. However, the complexity of neural network structure brings extra difficulty in hyperparameter tuning based on different data inputs. Additionally, when an engineered system has complex physical structures with multiple hierarchical levels, treating all structural levels as a single group of inputs may fail to capture critical information. To address the issues, we propose a Structured Segmented Hazard Deep Neural Network (SSH-Net) for failure time prediction under cause-specific competing risks framework. Our approach associates neural network structure with data structures, and allows different covariate groups to impact the failure prediction through separate sub-networks. The neural network is constructed based on a cause-specific competing risks model. The SSH-Net outputs cause-specific hazard functions, and utilizes the penalized log-likelihood as the loss function. The prediction accuracy of SSH-Net is validated through simulation studies by evaluating the Brier score, the area under receiver operating characteristic curves (AUC), and the root mean square error (RMSE) of the predicted cause-specific cumulative incident function. We further demonstrate the model's ability to predict failure time distribution functions using the Titan GPU failure time data.

21.
arXiv (CS.AI) 2026-06-18

Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks

arXiv:2606.18272v1 Announce Type: cross Abstract: This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the Bimodal Constraint-Avoidance Utility Theorem, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model (\texttt{otel-llm-1b-it}) confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25\%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui.

22.
arXiv (CS.AI) 2026-06-12

WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning

arXiv:2604.08958v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-online RL leverages prior data but typically assumes a given fixed dataset and does not address how to generate reliable data for transfer. We propose World Model-Based Experience Transfer (WOMBET), a framework that jointly generates and utilizes prior data. WOMBET learns a world model in the source task and generates offline data via uncertainty-penalized planning, followed by filtering trajectories with high return and low epistemic uncertainty. It then performs online fine-tuning in the target task using adaptive sampling between offline and online data, enabling a stable transition from prior-driven initialization to task-specific adaptation. We show that the uncertainty-penalized objective provides a lower bound on the true return and derive a finite-sample error decomposition capturing distribution mismatch and approximation error. Empirically, WOMBET improves sample efficiency and final performance over strong baselines on continuous control benchmarks, demonstrating the benefit of jointly optimizing data generation and transfer.

23.
arXiv (CS.LG) 2026-06-18

Hierarchical Attention via Domain Decomposition

arXiv:2606.18525v1 Announce Type: new Abstract: We propose a hierarchical attention mechanism based on two-level overlapping Schwarz domain decomposition. The method is motivated by the observation that two-level Schwarz domain decomposition methods combine local subdomain corrections with a coarse level that communicates global, long-range information. We test its usefulness in the context of finite-dimensional operator learning using a simple, one-dimensional diffusion problem with homogeneous Dirichlet boundary conditions. Although elementary, this problem provides a controlled sequence-to-sequence setting in which the exact nonlocal solution operator is known. After discretization, learning the solution operator amounts to approximating the inverse of a symmetric positive definite matrix. As a baseline, we use a global softmax-free low-rank attention operator of the form $QK^T$. The proposed construction replaces this dense global factorization by a two-level additive structure: local low-rank attention blocks on overlapping subdomains are combined with a coarse attention block. The resulting operator has the form $$M_{\theta}^{-1} = \Phi Q_0 K_0^T \Phi^T + \sum_{i=1}^{N} R_i^T D_i^{1/2} Q_i K_i^T D_i^{1/2} R_i.$$ Here $R_i$ restricts to an overlapping subdomain, $D_i$ is a partition-of-unity weight, and $\Phi$ is a coarse interpolation (or prolongation) matrix. Numerical experiments for synthetic Fourier right-hand sides indicate that the domain-decomposition attention operator is able to train faster and can give more accurate approximations than a global low-rank attention baseline while using significantly fewer parameters.

24.
arXiv (CS.CL) 2026-06-16

DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing

As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical problem. Existing defenses often rely on known-attack coverage, prompt-level semantic judgment, or local runtime control, yet these paths can become unstable under evolving prompt packaging, expression rewriting, and structure manipulation. We observe that many black-box jailbreaks do not remove the harmful goal, but reorganize the information needed to express and execute it, thereby evading safety alignment while remaining recoverable during generation. Motivated by this observation, we propose DoubtProbe, a dual-branch inference-time defense framework that combines structural verification with semantic auditing and formulates black-box jailbreak defense as consistency checking under controlled transformation. The structural branch extracts a structured representation from the original request, reconstructs the request under representation constraints, and detects information-preservation failures between the original and reconstructed requests; the semantic branch audits the original prompt directly. We evaluate DoubtProbe against representative black-box defenses on jailbreak and benign-request benchmarks, and further test backbone transfer from Qwen2.5-72B to Llama-3.1-70B. Results show that DoubtProbe achieves a stronger and more stable defense-utility trade-off: on Qwen2.5-72B, it reduces the JBB attack success rate from 0.293 to 0.100 and the CodeAttack attack success rate from 0.152 to 0.001, while maintaining false positive rates of 0.022 and 0.016 on AlpacaEval and OR-Bench; the same pattern remains stable on Llama-3.1-70B. These findings show that structural inconsistency signals provide a practical and generalizable basis for black-box jailbreak defense, especially when combined with semantic auditing.

25.
medRxiv (Medicine) 2026-06-22

Brain-gut axis imaging, motion correction with 11C-carfentanil total-body PET

Background: Mu-opioid receptors (MORs) are expressed throughout the body including in the brain and gastrointestinal (GI) tract. Total-body PET imaging of the brain and GI tract offers a promising approach for cross-sectional in vivo evaluation of the MOR brain-GI axis. However, intestinal motility and bladder filling introduce motion throughout the GI tract over the scan window. Here we establish analysis methodology to account for motion for dynamic imaging of the brain-GI axis, to further characterize peripheral MORs throughout the body and provide a framework for semi-automatic total-body PET modeling. Methods: 4 subjects underwent 90-min dynamic [11C]-carfentanil (cfn) total-body PET acquisitions at baseline, after intravenous naloxone (central antagonist) administration, and after orally administered loperamide (peripheral agonist and P-glycoprotein substrate). Thalamic MOR availability was measured using the Logan reference tissue model. Using CT-based segmentation, the GI tract was subdivided into anatomical segments, in addition to other peripheral organs (e.g., liver, psoas muscle). Frame-by-frame semi-automatic motion correction was performed with three distinct reference frames (11-14 min post-injection, p.i., 35-40 min p.i., and 85-90 min p.i.). The performance of these three were compared to manual correction. Compartment modeling and Logan graphical analysis were performed to estimate relevant kinetic parameters (K1, VT, VTLogan). Results: Across the 4 subjects and regions, kinetic parameter estimates were highly correlated (r>0.7) for K1, VT and VT Logan when comparing semi-automatic (reference frame at 35-40 min p.i.) and manual correction. With semi-automatic motion correction, graphical-based estimation of VTLogan in the gastrointestinal tract was significantly decreased with loperamide relative to baseline (p