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) 2026-06-15

Filum Terminale Diameter on Routine Pediatric MRI: A Large-Cohort Clinical Reference in 3,406 Children and the Age-Dependent Meaning of the 2-mm Thickened-Filum Threshold

Background. A filum diameter >2 mm is the conventional MRI threshold for a thickened filum, but it derives from small, mostly adult series showing no age dependence; whether one cutoff suits all of childhood is untested. Objective. To build an age-specific filum-diameter reference on routine pediatric MRI and test, adjusting for image resolution, whether the 2-mm threshold is age-stationary. Materials and methods. In this retrospective study an nnU-Net tracer measured the maximal filum diameter on consecutive lumbosacral MRI; versus manual tracing it showed negligible bias but moderate single-measure agreement. After excluding report-confirmed fatty filum, lipoma, or tethered cord, the proportion >2 mm was analysed within one acquisition protocol and by logistic regression adjusting for voxel size and slice thickness. Results. Of 7,245 examinations, 3,869 (53%) were traceable; untraced ones were younger (median 0.75 vs 2.0 years). The presumed-normal cohort had median diameter 1.48 mm. At matched resolution, 2 mm marked the 94th percentile in infants (5.6% exceeded it) but the 83rd by 3-6 years (17.4%); the age effect persisted after adjusting for voxel size and slice thickness (3-6 years vs infants, adjusted OR 4.7; P < .001). Conclusion. Filum diameter clusters near 1.5 mm, and the fixed 2-mm cutoff flags ~5% of infants but ~17% of preschoolers. Caliber should be judged against an age-specific clinical reference, not one fixed cutoff; a thick filum is not itself a diagnosis of tethered cord.

02.
arXiv (CS.LG) 2026-06-16

Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts

arXiv:2606.15625v1 Announce Type: new Abstract: The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation. While federated learning (FL) emerges as the paradigm for privacy-preserving collaborative optimization, integrating MoE into FL under data heterogeneity may trigger conflicting expert optimizations. Client-specific data distributions force same-indexed experts to optimize under inconsistent or even conflicting feature-label correlations. This mismatch induces destructive interference during aggregation, thus destabilizing the optimization trajectory and degrading model performance. To address this issue, we propose FC-MoE, a federated conflict-aware framework for MoE fine-tuning. It employs an importance aware weighting scheme to prioritize reliable local updates and utilizes gradient consensus projection to suppress conflicting updates, ensuring a stable global optimization path. Moreover, a local knowledge retention mechanism further preserves specialized client expertise by re-anchoring domain-specific residuals. Extensive experiments demonstrate that FC-MoE accelerates convergence and enhances both global and local model performance in non-IID federated environments.

03.
arXiv (math.PR) 2026-06-18

Phase transitions for contact processes on sparse random graphs via metastability and local limits

arXiv:2505.22471v2 Announce Type: replace Abstract: We propose a new perspective on the asymptotic regimes of fast and slow extinction in the contact process on locally converging sequences of sparse finite graphs. We characterise the phase boundary by the existence of a metastable density, which makes the study of the phase transition particularly amenable to local-convergence techniques. We use this approach to derive general conditions for the coincidence of the critical threshold with the survival/extinction threshold in the local limit. We further argue that the correct time scale to separate fast extinction from slow extinction in sparse graphs is, in general, the exponential scale, by showing that fast extinction may occur on stretched exponential time scales in sparse scale-free spatial networks. Together with {the results of} Nam, Nguyen and Sly (Trans.\ Am.\ Math.\ Soc.\ 375, 2022), our methods can be applied to deduce that the fast/slow threshold in sparse configuration models coincides with the survival/extinction threshold on the limiting Galton-Watson tree.

04.
arXiv (CS.AI) 2026-06-17

MemTrace: Probing What Final Accuracy Misses in Long-Term Memory

arXiv:2606.17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, even when several questions probe the same fact, it cannot show how that fact behaves as conditions change. We introduce MemTrace, a benchmark whose unit of measurement is the knowledge point: a single typed fact about the user, rather than an individual question. MemTrace probes each fact along three controlled dimensions: memory age, defined by how many sessions ago the fact appeared in the history; question type, covering current state, earlier state, and trajectory of change; and evidence condition, covering present, missing, and contradicted-by-false-premise settings. Evaluating 13 memory-system configurations across four paradigms, we find that similar pooled accuracy hides different failures: recovering a fact's current and earlier states does not imply tracking how it changed, and safe abstention does not imply correcting a false premise. The dominant bottleneck is evidence use, not retrieval: when systems fail, the evidence was retrievable 10 times more often than it was missing. These results suggest that improving long-term memory requires better use of reachable evidence, not simply more storage or retrieval.

05.
arXiv (CS.AI) 2026-06-16

Inference-time Policy Steering via Vision and Touch

arXiv:2606.14981v1 Announce Type: cross Abstract: Inference-time steering adapts pre-trained generative robot policies during deployment by verifying candidate actions before execution. While prior methods typically perform this verification only with visual observations, vision alone is often insufficient for contact-rich manipulation, where success depends on both global task progress and subtle local interactions such as contact force. We introduce ViTaL, a visuo-tactile inference-time steering framework that formulates multimodal guidance as a bi-level optimization problem. At the high level, visual sampling-and-verification performs long-horizon mode selection, deciding what behavior the robot should execute. At the low level, tactile-guided diffusion editing refines the selected action sequence over a shorter horizon to satisfy local contact requirements. To support outcome-based steering, ViTaL learns a visuo-tactile latent world model and employs semantically aligned visual and tactile verifiers, including a novel text-conditioned tactile reward that scores predicted tactile futures directly in latent space. Across three real-world contact-rich manipulation tasks, ViTaL improves overall success by 51% over the base policy, outperforms unimodal steering by at least 33%, and exceeds naive multimodal fusion by at least 20%. Website: https://yilin-wu98.github.io/vital_website.

06.
PLOS Medicine 2026-05-29

Characterization of the VHH-Fc construct rimteravimab in healthy adults and patients hospitalized for mild-to-moderate COVID-19: Two Phase 1 randomized clinical trials

作者:

by Ellen Jansen, Viki Bockstal, Florence Herschke, Per Olsson Gisleskog, Manuela Rinaldi, Angélique Boerboom, Salah Hadi, Natalia Gaibu, Michel Moutschen, Dominique Tersago Background Variable Heavy domain of Heavy chains (VHH) are innovative tools to target unique epitopes, yet few have been developed as heavy chain-only antibodies for clinical use. Rimteravimab (referred to here as XVR011) is a humanized antibody developed for the treatment of mild-to-moderate coronavirus disease 2019 (COVID-19), consisting of two identical VHHs targeting the receptor binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike, with a human immunoglobulin (Ig) G1 fragment constant of antibody (Fc), silenced for Fc effector functions. We conducted two Phase 1 studies in healthy volunteers or hospitalized COVID-19 patients to evaluate its safety, tolerability, pharmacokinetics and immunogenicity. Methods and findings A randomized, double-blinded, single-center, placebo-controlled, single ascending dose study was performed in healthy volunteers (Phase 1a, EXEVIR0102, EudraCT 2021-003707-17), in parallel to an open-label, multi-center, single ascending dose study in patients hospitalized for mild to moderate COVID-19 (Phase 1b, EXEVIR0101, EudraCT 2020-005299-36, NCT04884295). Participants received a single intravenous infusion of 250, 500 or 1,000 mg of XVR011. The primary objective for both trials was the safety and tolerability of XVR011. Pharmacokinetics were evaluated as a secondary objective in Phase 1a and as an exploratory objective in Phase 1b. Efficacy (evaluated as respiratory parameters and COVID-19 clinical status) and antiviral activity in patients were evaluated as a secondary objective in Phase 1b. Immunogenicity was evaluated as an exploratory objective. Part 2 of the EXEVIR0101 study (initially a phase 1b/2 study) was not conducted due to the loss of XVR011 potency against SARS-CoV-2 Omicron BA.2. Demographics, safety, efficacy, and immunogenicity were analyzed using descriptive statistics, while pharmacokinetics were analyzed with noncompartmental pharmacokinetics (PK) modeling.In the Phase 1a study, there were no infusion-related reactions, serious treatment-emergent adverse events (TEAEs) or TEAEs grade ≥3. 22/30 volunteers (73.3%) reported 53 TEAEs (49 Grade 1, 4 Grade 2) with none being related to XVR011. The most common TEAE was headache (n = 8, 26.7%) in various treatment groups. In the Phase 1b study, 27 hospitalized patients were enrolled, and followed up to 30 days. Seven patients (25.9%) reported a total of 15 TEAEs, the majority (80%) being mild to moderate (Grade 1–2). There were no treatment-related serious TEAEs. All TEAEs resolved by the end of the study. Peak exposure (maximal concentration, Cmax) and systemic exposure (area under the curve, AUC0-t, and AUC0-inf) for XVR011 increased dose-proportionally. Geomean half-life ranged from 15.4 to 17.0 days in Phase 1a, while individual half-life ranged from 11.4 to 15.6 days in Phase 1b. SARS-CoV-2 viral load, as detected in nasopharyngeal samples by reverse transcription and quantitative polymerase chain reaction (RT-qPCR), decreased similarly in all cohorts compared to baseline. No treatment-induced anti-drug antibodies (ADA) were detected in Phase 1a. In Phase 1b, higher XVR011 concentrations increased the likelihood of ADA formation, without impacting pharmacokinetics and pharmacodynamics. No obvious dose-response in COVID-19 clinical status or respiratory parameters was observed.Technological limitations included study size, absence of placebo for the Phase 1b, absence of repeated dosing, evolving SARS-CoV-2 variants and standard-of-care. Conclusions XVR011 displayed a favourable safety, tolerability, pharmacokinetics, and immunogenicity profile, both in healthy volunteers and in patients hospitalized for mild to moderate COVID-19. These data pave the way for the design and clinical development of VHH-Fc constructs.

07.
arXiv (CS.AI) 2026-06-12

The Query Channel: Information-Theoretic Limits of Masking-Based Explanations

arXiv:2604.16689v2 Announce Type: replace Abstract: Masking-based post-hoc explanation methods, such as KernelSHAP and LIME, estimate local feature importance by querying a black-box model under randomized perturbations. This paper formulates this procedure as communication over a query channel, where the latent explanation acts as a message and each masked evaluation is a channel use. Within this framework, the complexity of the explanation is captured by the entropy of the hypothesis class, while the query interface supplies information at a rate determined by an identification capacity per query. We derive a strong converse showing that, if the explanation rate exceeds this capacity, the probability of exact recovery necessarily converges to one in error for any sequence of explainers and decoders. We also prove an achievability result establishing that a sparse maximum-likelihood decoder attains reliable recovery when the rate lies below capacity. A Monte Carlo estimator of mutual information yields a non-asymptotic query benchmark that we use to compare optimal decoding with Lasso- and OLS-based procedures that mirror LIME and KernelSHAP. Experiments reveal a range of query budgets where information theory permits reliable explanations but standard convex surrogates still fail. Finally, we interpret super-pixel resolution and tokenization for neural language models as a source-coding choice that sets the entropy of the explanation and show how Gaussian noise and nonlinear curvature degrade the query channel, induce waterfall and error-floor behavior, and render high-resolution explanations unattainable.

08.
arXiv (quant-ph) 2026-06-16

Readout-Induced Leakage in Superconducting Circuits with Nonlinear Couplings

arXiv:2606.16055v1 Announce Type: new Abstract: In superconducting circuits, drive-induced unwanted transitions limit the readout power, thereby constraining readout speed and fidelity. When such transitions excite the qubit into leakage states, they produce correlated errors that are particularly harmful for quantum error correction. Native nonlinear qubit-readout resonator coupling is a promising alternative to conventional linear hybridization because it provides intrinsic Purcell protection and stricter selection rules for multiphoton processes. In realistic devices, however, we show that such a coupling alone neither eliminates nor necessarily suppresses drive-induced transitions. Instead, if not appropriately engineered, these couplings often worsen the situation by introducing additional parasitic processes. Moreover, the rates of these unwanted transitions remain sensitive to the choice of readout frequency, regardless of the coupling mechanism. We demonstrate that readout-induced leakage can thus vary by orders of magnitude even when readout frequencies differ by less than ~7%. Our results establish that the benefits of native nonlinear couplings are realized only through informed device design, including the spectral placement of relevant auxiliary modes and elimination of parasitic ones.

09.
arXiv (CS.CL) 2026-06-17

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) training-free cluster-based routing that exploits empirical priors for domain-specific alignment, and (2) RL-based multi-step routing that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.

10.
arXiv (CS.AI) 2026-06-12

FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models

arXiv:2605.03460v3 Announce Type: replace Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail in the financial domain, which exhibits unique characteristics. We propose a general 2 x 2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain-where the distinction between deterministic assessment and stochastic prediction is particularly critical-as ten financial reasoning tasks, forming the FinTSR-Bench benchmark based on S&P stocks. To this end, we propose FinSTaR (Financial Time Series Thinking and Reasoning), trained on FinTSR-Bench with distinct chain-of-thought (CoT) strategies tailored to each category. For assessment, which is deterministic (i.e., computable from observable data), we employ Compute-in-CoT, a programmatic CoT that enables models to derive answers directly from raw prices. For prediction, which is inherently stochastic (i.e., subject to unobservable factors), we adopt Scenario-Aware CoT, which generates diverse scenarios before making a judgment, mirroring how financial analysts reason under uncertainty. The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT. Code is available at https://github.com/seunghan96/FinSTaR.

11.
medRxiv (Medicine) 2026-06-22

Development of a Novel Risk Prediction Model for Rheumatoid Arthritis-Associated Interstitial Lung Disease (RA-ILD): A Longitudinal Study

Background: Interstitial lung disease (ILD) is one of the most common and potentially most devastating extra-articular complication of rheumatoid arthritis (RA) and is associated with substantial morbidity and mortality. However, reliable tools for the early identification of ILD in patients with RA remain limited. This study aimed to identify plasma protein biomarkers of RA-ILD and develop an interpretable machine learning model for risk prediction using data from the UK Biobank. Methods: We first evaluated the association between baseline RA and the risk of incident ILD in the UK Biobank using Cox proportional hazards models. Mendelian randomization analysis was then performed to investigate the potential causal relationship between RA and ILD. Finally, we analyzed 2,920 plasma proteins measured using the Olink platform in 781 eligible RA patients. Proteins associated with ILD risk were identified using Cox proportional hazards models and subsequently used to construct eight machine learning models. Model performance was assessed using the receiver operating characteristic curve (ROC) and decision curve analysis. The best-performing model was further interpreted using Shapley additive explanations (SHAP) to evaluate feature importance. Results: Compared with participants without RA, Patients with baseline RA had a significantly higher risk of developing ILD (Hazard ratio: 4.425, 95% CI: 3.549,5.518). The MR supported a potential causal association between RA and ILD (Odds ratio: 1.227, 95% CI: 1.121,1.343). Among the eight machine learning models, the CatBoost model showed the best performance, achieving an area under the curve (AUC) of 0.884 (95% CI: 0.773,0.996). The SHAP analysis identified LAG3, NPC2, and LAMP3 are the three most important plasma protein predictors of ILD development in patients with RA. Conclusion: Plasma proteomics combined with machine learning may provide a promising approach for identifying biomarkers and predicting ILD risk in patients with RA. LAG3, NPC2, and LAMP3 may serve as candidate biomarkers for RA-ILD and warrant further validation. Keywords: Rheumatoid arthritis, Interstitial lung disease, Mendelian randomization, Machine learning, Plasma proteins.

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

Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems

arXiv:2606.12337v1 Announce Type: cross Abstract: Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization, while physics-informed neural networks (PINNs) have emerged as a flexible alternative. Their relative performance remains difficult to assess because the two approaches are often compared under different formulations, parameterizations, optimizers, and regularization choices. We present a fair comparison of adjoint optimization and PINNs for PDE-constrained inverse problems. From a common abstract formulation, we instantiate both methods on identical domains, governing equations, observation models, and regularization terms, while matching the optimizer, unknown parameterization, and arithmetic precision wherever applicable. The benchmarks include unsteady Burgers, noisy Darcy permeability inversion, three-dimensional Allen–Cahn reaction identification, and unsteady Navier–Stokes viscosity identification. The results show that the representation of the unknown largely determines the preferred method: grid-based fields favor the discrete adjoint, whereas neural representations are native to PINNs and relevant for closure and constitutive modeling. For time-dependent problems, adjoint inversion can be dominated by trajectory storage and differentiation, while PINNs provide satisfactory reconstructions at lower cost. A PINN-warm-started adjoint strategy then recovers adjoint-level accuracy at substantially reduced cost.

13.
arXiv (CS.CV) 2026-06-11

RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval

Composed Image Retrieval (CIR) constitutes a pivotal paradigm requiring models to perform joint reasoning on reference images and modification texts. However, the prevalence of Noisy Triplet Correspondence (NTC) in large-scale datasets severely constrains model performance. Existing denoising methods either target binary mismatches or rely on scalar-based point-wise estimation, neglecting rich global structural correlations among sample populations and dynamic value variations during training, thereby yielding suboptimal results. This paper identifies two critical unresolved challenges: Global Structural Inconsistency of Semantic Correlations and Hard Sample Discrimination Uncertainty. To address these, we propose RankVR, a framework designed to construct a robust CIR model via global structure consistency and dynamic value perception. Specifically, we introduce the Global Structure Consistency Perception (GSCP) module, which utilizes the Effective Rank of the Correlation Matrix to decouple clean samples from structural noise. By measuring rank difference, GSCP identifies samples disrupting macroscopic semantic symmetry. Furthermore, we develop the Adaptive Semantic Value Calibration (ASVC) module to distinguish high-value hard clean samples. By integrating training potential and reliability, it dynamically quantifies the semantic value of each triplet, ensuring effective utilization of hard samples while suppressing noise characterized by logical conflicts. Extensive experiments on the FashionIQ and CIRR benchmark datasets demonstrate that RankVR significantly outperforms existing state-of-the-art methods, validating its superior robustness in noisy environments.

14.
medRxiv (Medicine) 2026-06-15

Sociodemographic Disparities in Tafamidis Initiation and Clinical Outcomes in ATTR-CM Across the United States

BACKGROUND Transthyretin amyloid cardiomyopathy (ATTR-CM) is a progressive, life-threatening disease. Sociodemographic factors may influence time to treatment initiation and resulting clinical outcomes, yet these relationships are poorly characterized. OBJECTIVE Assess the effects of sex and race on tafamidis initiation and subsequent outcomes and their interaction with factors such as ATTR-CM type and social deprivation measures. METHODS A retrospective cohort analysis was conducted using the US Komodo Healthcare Map (01/2016-06/2024) among patients with amyloidosis, identified by ICD-10-CM diagnosis codes. Cumulative incidence of treatment initiation and survival probabilities for cardiovascular-related hospitalization (CVH) or death were estimated by Kaplan-Meier, stratified by sex and race. Cox proportional hazards models were fitted for both endpoints to estimate hazard ratios, adjusting for demographics and clinical characteristics. RESULTS Of 11,311 patients identified, White and Black patients (n=9,223) were included in subsequent analyses. Within 12 months of diagnosis, White women had the lowest cumulative incidence of tafamidis initiation (11.4%), followed by Black women (22.0%), Black men (26.7%), and White men (31.0%). Event-free survival at 12 months was lowest in Black women (42.9%), followed by Black men (46.8%), White women (48.6%), and White men (54.4%). Median (95% CI) time to CVH or death was shortest for Black women (8.0 months [6.8-10.0]) followed by Black men (9.9 months [8.8-12.0]), White women (11.0 months [9.6-13.0]), and White men (15.0 months [14.0-16.0]). CONCLUSIONS In this large, real-world cohort of US patients with ATTR-CM, sex and race contributed to disparities in tafamidis initiation and survival, underscoring compounded disparities in both access and outcomes.

15.
arXiv (CS.CL) 2026-06-15

Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling

作者:

Neural topic models enable scalable semantic discovery, but their integration with quantum hardware remains largely unexplored. We present a proof-of-concept hybrid classical-quantum variational autoencoder (VAE) for topic modeling, embedding parameterized quantum circuits within the VAE inference network while retaining a classical topic-word decoder. To address the resource constraints of quantum hardware, we propose a modified Gaussian Softmax posterior that decouples latent space dimensionality from the number of topics to be extracted, enabling the model to operate with a low-resource 10-qubit quantum device. On the AgNews dataset, the hybrid VAE outperforms state-of-the-art neural topic models (NTMs), reaching a $C_v$ coherence score of 0.71 and an NPMI score of 0.20 while preserving high topic diversity. For comparison, we also construct a fully classical variant, which also outperforms state-of-the-art models on AgNews and exhibits clear class separation in the latent space. These results demonstrate that hybrid VAEs are computationally viable even on NISQ-era devices and represent a promising direction for quantum-enhanced topic modeling.

16.
arXiv (CS.LG) 2026-06-18

Predicting the Neutrino Mass Ordering Using Neural Networks

arXiv:2606.03745v1 Announce Type: cross Abstract: Determining the neutrino mass ordering remains a central open problem in particle physics. While next-generation long-baseline experiments are expected to resolve this question, current data provide limited sensitivity because the spectral differences between normal and inverted ordering are subtle and entangled with parameter degeneracies. We investigate a machine-learning strategy for mass-ordering determination using a feed-forward neural-network classifier trained on synthetic long-baseline datasets generated with three-flavour oscillation probabilities, matter effects, and statistical fluctuations. We evaluate the classifier against standard $\chi^2$ and $\log\mathcal{L}$ approaches using common discrimination metrics, including receiver-operating-characteristic curves, to quantify sensitivity and to illustrate how operating points can be selected to prioritise purity or efficiency. We find that the neural network achieves performance comparable to conventional fits for the scenarios studied, providing a flexible, independent cross-check of established analyses. The framework can be extended to incorporate systematic uncertainties and to explore joint inference of oscillation parameters, and it may also serve as a pedagogical tool for introducing machine-learning methods in neutrino physics.

17.
arXiv (CS.LG) 2026-06-19

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

arXiv:2605.05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

18.
medRxiv (Medicine) 2026-06-16

A Poisson Process Life Expectancy framework for optimising patient lifetime during chemotherapy

Cancer therapy balances between two competing objectives - treatment efficacy against the tumour and the risk of treatment related severe adverse events, including patient death. Most existing optimal control theory (OCT) formulations rely on optimising heuristic cost functionals that lack direct clinical interpretability. In clinical practice treatment efficacy and patient tolerability are primarily assessed through survival metrics and adverse event rates. Here we introduce the Continuous Lifetime Payoff (CLP), a novel OCT objective functional that directly links treatment decisions to patient survival. It explicitly incorporates tumour dynamics, tumour eradication, and patient mortality from tumour progression, drug-related toxicity and age. We fit age-related mortality from life tables and infer parameters from simulated survival data. The CLP provides a clinically grounded framework for optimising chemotherapy regimens.

19.
arXiv (CS.AI) 2026-06-16

Running hardware-aware neural architecture search on embedded devices under 512MB of RAM

arXiv:2606.14824v1 Announce Type: cross Abstract: This document proposes a novel approach to hardware-aware neural architecture search (HW NAS) that considers the resources available on the computing platform running it, enabling its execution on various embedded devices. The presented HW NAS produces tiny convolutional neural networks (CNNs) targeting low-end microcontroller units (MCUs), typically involved in the Internet of Things (IoT) or wearable robotics, opening new use cases. A gateway could run it to tailor CNNs' architecture on the acquired data without using external servers, ensuring privacy. The proposed technique achieves state-of-the-art results in the human-recognition tasks on the Visual Wake Word dataset, a standard TinyML benchmark, on several embedded devices.

20.
arXiv (quant-ph) 2026-06-12

Multi-entropy in heavy local quenches

arXiv:2606.12526v1 Announce Type: cross Abstract: We study the time evolution of tripartite entanglement in heavy local quenches in two-dimensional holographic conformal field theories. Our diagnostic is the genuine multi-entropy of adjacent intervals, computed from both bulk and boundary perspectives. A perturbative bulk analysis shows that the first-order small-mass perturbation around the vacuum geodesic network cancels identically at any time after the quench. In the fully back-reacted geometry, a vacuum-subtracted genuine multi-entropy arises from a mismatch between the winding selected by the trivalent geodesic network and the windings selected independently by the pairwise geodesics. In the sharp quench limit, the time dependence of genuine multi-entropy is kinematically fixed to logarithms of rational functions of time and is independent of the heavy operator dimension. The CFT calculation reproduces the same formula within the heavy-light vacuum block approximation, where the branch choice in the heavy-background uniformization map corresponds to the winding selection in the bulk. These results indicate that, in this setup, the genuine multi-entropy is controlled by global saddle selection, rather than by a local energy response or quasiparticle propagation.

21.
arXiv (CS.LG) 2026-06-16

CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization

arXiv:2602.08210v2 Announce Type: replace Abstract: Heatmap-based solvers have emerged as a promising paradigm for Combinatorial Optimization (CO). However, we argue that the dominant Supervised Learning (SL) training paradigm suffers from a fundamental objective mismatch: minimizing imitation loss (e.g., cross-entropy) does not guarantee solution cost minimization. We dissect this mismatch into two deficiencies: Decoder-Blindness (being oblivious to the non-differentiable decoding process) and Cost-Blindness (prioritizing structural imitation over solution quality). We empirically demonstrate that these intrinsic flaws impose a hard performance ceiling. To overcome this limitation, we propose CADO (Cost-Aware Diffusion models for Optimization), a streamlined Reinforcement Learning fine-tuning framework that formulates the diffusion denoising process as an MDP to directly optimize the post-decoded solution cost. We introduce Label-Centered Reward, which repurposes ground-truth labels as unbiased baselines rather than imitation targets, and Hybrid Fine-Tuning for parameter-efficient adaptation. CADO achieves state-of-the-art performance across diverse benchmarks, validating that objective alignment is essential for unlocking the full potential of heatmap-based solvers.

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

Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures

Scientific figures compress complex pipelines into a single canvas, yet understanding them requires paper-grounded, step-by-step narration aligned with visual highlights a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. We propose MINARD (Multimodal Interpretation of Narrated Architecture via Region Decomposition), a pipeline that generates paper-grounded narrations and sequentially grounds them to figure regions. We also release FigTalk, a benchmark with new sequential and component-level grounding metrics derived. On FigTalk, MINARD generates humanlike, paper-faithful narrations and outperforms narration-conditioned figure spatial grounding compared to existing approaches in both automatic and human evaluation

23.
arXiv (CS.LG) 2026-06-17

Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining

arXiv:2606.17445v1 Announce Type: new Abstract: Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone. Although machine learning-based high-throughput screening has accelerated catalyst discovery, its efficiency inevitably declines as the search space grows, motivating the development of generative models that can directly construct catalysts with target properties. Here, we present a conditional catalyst generative model based on the Generative Pretrained Transformer architecture with a numerical embedding layer that enables the generation of catalyst structures conditioned on both categorical and continuous properties within a single autoregressive framework. The model was pretrained on 133 million catalyst structures and subsequently fine-tuned on approximately 460,000 optimized structures with associated categorical properties and binding energies for conditional generation. The resulting model achieved 98% structural validity, 95% optimization validity, and high categorical condition fidelity, with a 93 % joint match rate for adsorbate type and composition. For binding energy conditioning, the match rate of approximately 20% represents a four-fold improvement over the baseline training distribution, and the generated distributions shift systematically toward the target values, enabling a 1.5 to 4-fold improvement in screening efficiency for reaction-targeted catalyst discovery without additional fine-tuning. These results show that large-scale autoregressive pre-training, combined with explicit property conditioning, provides a practical route toward controllable catalyst generation and accelerated catalysts discovery.

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

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

25.
arXiv (CS.CV) 2026-06-17

DVD: Discrete Voxel Diffusion for 3D Generation and Editing

We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced continuous diffusion in image-like generation, we show that it can be an effective first-stage prior for sparse voxel scaffolds. By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete thresholding and provides a simple framework for voxel generation, uncertainty estimation, and editing. Beyond quality gains, DVD provides more interpretable generation dynamics through explicit categorical modeling. Furthermore, we leverage the predictive entropy as a robust uncertainty metric to identify ambiguous voxel regions and complicated samples, facilitating tasks such as data filtering and quality assessment. Finally, we propose a lightweight fine-tuning strategy using block-structured perturbation patterns. This approach empowers the model to inpaint and edit voxels within a single sampling round, requiring negligible auxiliary computation and no additional model evaluations. Code is available at https://github.com/TeCai/DVD.