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.
arXiv (quant-ph) 2026-06-19

Frequency-Multiplexed Millimeter-Wave Fault-Tolerant Superconducting Qubits Enabled by an On-Chip Nonreciprocal Control Bus

arXiv:2512.17588v2 Announce Type: replace Abstract: Scaling superconducting quantum processors is fundamentally limited by the escalating complexity of cryogenic wiring and the detrimental effects of microwave crosstalk and Purcell decay. This paper proposes a novel architecture based on frequency-multiplexed millimeter-wave superconducting qubits, integrating an on-chip cryogenic nonreciprocal space-time-periodic Josephson frequency multiplier as a universal control bus. The bus replaces multiple high-frequency XY drive lines with a single low-frequency input tone, which is parametrically converted into a comb of high-order harmonics, each resonantly addressing a distinct qubit. The nonreciprocal nature of the bus provides intrinsic isolation that suppresses Purcell decay and reduces coherent crosstalk by more than $98\%$ compared to a conventional reciprocal shared drive line. Full error-budget analysis demonstrates that the architecture can maintain gate errors below the fault-tolerance threshold for arrays exceeding 25 qubits, converting a crosstalk-dominated error budget into one primarily limited by intrinsic material coherence. Theoretical modeling based on a non-Markovian master equation further indicates that the engineered environment enables information backflow, offering a pathway to enhanced coherence. This integrated, frequency-multiplexed, and nonreciprocal control bus offers a compelling route toward dramatic I/O simplification, improved noise resilience, and scalable high-coherence superconducting quantum processors.

02.
arXiv (CS.CL) 2026-06-17

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically infer which configuration will best improve the current policy. To automate this process, we propose the LLM-as-Environment-Engineer framework in which the current policy model analyzes failure trajectories together with contextual information and proposes modifications to the next-stage training environment configuration. We also introduce MAPF-FrozenLake, a controllable testbed whose generator exposes multi-dimensional environment configurations, making it suitable for studying and benchmarking environment redesign. On this testbed, we condition the environment engineer on structured summaries of policy behavior, failure cases, and environment statistics, from which it produces the configuration for the next training stage. With Qwen3-4B as the backbone, our framework achieves the strongest aggregate performance on our benchmarks, outperforming larger proprietary LLMs (e.g., GPT, Gemini) and fixed-environment training baselines. We further analyze which forms of context are most effective, finding that successful environment updates rely on failure evidence and preserve configurations that already work. Interestingly, the current RL checkpoint serves as a better environment engineer than the original base model, suggesting that policy learning improves the model's ability to diagnose its remaining weaknesses.

03.
arXiv (math.PR) 2026-06-19

Finite-Sample Bounds for Expected Signature Estimation under Weak Dependence

arXiv:2605.20541v2 Announce Type: replace-cross Abstract: The expected signature uniquely determines the law of a random rough path under a moment-growth condition, yet finite-sample bounds for estimating its truncations from a single long dependent trajectory remain unavailable. We study a strictly stationary stochastic process equipped with a geometric rough-path lift, observed in non-overlapping blocks of equally-spaced samples, and prove a non-asymptotic mean-squared error (MSE) bound for the block-averaging estimator of its truncated expected signature. Under moment and stationarity assumptions together with a direct covariance-decay condition on block signatures – strictly weaker than $\alpha$-mixing and applicable to long-range-dependent processes – the error separates into a discretization term and a fluctuation term, with rates determined respectively by path regularity and dependence strength. A levelwise rough-factorial variance analysis keeps finite-truncation constants explicit and yields an optimal allocation rule under a fixed observation budget. We verify the assumptions for independent-coordinate fractional Ornstein–Uhlenbeck processes in three regimes: short-range (Hurst $1/41/2$. Monte Carlo experiments show empirical slopes steeper than the guaranteed upper-bound rates.

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

Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting

arXiv:2606.19560v1 Announce Type: new Abstract: Seasonal influenza infects millions of people and causes substantial morbidity and mortality in the United States each year, making accurate short-term forecasting a core public-health need. Reliable forecasts of epidemic time series can inform vaccination timing, hospital staffing, and resource allocation, yet the comparative behavior of modern forecasting architectures on infectious-disease surveillance data remains insufficiently characterized. We address this gap through a systematic evaluation of regional influenza forecasting using influenza-like illness surveillance and influenza-associated hospitalization time series under both temporal and spatial generalization settings for 1-4-week-ahead prediction. We compare classical neural network architectures, numerical transformer-based models, pretrained time series foundation models, and LLM-based forecasting approaches. Across tasks, we demonstrate that a mixture-of-experts model that fuses multiple pretrained forecasters achieves the strongest overall performance, indicating that heterogeneous pretrained representations provide complementary predictive information. Our results further show that numerical transformer-based models produce reliable forecasts, while pretraining provides the largest gains at longer horizons, particularly when the pretraining domain is mechanistically aligned with influenza dynamics. In contrast, LLM-based time series methods underperform relative to numerical forecasters in this setting. Finally, we examine hospitalization information as both an auxiliary covariate and a pretraining source. Hospitalization signals provide complementary improvements in selected settings and clarify when additional surveillance streams enhance the robustness of multi-horizon forecasting. These findings provide actionable guidance on model selection, pretraining strategy, and auxiliary-signal use for influenza preparedness.

05.
medRxiv (Medicine) 2026-06-17

Preserved Medial Temporal Lobe Flexibility Predicts Memory Generalization Only in the Context of Good Sleep Quality among Older African Americans

Objectives: Poor sleep quality is a risk factor for Alzheimer's disease (AD). Older African Americans experience disproportionately high rates of sleep disturbance and AD. Medial temporal lobe (MTL) flexibility reflects dynamic neural reorganization and may be a marker of generalization performance. This study examined whether sleep quality moderates the association between MTL flexibility and memory generalization. Methods: Fifty older African Americans (MeanAge=69.7{+/-}6.21 years; 80% women) underwent rs-fMRI to quantify MTL flexibility, Rutgers Acquired Equivalence Task for memory generalization, and Pittsburgh Sleep Quality Index for sleep quality. Results: Greater MTL flexibility was associated with better generalization (r=0.367, p=.017). Good sleepers showed higher MTL flexibility (F(1,44)=8.11, p2=.156, p=.007) and superior generalization (F(1,46)= 12.33, p2=.211, p=.001). Sleep quality significantly moderated the MTL flexibility and generalization relationship ({beta}=-1.519, p=.012). Conclusions: Preserved MTL flexibility may confer generalization only in good sleepers, suggesting that sleep disturbance may disrupt the MTL neural resilience among older African Americans.

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

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

arXiv:2602.11590v3 Announce Type: replace Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once tokens are unmasked, they remain fixed, leading to error accumulation and ultimately degrading sample quality. We address this by proposing a framework that trains a model to perform both unmasking and correction. By reusing outputs from the MDM denoising network as inputs for corrector training, we train a model to recover from potential mistakes. During generation we apply additional corrective refinement steps between unmasking ones in order to change decoded tokens and improve outputs. We name our training and sampling method Progressive Self-Correction (ProSeCo) for its unique ability to iteratively refine an entire sequence, including already generated tokens. We conduct extensive experimental validation across multiple conditional and unconditional tasks, demonstrating that \method~yields better quality-efficiency trade-offs (up to ~4x faster sampling) and enables inference-time compute scaling to further increase sample quality beyond standard MDMs (up to ~1.2x improvement on benchmarks).

07.
arXiv (CS.CL) 2026-06-15

TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation

Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text-Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation.

09.
arXiv (math.PR) 2026-06-15

Boltzmann-Like Occupation of Nonequilibrium Steady States on Dense Networks

arXiv:2606.14542v1 Announce Type: cross Abstract: A central problem in statistical physics is to extend the Boltzmann distribution to nonequilibrium steady states (NESS). We prove that NESS on large dense networks have Boltzmann-like occupation despite extensive entropy production. We further show that the active-matter heuristic of "low rattling" is asymptotically exact. Intuitively, these NESS spend a greater fraction of their time in states they leave more slowly. This explanation extends to the broader class of "equiaccessible" steady states, which play a role in our analysis akin to that of equilibrium in linear response.

10.
arXiv (CS.LG) 2026-06-18

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

arXiv:2606.18537v1 Announce Type: new Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act in an environment. However, observations drawn from a heterogeneous population introduce conflicting behavioral signals, making it difficult to determine which behaviors are worth imitating. We address this challenge with General Reward Inference and Disentanglement (GRID), a social learning method that extracts universally useful behaviors from a heterogeneous population of demonstrators pursuing different goals. GRID decomposes per-agent reward functions into a general reward, capturing behaviors shared across all agents, and specific rewards, capturing individual preferences and objectives. Training exclusively on the general reward provides a new paradigm of generalist pretraining. It yields a generalist agent that internalizes universal environmental competencies, such as safety and basic task proficiency, without the mode-averaging bias that afflicts standard learning from demonstration techniques. This generalist serves as a superior prior for fine-tuning to downstream tasks, including preferences unseen during training. Experiments across a synthetic basis function decomposition, multi-agent Craftax, and a continuous autonomous driving simulator (Highway-Env) confirm that GRID successfully disentangles reward structure in a semantically meaningful way, outperforms standard learning from demonstration baselines, and enables more efficient and stable specialization.

11.
arXiv (CS.LG) 2026-06-17

Gradual Fine-Tuning for Flow Matching Models

arXiv:2601.22495v2 Announce Type: replace Abstract: Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fine-Tuning (GFT), a simple yet principled annealing-based framework for fine-tuning flow generative models when only samples from the target distribution are available. For stochastic flows, GFT defines a temperature-controlled sequence of intermediate objectives that smoothly interpolate between the pretrained and target drifts, provably approaching the true target as the temperature approaches zero. We analytically demonstrate that sample generation after GFT can be made substantially more efficient with the use of arbitrary (e.g., optimal transport) couplings, as well as by utilizing few-step inference methods. Empirically, GFT significantly improves convergence stability, while maintaining or improving generation quality, training speed, and generation diversity compared to other fine-tuning methods. Our results position GFT as a simple yet theoretically grounded and practically effective alternative for scalable adaptation of flow matching models under distribution shift.

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

Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention

arXiv:2603.14483v2 Announce Type: replace Abstract: Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of candidate functions chosen via available domain knowledge. In contrast, deep learning can demonstrably model systems of broad complexity with high fidelity, but black-box function approximation typically fails to yield explicit descriptive or disentangled representations revealing the structure of a system. We develop a novel identifiability theorem, leveraging causal representation learning, to uncover disentangled representations of system parameters without structural assumptions. We derive a graphical criterion specifying when system parameters can be uniquely disentangled from raw trajectory data, up to permutation and diffeomorphism. Crucially, our analysis demonstrates that global causal structures provide a lower bound on the disentanglement guarantees achievable when considering local state-dependent causal structures. We instantiate system parameter identification as a variational inference problem, leveraging a sparsity-regularised transformer to uncover state-dependent causal structures. We empirically validate our approach across four synthetic domains, demonstrating its ability to recover highly disentangled representations that baselines fail to recover. Corroborating our theoretical analysis, our results confirm that enforcing local causal structure is often necessary for full identifiability.

13.
arXiv (CS.CL) 2026-06-12

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models' abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

14.
arXiv (math.PR) 2026-06-11

Stochastic epidemic model with varying infectivity and waning immunity: the law of large numbers with unbounded infectivity

arXiv:2606.11845v1 Announce Type: new Abstract: We revisit the large population limit of our epidemic model with infection age dependent infectivity and progressive immunity waning, under the assumption that the supremum in $t$ of the random infectivity function has a finite expectation, while the previous proofs assumed that this supremum admits a deterministic upper bound.

15.
arXiv (CS.LG) 2026-06-16

ANCHOR: Error-Controlled Adaptive Numerical Correction for Neural Operator Time Marching

arXiv:2512.19643v2 Announce Type: replace Abstract: Numerical simulation of time-dependent partial differential equations (PDEs) is central to scientific and engineering applications, but high-fidelity solvers are often prohibitively expensive for long-horizon or time-critical settings. Neural operator (NO) surrogates offer fast inference across parametric and functional inputs; however, most autoregressive NO frameworks remain vulnerable to compounding errors, and ensemble-averaged metrics provide limited guarantees for individual inference trajectories. In practice, error accumulation can become unacceptable beyond the training horizon, and existing methods lack mechanisms for online monitoring or correction. To address this gap, we propose ANCHOR (Adaptive Numerical Correction for High-fidelity Operator Rollouts), an online, instance-aware hybrid inference framework for stable long-horizon prediction of nonlinear, time-dependent PDEs. ANCHOR treats a pretrained NO as the primary inference engine and adaptively couples it with a classical numerical solver using a physics-informed, residual-based error estimator. Inspired by adaptive time-stepping in numerical analysis, ANCHOR monitors an exponential moving average (EMA) of the normalized PDE residual to detect accumulating error and trigger corrective solver interventions without requiring access to ground-truth solutions. We show that the EMA-based estimator correlates strongly with the true relative L2 error, enabling data-free, instance-aware error control during inference. Evaluations on six canonical PDEs: 1D and 2D Burgers', 2D Allen-Cahn, 2D Cahn-Hilliard, 2D Navier-Stokes, and 3D heat conduction, demonstrate that ANCHOR reliably bounds long-horizon error growth, stabilizes extrapolative rollouts, and significantly improves robustness over standalone neural operators, while remaining substantially more efficient than high-fidelity numerical solvers.

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

The Hidden Cost of Approximation in Online Mirror Descent

arXiv:2511.22283v2 Announce Type: replace Abstract: Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms in optimization, machine learning and sequential decision-making. The OMD iterates are defined as solutions to optimization subproblems which, oftentimes, can be solved only approximately, leading to an inexact version of the algorithm. Nonetheless, existing OMD analyses typically assume an idealized error free setting, thereby limiting our understanding of performance guarantees that should be expected in practice. In this work we initiate a systematic study into inexact OMD, and uncover an intricate relation between regularizer smoothness and robustness to approximation errors. When the regularizer is uniformly smooth, we establish a tight bound on the excess regret due to errors. Then, for barrier regularizers over the simplex and its subsets, we identify a sharp separation: negative entropy requires exponentially small errors to avoid linear regret, whereas log-barrier and Tsallis regularizers remain robust even when the errors are only polynomial. Finally, we show that when the losses are stochastic and the domain is the simplex, negative entropy regains robustness-but this property does not extend to all subsets, where exponentially small errors are again necessary to avoid suboptimal regret.

17.
arXiv (CS.LG) 2026-06-16

Discovering Subgroups with Exceptional Survival Characteristics

arXiv:2602.22179v2 Announce Type: replace Abstract: In many applications, it is important to identify subpopulations that survive longer or shorter than the rest of the population. In medicine, for example, it allows determining which patients benefit from treatment, and in predictive maintenance, which components are more likely to fail. Existing methods for discovering subgroups with exceptional survival characteristics rely on restrictive assumptions about the survival model (e.g. proportional hazards), require pre-discretized features, and, as they compare average statistics, tend to overlook individual heterogeneity. In this paper, we propose Sysurv, a non-parametric, fully differentiable method that discovers human-readable rules selecting subgroups with exceptional survival characteristics. Empirical evaluation on a wide range of datasets and settings, including a case study on cancer data, shows that Sysurv reveals insightful and actionable survival subgroups, outperforming the state of the art.

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

Adaptive inference and function vectors in deep transformers

arXiv:2606.16694v1 Announce Type: cross Abstract: Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious. We introduce a theory of a deep transformer as a mean-field interacting system that implements distributed inference, subject to constraints on communication, locality and depth. We show that such a system can exploit internal state representations ('function vectors') to infer a latent context variable at increasingly finer scales over its layers. In an in-context regression task, the theory predicts a non-trivial relationship between non-Gaussian, hierarchical structure in the latent context variable, and transformer depth. Predictions are tested using constrained linear attention transformers and demonstrate adaptive inference in deep architectures. Feedforward blocks and depth enable transformers to implement a much richer class of in-context learning algorithms than previously described.

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

Task-Error Residual Learning for Real-Robot Five-Ball Juggling

arXiv:2606.16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional task-error supervision and a task error model that drives sample selection, we achieve stable three-, four-, and five-ball juggling on anthropomorphic Barrett WAM arms. Despite planning and controlling through a simple, idealized stack, the system converges from the second attempt. The first attempt drops, after which task error decreases monotonically without further failures. In comparison, five-ball juggling typically takes humans years of practice. We compare residual learners across two ternary axes, the directional information in the learning feedback and the commitment of the analytic prior, spanning Newton-style Jacobian updates, Composite Bayesian Optimization, and stochastic search methods. Both axes prove necessary: neither directional feedback nor an informative prior suffices alone, and the simplest method that combines them, a fixed-Jacobian Newton update, is the most reliable. The learned residual tolerates substantial prior misalignment and degraded joint tracking, affecting mainly convergence speed. The bottleneck for residual learning on real robots is therefore the information content of the supervision signal and how the learner uses it, not the accuracy of the surrounding stack. Video documentation of all experiments is available at https://kai-ploeger.com/residual-juggling.

20.
arXiv (CS.CV) 2026-06-16

CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding

Accurate detection and localization of traumatic injuries in abdominal CT remain challenging because voxel-level annotations are limited and expensive to obtain. We present a label-efficient framework for 3D abdominal trauma detection that combines self-supervised pretraining with semi-supervised transformer-based detection. First, we use Masked Image Modeling (MIM) on 1098 CT volumes to pretrain a 3D U-Net encoder for anatomical representation learning. Next, we adapt V-DETR to dense volumetric CT through a feature adapter that converts the encoder feature grid into a compact token sequence for transformer decoding. The pretrained encoder is then integrated with V-DETR and 3D Vertex Relative Position Encoding (3D V-RPE) to improve the localization of irregularly shaped injuries. Finally, semi-supervised teacher-student consistency regularization leverages 2,000 additional unlabeled volumes during detector training. To the best of our knowledge, this is the first application of a 3D DETR-style detector to the RSNA abdominal trauma detection task. On this benchmark, the proposed method achieves 31.33% test mAP@0.50 using only 78 labeled training volumes, corresponding to a 1.53x improvement over supervised-only training. These results show that combining medical-domain pretraining with semi-supervised learning is an effective strategy for label-scarce 3D medical detection.

21.
arXiv (CS.AI) 2026-06-12

Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories

arXiv:2606.13298v1 Announce Type: cross Abstract: AI coding tools are now used by a majority of developers, and agentic use of these tools has popularized the practice colloquially called "vibe coding". Yet causal evidence on their effect on software architecture is scarce. Prior causal work has measured code-level outcomes (complexity, static analysis warnings); whether such degradation propagates to architecture-level outcomes remains unknown. We mine 151 open-source Java repositories, 74 with detectable agentic AI adoption (identified via configuration files and Co-Authored-By commit trailers) and 77 propensity-matched controls, across a 13-month per-repository window yielding 1,811 monthly Arcan snapshots. We estimate the causal effect of adoption on architectural smell density (ASD) with a staggered difference-in-differences design and the Borusyak imputation estimator, applying a causal design recently used for code-level metrics to the architecture level. Total smell counts are essentially unchanged (+1.1%, p = 0.82) while lines of code grow +12.8% (p = 0.003); the resulting 6.7% ASD decline (p = 0.004) is therefore a denominator effect rather than an architectural improvement. Per-type estimates and robustness checks (wild cluster bootstrap, Lee bounds, stale-observation sensitivity) corroborate the pattern; pre-trends are flat (Wald p = 0.90), consistent with parallel trends. Density-normalized outcomes can mislead when treatment affects system size: raw counts and explicit decomposition are required for causal mining studies of AI tool adoption. The complete replication package, including the curated 151-repository monthly panel, is publicly available.

22.
arXiv (CS.CL) 2026-06-16

REFLEX: Reflective Evolution from LLM Experience

作者:

Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies. However, existing frameworks rely on a monolithic model call to simultaneously interpret visual behavioral evidence and synthesize corrective code. This diagnosis-repair entanglement creates an opaque feedback loop, obscuring the rationale behind mutations and preventing the retention of algorithmic insights across independent runs. To achieve auditable and efficient policy search, we argue that visual diagnosis must be structurally decoupled from code generation. We present REFLEX, a train-free evolutionary framework that operationalizes this decoupling. In REFLEX, a vision-enabled Critic first distills task-specific behavioral evidence into structured, auditable diagnoses. Subsequently, a text-optimized Actor synthesizes child policies using these diagnoses alongside a persistent, self-evolving Skill Memory of reusable code snippets. This architecture not only provides transparent mutation traces but also enables cross-run programmatic knowledge transfer. Extensive evaluations across control benchmarks (Lunar Lander, Acrobot, Pendulum) and a 36-dimensional antenna array synthesis task demonstrate exceptional sample efficiency. Notably, REFLEX solves Acrobot and Pendulum in under 10 LLM calls and reaches a best Normalized Weighted Score of 1.092 on Lunar Lander, achieving highly competitive final performance while significantly accelerating the early-stage discovery of transparent policies.

23.
arXiv (CS.CL) 2026-06-16

Tying the Loop – Tied Expert Layers in Mixture-of-Experts Language Models

作者:

Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory. To address this, we introduce Expert Tying, an architectural modification that shares expert parameters across consecutive transformer layers while preserving independent, layer-wise routing and attention. We evaluate this approach across common, state-of-the-art architectures, including OLMoE, Qwen3, and DeepSeek-style MoEs. Our pretraining experiments demonstrate that tying experts can reduce memory footprint by almost 2x at virtually no degradation in perplexity or downstream quality. By exploiting the parameter redundancy inherent in MoE pathways, our method provides a highly favorable compute-to-memory trade-off, advancing efficient training and scaling of next-generation LLMs.

24.
medRxiv (Medicine) 2026-06-16

Infections and suicide and self-harm: a population-based matched cohort study

Background Infections have been associated with adverse mental health outcomes, including suicide, but evidence beyond severe or central nervous system infections is limited. We investigated associations between a range of acute infections and subsequent suicide/self-harm outcomes. Methods We conducted six infection-specific matched cohort studies using English primary care records from the Clinical Practice Research Datalink Aurum (2007-2024), linked to hospital admissions and mortality data. Adults ([≥]18 years) with a primary care record of infection (gastroenteritis, lower respiratory tract [LRTI], skin/soft-tissue [SSTI], urinary tract [UTI], sepsis, meningitis/encephalitis [positive control]) were matched (age, sex, practice, calendar period) to up to five comparators without infection. We estimated hazard ratios (HRs) for suicide/self-harm outcomes using Cox regression, stratified by matched set and implicitly adjusting for matching factors, with additional adjustment for deprivation, lifestyle factors, and comorbidities. We examined whether associations varied over time, by infection severity, antimicrobial treatment, sex, and prior mental health conditions. Findings Cohorts ranged from 18,192 individuals with meningitis/encephalitis (matched to 90,915 without) to 398,099 with SSTI (matched to 1,743,747). After adjustment, individuals with infection had a higher hazard of suicide/self-harm outcomes than comparators across all cohorts: sepsis (HR 1.79, 95% CI 1.65-1.93), gastroenteritis (1.62, 1.55-1.70), meningitis/encephalitis (1.56, 1.32-1.84), UTI (1.41, 1.33-1.50), SSTI (1.37, 1.31-1.43), and LRTI (1.37, 1.31-1.44). Risk was highest in the year post-infection, attenuating over time, and was higher among severe infections and those without prior mental health conditions. Interpretation Common acute infections recorded in primary care are associated with increased risk of suicide and self-harm, particularly following severe infections and in the year post-infection. Findings support suicide risk monitoring following acute infection, particularly among individuals without prior mental health conditions, and highlight infection prevention as a potentially modifiable strategy in vulnerable populations. Funding Wellcome and La Caixa. Copyright This work is licensed under a Creative Commons Attribution (CC BY) licence.

25.
arXiv (CS.AI) 2026-06-19

Mitigating Legibility Tax with Decoupled Prover-Verifier Games

arXiv:2602.23248v2 Announce Type: replace Abstract: As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems. Prover-verifier games can be used to improve checkability of model outputs, but display a degradation in accuracy compared to a baseline trained only to maximize correctness – a phenonemon named legibility tax. We propose a solution by decoupling the correctness from the checkability condition and instead training a "translator" model that turns a fixed solver model's solution into a checkable form. This allows us to first train the solver to maximize correctness, and then train the translator to translate the solver into a checkable form while retaining the solver's answer. To accommodate this new objective of translation, we formulate a decoupled prover-verifier game (DPVG) where the equilibria correspond to faithful and checkable translators.