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 (math.PR) 2026-06-16

A tree-free approach to 3D Yang-Mills Langevin dynamic. Analytic estimates and the existence of a model for a regularity structure

arXiv:2605.14616v2 Announce Type: replace Abstract: Using the multi-index approach to regularity structures due to F. Otto et al., we construct a regularity structure and a model for it associated to the stochastic Langevin equation for the 3D Euclidean Yang-Mills functional. For the model we also obtain global stochastic and global pointwise weighted Besov type estimates which hold almost surely. The model is defined as a limit of a sequence of smooth models introduced with the help of a mollified noise. When the mollification is removed the sequence converges in a certain topology defined with the help of the stochastic estimates. To obtain these results we develop the multi-index approach for systems of equations with vector-valued white noises. This project is motivated by the problem for constructing 3D Euclidean Yang-Mills measure and by the earlier results of the author on the related problem of canonical quantization of the Yang-Mills field on the Minkowski space.

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

Gender Differences in AI Literacy Workshop Outcomes and Deepfake Engagement

arXiv:2606.14718v1 Announce Type: cross Abstract: As Artificial Intelligence (AI) literacy initiatives expand in K-12 settings, understanding how gender shapes student baseline perceptions, tool-use, and responsiveness to interventions is essential for equitable curriculum design. This study examines gender differences in AI literacy, safety awareness, and STEM career aspirations among Australian secondary students (Years 7, 8, and 10; N(pre) = 199, n(post) = 136) from two co-educational government schools who participated in a one-day AI literacy workshop. Using statistical regression methods controlling for year level and school, we found that pre-workshop, male students reported significantly higher STEM career interest across all three domains (AI, computer science, and engineering), while female students were significantly more likely to use AI for schoolwork and to seek advice from AI tools. Gender-differentiated patterns also emerged in deepfake behaviours: males were significantly more likely to have created or shared deepfake content. Both genders improved in AI knowledge post-intervention, yet females showed a richer profile of gains: wider conceptual understanding, greater confidence, and meaningful increases in AI and CS career interest that partially narrowed the gender STEM gap. These findings highlight the need for gender-responsive AI curricula, particularly deepfake safety education for male students, and demonstrate that even single-day workshops can narrow gender gaps in STEM aspirations and AI confidence.

03.
medRxiv (Medicine) 2026-06-15

Fanconi Anemia as a Window into Premalignant Field Cancerization of the Oral Mucosa

Head and neck squamous cell carcinoma (HNSCC) evolves through stepwise clonal expansion within genetically altered mucosa fields, yet actionable biomarkers remain undefined. Leveraging Fanconi anemia (FA), a cancer predisposition syndrome with extreme HNSCC risk due to defective DNA interstrand crosslink repair, we profiled premalignant changes in the oral cavity using noninvasive brush biopsies. Consistent with our prior demonstration of genomic instability in FA-associated SCCs, we detected pathogenic TP53 variants in 26% and copy number alterations in 60.5% in clinically normal-appearing oral mucosa of individuals with FA. These subclinical clonal expansions define candidate biomarkers of early clonal evolution amenable to serial sampling for risk stratification and prevention studies. Since FA-associated SCCs share genomic features with sporadic HNSCC, these findings may extend to the broader population. We also identify somatic reversion of a pathogenic FANCB variant, providing evidence of genomic self-correction and suggesting a potential avenue for gene-based cancer prevention in FA.

04.
arXiv (CS.LG) 2026-06-11

Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems

arXiv:2606.11474v1 Announce Type: new Abstract: In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems. RL controllers can quickly control high-dimensional systems within the training distribution, but their performance can degrade when time-varying dynamics produce unseen observations. We consider a combined ES–DRL controller, where RL provides fast in-distribution actions and bounded extremum seeking (ES) provides robust model-independent control under OOD operation. The key challenge is deciding when to switch. We train a variational autoencoder (VAE) on in-distribution beam-profile observations and use Mahalanobis distance in the VAE latent space to detect OOD beam profiles at test time. This OOD decision sets a binary switch that selects either the RL controller or the ES controller. We evaluate the approach in safety-critical particle accelerator control. In this setting, spatial magnet motion creates OOD beam profiles that were not seen during RL training. Visualization of the VAE latent space shows that the proposed method identifies this OOD scenario and provides an interpretable signal for switching between RL and ES in the combined controller.

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

One-Step Generalization Ratio Guided Optimization for Domain Generalization

arXiv:2606.16301v1 Announce Type: new Abstract: Domain Generalization (DG) aims to train models that generalize to unseen target domains but often overfit to domain-specific features, known as undesired correlations. Gradient-based DG methods typically guide gradients in a dominant direction but often inadvertently reinforce spurious correlations. Recent work has employed dropout to regularize overconfident parameters, but has not explicitly adjusted gradient alignment or ensured balanced parameter updates. We propose GENIE (Generalization-ENhancing Iterative Equalizer), a novel optimizer that leverages the One-Step Generalization Ratio (OSGR) to quantify each parameter's contribution to loss reduction and assess gradient alignment. By dynamically equalizing OSGR via a preconditioning factor, GENIE prevents a small subset of parameters from dominating optimization, thereby promoting domain-invariant feature learning. Theoretically, GENIE balances convergence contribution and gradient alignment among parameters, achieving higher OSGR while retaining SGD's convergence rate. Empirically, it outperforms existing optimizers and enhances performance when integrated with various DG and single-DG methods.

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

CacheMuon: Using Temporal Preconditioning To Approximate Polar Factor

arXiv:2606.16371v1 Announce Type: new Abstract: Muon is an optimizer that computes updates using the polar factor of the momentum matrix and has shown strong empirical performance across a range of training settings. A key component of Muon is the Newton-Schulz iteration used to compute this polar factor. Although this avoids the cost of an exact singular value decomposition, it remains expensive in practice because it is applied at every optimization step. At the same time, the momentum matrix changes smoothly over training, suggesting strong temporal correlation in the corresponding polar factors. In this paper, we exploit this structure and propose CacheMuon, a temporal preconditioning method that reuses information from previous optimization steps to approximate the polar factor at the current step. This reduces redundant orthogonalization computation across iterations. We analyze CacheMuon as an inexact Muon update, with error controlled by fresh-solver error and cache staleness. Empirically, CacheMuon provides a controllable quality-efficiency frontier: conservative thresholds closely match fresh Muon on language-model and vision training while reducing orthogonalization FLOPs, whereas more aggressive thresholds yield larger arithmetic savings at the cost of modest validation-quality degradation.

07.
arXiv (CS.AI) 2026-06-17

C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

arXiv:2606.18003v1 Announce Type: cross Abstract: Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Scaling this intelligence, however, raises fundamental challenges: sensed data is often privacy-sensitive, preventing centralized collection; nodes are mobile, traversing regions where nearby nodes perceive similar phenomena while distant ones observe radically different conditions, creating natural spatial clusters; and these distributions evolve over time due to mobility, introducing temporal drift that makes local models progressively stale. These dynamics arise across domains - vehicular sensing, drone-based monitoring, smartphone crowdsensing - yet the interplay of privacy, spatial heterogeneity, and temporal drift severely undermines conventional learning strategies. Therefore, we propose C2FL, a fully distributed Federated Learning (FL) approach where nodes self-organize into learning groups through spatial clustering, reflecting the geographic structure of the environment. To counteract temporal drift, each node combines experience replay with a dwell-time-aware adaptive averaging step, progressively incorporating the regional consensus as it remains longer within the same area, while preserving previously acquired knowledge under evolving distributions. We evaluate our approach on synthetic experiments that systematically reproduce spatial and temporal shifts, showing that standard federated strategies degrade significantly under these conditions and that our method restores robust collective adaptation.

08.
arXiv (CS.AI) 2026-06-11

Preregistration for Experiments with AI Agents

arXiv:2606.11217v1 Announce Type: cross Abstract: The proliferation of large language models (LLMs) and autonomous AI agents has given rise to a rapidly growing methodological paradigm: "in silico" behavioral experiments. Originally conceived as a way to use AI agents as proxies for human participants in studies of cognition, decision-making, and social dynamics, this approach has taken on new significance – as AI agents increasingly negotiate, transact, and make consequential decisions on behalf of people and organizations, understanding their behavior has become a research priority in its own right. While these experiments with AI agents offer unprecedented advantages in terms of scalability, cost efficiency, and experimental control, they also inherit, and in some cases amplify, methodological vulnerabilities that have long plagued human subjects research. To address these issues, this paper argues that preregistration practices – central to improving the credibility of human subjects experiments – should now be extended to experiments with AI agents. We systematically catalog the researcher degrees of freedom that experiments with AI agents introduce – model selection, prompt wording, settings, and outcome-contingent redesign, for example – and show how the low cost of iteration and lack of reporting norms make these choices both easy to exploit and difficult to detect. We propose a preregistration template tailored to experiments with AI agents and call on conferences, journals, and funding agencies to make preregistration standard practice for this emerging research paradigm.

09.
arXiv (CS.CL) 2026-06-12

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants

Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.

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

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

11.
arXiv (CS.AI) 2026-06-16

FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (June 13th version)

arXiv:2606.06510v2 Announce Type: replace-cross Abstract: Conventional HPC holds that native hardware FP64 is the irreducible foundation of scientific computing. On AI-optimized GPUs of the NVIDIA B300 generation and beyond, native FP64 throughput has collapsed to ~1.3 TFLOPS even as FP8 tensor throughput has grown to multiple PFLOPS. We argue something stronger than that this is survivable: the FP8 tensor-core matrix-multiply is the sole computational primitive on which double-precision scientific computing needs to be built. Every canonical kernel – dense and sparse linear algebra, spectral transforms, stencils – and every application composing them reduces, via the Chinese Remainder Theorem-based Ozaki Scheme II, to sequences of FP8 matrix operations; the only non-FP8 arithmetic is a bounded, fixed-width integer accumulation at reconstruction. Native FP64 is thereby demoted from a hardware requirement to a derived accuracy guarantee obtained by composition over the FP8 primitive. We organize the claim as a five-layer hierarchy – the FP8 op, Ozaki II, the basic kernels or Berkeley "dwarfs", composite solvers, and full applications – and, because the dwarf taxonomy already spans scientific computing, establish it by exhibiting the reduction for every dwarf rather than a sample. The claim is falsifiable, and we build the instrument that tests it: a Tensor-Memory Equilibrium (TME) model extending the Roofline with emulation parameters (alpha, beta, gamma). We identify register-level fusion as the mechanism that keeps emulation memory-bound, project recovered FP64 performance across B300 and Rubin against an H100 baseline, and close the kernel coverage with a companion FFT analysis and compensated reductions. The model could have returned a negative verdict; instead it passes across the dwarfs and their compositions. This is the analytical half of a two-part program, with a follow-on implementation to validate the thesis on real silicon.

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

CRAFTIIF: Cross-Resolution Analytic Four-Type Interpretable Isolation Forest for Multivariate Time Series Anomaly Detection

arXiv:2606.13486v1 Announce Type: cross Abstract: Anomaly detection in multivariate time series is challenged by four structurally distinct anomaly types – point (isolated spikes), distributional (level shifts), temporal (rhythm changes), and collective (inter-sensor correlation breakdowns) – each requiring different feature representations. Most unsupervised methods target only one or two types and provide limited interpretability. We present CRAFTIIF (Cross-Resolution Analytic Four-Type Interpretable Isolation Forest), a fully unsupervised framework targeting all four types without dataset-specific tuning. CRAFTIIF generates K=500 random analytic wavelet feature draws across four families (Morlet, DOG, Haar, Coiflet), each targeting a specific anomaly type, feeding five structured Isolation Forests – one per type plus a meta-IF for compound anomalies. An adaptive Otsu/MAD threshold calibrates detection automatically across anomaly rates from 0.1% to 69.2%. Because each IF is trained exclusively on type-specific features, branch firing provides direct anomaly-type attribution by construction, without post-hoc explanation. Evaluated on all 19 datasets of the mTSBench benchmark (Zhou et al., TMLR 2026), CRAFTIIF achieves mean F1=0.228 (all 19 datasets) and F1=0.322 (13 detectable datasets), ranking first among all 25 evaluated methods on VUS-PR (0.463 vs. previous best 0.329, +40.7%). A diagnostic framework – oracle F1, detectability limits, and branch separation ratios – identifies 6 of 19 datasets as fundamentally undetectable by any unsupervised method. Ablation over 11 conditions confirms adaptive thresholding (+38% F1), four-branch structure (+20%), and meta-IF (+23%) are each essential. Code: https://github.com/smitswil/craftiif

13.
arXiv (CS.AI) 2026-06-17

DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack

arXiv:2606.17574v1 Announce Type: new Abstract: Evaluating a Physical AI stack spans operators that differ by more than three orders of magnitude – from a single foundation-model decoding step to thousands of physics ticks of whole-body control – varying orthogonally in modality, reward semantics, and resource profile. No existing framework spans this range, so the stack is evaluated today by stitching together separate harnesses that share neither runtime nor scoring, preserving each segment's local validity but losing the shared identity needed to diagnose cross-layer regressions. We present DeepInsight, an evaluation infrastructure that serves this full spectrum on a single runtime. Rather than homogenize the regimes, it preserves their heterogeneity behind three narrow abstractions – task, resource, and result – each realized as one invariant shared by every subsystem: one episode driver, one resource-handle protocol implemented by every expensive backend (LLM inference and sandboxed runtimes alike), and one trace identity scheme under which every event is written. Deployed in production across all three layers of an embodied humanoid stack, this single set of invariants onboards new benchmarks largely by configuration. Where mature peer orchestrators exist – at the foundation-model end – it reproduces published references and peer-framework readings within their own spread, runs the same suites faster on a single node, and scales near-linearly across nodes. Its distinctive return is diagnostic: because every layer writes into one shared trace, a regression that begins in one layer and surfaces in another stays localizable on that trace – a cross-layer payoff no federation of per-segment harnesses can reproduce.

14.
arXiv (quant-ph) 2026-06-19

Electrical Noise Produced by Micron-Sized Particles above a Surface Paul Trap

arXiv:2606.19585v1 Announce Type: new Abstract: Electric field noise produced by the surface of ion trap electrodes reduces the fidelity of quantum computing operations. Despite decades of investigation its microscopic origins remain unclear. Here, we measure electric field noise at trapping locations along the symmetry axis of a linear surface Paul trap. We find that noise levels vary by three orders-of-magnitude in one 600$\,\mu$m section of the trap. Optical and scanning electron microscope images show micron-sized particles close to the trapping locations with the highest noise levels. We find that modeling the particles as a lossy dielectric with a effective loss tangent $\tan\theta=0.33(0.06)$ describes the magnitude of the noise, as well as its spatial and frequency dependence. Our observations may explain the large variation of reported noise levels in literature.

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

Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework

Current image editing methods excel at static attributes but fail at complex Human-Object Interactions (HOI), a critical challenge unaddressed by existing benchmarks that conflate HOI with static attributes, relying on global metrics incapable of simultaneously assessing dynamic interaction validity and entangled human-object pair preservation. Thus, we first introduce HOI-Edit, a comprehensive benchmark with three progressive cognitive levels, which features an automated metric HOI-Eval that reliably evaluates instance-level interaction by letting VLM Q&A after thinking with images containing grounded Human-Object pairs. Considering the task's essence of remodeling dynamic relationships, we benchmark Image-to-Video (I2V) models, finding them inherently suited for dynamic editing due to their temporal generation capabilities. Crucially, beyond superior performance, this capability provides a "replay of the failure process," offering unique diagnosability into why errors occur. We thus propose SCPE (Self-Correcting Process Editing), a novel, agentic self-correcting framework that constrains the generation of I2V models through iteratively refined prompts, enabling the generated videos to more accurately present the target HOI. Extracted frames from these videos are the final editing results. On HOI-Edit, SCPE achieves performance competitive with state-of-the-art (SOTA) editing models like Nano Banana on interaction. Code is available at https://github.com/oceanflowlab/HOI-Edit.

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

MotionVLA: Vision-Language-Action Model for Humanoid Motion

Generating realistic humanoid motion from scene images and text involves both low-frequency pose semantics and high-frequency physical dynamics. However, many existing methods tokenize motion with a single shared codebook, forcing heterogeneous motion signals into the same quantization space. Our frequency-domain analysis of human motion data reveals a clear mismatch between single-codebook quantization and motion statistics: five DCT coefficients capture 93% of joint-position energy but only 37% of joint-velocity energy, which can bias quantization toward pose statistics and under-represent high-frequency velocity components. A second challenge lies in adapting a standard autoregressive model to effectively model high-frequency physical signals in motion sequences. Therefore, we propose DSFT, a dual-stream frequency tokenizer that separates motion into Base and physical streams and compresses them independently with DCT truncation and BPE. Furthermore, we present MotionVLA, a Qwen3.5-based model that arranges Base and physical tokens in a unified sequence, where Phys tokens are predicted after Base tokens. Experiments on HumanML3D and MBench show that, despite using a lightweight 2B backbone, MotionVLA reduces the Diversity gap to real data by over 50% on HumanML3D and improves Motion-Condition Consistency by 3.8% on MBench, supporting frequency-aware dual-stream decoupling as an effective formulation for autoregressive motion generation. Code: https://github.com/AIGeeksGroup/MotionVLA. Website: https://aigeeksgroup.github.io/MotionVLA.

17.
arXiv (quant-ph) 2026-06-15

No classical particle limit for massless quanta

arXiv:2606.14632v1 Announce Type: new Abstract: We investigate whether relativistic massless classical particles may emerge as the classical limit of massless quanta. To address this question independently of any specific dynamics, environment, or pointer basis, we develop an axiomatic and purely kinematical framework for the coarse-graining approach. In this formulation, a candidate classical phase space is taken as the outcome space of a POVM subject only to minimal classicality and covariance under the relevant spacetime symmetry group. Applying this framework to the Poincaré group, we prove a no-go theorem for massless particles: the covariance requirement is incompatible with the operational conditions for classicality. The theorem leaves open field-like limits of massless quanta, for example the emergence of electromagnetic or gravitational fields, while ruling out classical massless particles, such as classical photons or gravitons.

18.
arXiv (CS.AI) 2026-06-17

Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers

arXiv:2602.07429v2 Announce Type: replace-cross Abstract: Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer analytical precision but are visually abstract, whereas discrete methods provide intuitive clarity at the expense of geometric precision. To bridge this gap, we introduce Brep2Shape, a novel self-supervised pre-training method designed to align abstract boundary representations with intuitive shape representations. Our method employs a geometry-aware task where the model learns to predict dense spatial points from parametric Bézier control points, enabling the network to better understand physical manifolds derived from abstract coefficients. To enhance this alignment, we propose a Dual Transformer backbone with parallel streams that independently encode surface and curve tokens to capture their distinct geometric properties. Moreover, the topology attention is integrated to model the interdependencies between surfaces and curves, thereby maintaining topological consistency. Experimental results demonstrate that Brep2Shape offers significant scalability, achieving state-of-the-art accuracy and faster convergence across various downstream tasks.Code is available at this repository: https://github.com/thuml/Brep2Shape.

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

MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios

Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available.

20.
arXiv (math.PR) 2026-06-19

The t-Split Two-Periodic Aztec Diamond Model

arXiv:2606.19507v1 Announce Type: new Abstract: In this work we consider an Aztec diamond model split into two unequal regions which are asymptotically fixed in size. Each region is weighted with a distinct two-periodic weighting. We refer to this model as the t-split two-periodic Aztec diamond, to signify its difference from the previous work title Split Two-Periodic Aztec Diamond, where the model was split into two equal regions. We derive an integral expression for the correlation kernel of the model and give a partial description of the scaling limit behavior, along with a conjecture for the remainder. We refer to the larger and smaller sides of the model as the dominant and non-dominant sides, and to the location of the weight change as the interface. The dominant side exhibits a limit shape that depends only on its own weighting and is identical to that of the two-periodic Aztec diamond, while the non-dominant side appears to have a novel limit shape that depends on both weightings and the location of the interface. Lastly, we consider the complete limit shape in the case where the dominant side two-periodic parameter goes to 0.

21.
arXiv (CS.AI) 2026-06-19

Toward Calibrated Mixture-of-Experts Under Distribution Shift

arXiv:2606.20544v1 Announce Type: new Abstract: Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent work shows that enforcing calibration at the level of individual predictors can improve ensemble accuracy and calibration, with mixture-of-experts (MoE) models showing strong empirical improvements in particular; however, the conditions under which calibration helps MoE are not well understood. In this work, we study how MoE models behave under distribution shift, focusing on how routing mechanisms interact with expert-level calibration. We show that expert calibration is sufficient to ensure calibration of the overall model under a broad class of distribution shifts in hard-routed models, but is insufficient for calibrating soft-routed models. To address this, we propose an adversarial reweighting that penalizes calibration errors of the routed aggregate under distribution shift, and we demonstrate that it improves the accuracy-calibration tradeoff both on average and on difficult subsets of the data, across model classes, prediction tasks, and distribution shifts.

22.
arXiv (CS.CL) 2026-06-15

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19–0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise–pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% ($\kappa = 0.51$), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

23.
medRxiv (Medicine) 2026-06-17

Investigating shared genetic overlap of immune-mediated inflammatory diseases and cardiometabolic diseases

Abstract Background: Immune-mediated inflammatory diseases (IMIDs) are associated with increased risk of cardiometabolic diseases. Investigating genetic overlap among these conditions can provide insights into their clinical management. Methods: Genetic correlation was assessed using linkage disequilibrium score regression (LDSC). Then, a meta-analysis was conducted using Association Analysis Based on SubSETs (ASSET) to pinpoint independent single nucleotide polymorphisms (SNPs) shared across the diseases. Each independent SNP was then used to define a genomic window (+/-500KB) for colocalisation analysis and Local Analysis of [co]Variant Association (LAVA) to offer multiple layers of regional pleiotropic evidence. Over-representation analysis was then run to identify enriched biological pathways, which then were used for drug target analysis. Results: The LDSC analysis showed a significant global genetic correlation for rheumatoid arthritis (RA) and cardiometabolic diseases including hypertension, coronary artery disease (CAD), heart failure (HF), stroke, atrial fibrillation (AF), and type two diabetes mellitus (T2DM) ranging from rg = 0.09 to 0.24. ASSET meta-analysis identified 164 independent SNPs shared across RA and the cardiometabolic diseases with P < 5 x 10- in the overall one-sided meta-analysis P-value, FDR < 0.05 in both individual GWASs, and TRUE phenotype matrix. Colocalisation analysis revealed multiple loci with strong evidence (Posterior probabilities [&ge;] 80) of single causal SNPs between the trait pairs. LAVA analysis was then used as an additional layer of confirmation for the findings generated by ASSET and colocalisation and thus several loci were highlighted. Over-representation analysis showed significant enriched immune-related pathways across RA-hypertension, RA-CAD, RA-AF, and RA-T2DM trait pairs. Drug target analysis highlighted several drugs which could be further tested for their effectiveness in RA and its common comorbidities. Conclusion: The findings revealed a shared genetic architecture and key immune-related biological pathways underlying RA and its associated cardiometabolic comorbidities. The identified genes and drugs provide opportunities for further therapeutic assessment which could improve clinical management strategies.

24.
arXiv (CS.LG) 2026-06-19

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

arXiv:2606.04101v3 Announce Type: replace-cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04.

25.
arXiv (CS.LG) 2026-06-11

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

arXiv:2606.11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution. Upon detection, a conformal abstention layer adapts decision thresholds to recover a target error rate epsilon=0.1. In a pre-registered factorial evaluation (4 classifiers x 5 shift conditions x 20 seeds x 2 window sizes, 800 cells), the system achieves 86.6% valid detection (693/800, 95% CI [84.1%, 88.8%]) with mean latency of 39.5 steps. Detection holds across three ground-truth regimes: synthetic onset (86.6%), real temporal jailbreaks (85%, 17/20), and GCG adversarial attacks. Weighted conformal prediction recovers up to 39 pp of lost coverage for DeBERTa (ESS=46/300) but collapses for all other classifiers (ESS~300): logistic density ratio estimation achieves perfect source/target separability in high-dimensional embedding spaces, clipping all importance weights to the floor. DeBERTa shows a gradient from effective correction (paraphrase, ESS=46) to near-total collapse (adversarial suffix, ESS=206). PCA to 32 dimensions breaks the collapse, recovering 33 pp for Llama Guard and 21 pp for ShieldGemma. Variance decomposition reveals classifier (eta^2=0.243), shift type (eta^2=0.237), and their interaction (eta^2=0.185) all contribute substantially to detection latency variance (all p