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) 2026-06-11

Impact of Out-Migration and Remittances on Food Consumption Outcomes among Rural Households in Tigray, Ethiopia

作者:

This study examines the effects of rural out-migration and remittance inflows on food consumption outcomes among rural households in the Tigray region of Ethiopia. Utilizing household survey data collected from 521 rural households across three distinct Weredas (districts) (Tahtay Maichew, Kola Tembien, and Kilte-awlaelo). A Binary Probit model was employed to identify factors influencing migration decisions, while an Endogenous Switching Regression (ESR) model was used to estimate the impact of migration on food consumption outcomes while controlling for selection bias and unobserved heterogeneity. Food security was measured using the Food Consumption Score (FCS) and dietary diversity indicators. The empirical results reveal that severe food insecurity is widespread, with over 60% of all surveyed households falling into the "Poor" food consumption category. Descriptive baseline comparisons show that migration and remittance transfers marginally shift the raw average FCS upward from 23.86 to 25.48. However, this impact is profoundly nuanced: remittances serve as an immediate consumption-smoothing safety net but run parallel to a "labor-lost" constraint that reduces own-production capacities, forcing households to rely increasingly on market purchases for staple foods. The findings reveal that migration creates short-term labor shortages in agricultural production; however, remittance inflows substantially improve household food consumption frequencies, particularly for pulses, vegetables, and other nutrient-rich foods. After accounting for self-selection bias and unobserved traits, the rigorous ESR estimates indicate that migration increases the Food Consumption Score of participating households by an average Treatment Effect on the Treated (ATT) of 10.75 points, shifting them into more secure dietary tiers. Moreover, remittances help households mitigate the adverse effects of drought and other shocks by relaxing liquidity constraints and supporting both food purchases and agricultural investments. The study recommends establishing target food security safety nets for non-remittance households, promoting scale-appropriate labor-saving agricultural technologies, expanding traditional communal labor-sharing innovations, and boosting irrigation and agricultural input support programs to enhance rural food security and livelihood resilience.

02.
arXiv (CS.AI) 2026-06-24

DynamicPO: Dynamic Preference Optimization for Recommendation

arXiv:2605.00327v3 Announce Type: replace-cross Abstract: In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback negatives and sharpen preference boundaries. However, our empirical analyses reveal a counterintuitive phenomenon, preference optimization collapse, where increasing the number of negative samples can lead to performance degradation despite a continuously decreasing training loss. We further theoretically demonstrate that this collapse arises from gradient suppression, caused by the dominance of easily discriminable negatives over boundary-critical negatives that truly define user preference boundaries. As a result, boundary-relevant signals are under-optimized, weakening the model's decision boundary. Motivated by these observations, we propose DynamicPO (Dynamic Preference Optimization), a lightweight and plug-and-play framework comprising two adaptive mechanisms: Dynamic Boundary Negative Selection, which identifies and prioritizes informative negatives near the model's decision boundary, and Dual-Margin Dynamic beta Adjustment, which calibrates optimization strength per sample according to boundary ambiguity. Extensive experiments on three public datasets show that DynamicPO effectively prevents optimization collapse and improves recommendation accuracy on multi-negative preference optimization methods, with negligible computational overhead. Our code and datasets are available at https://github.com/xingyuHuxingyu/DynamicPO.

03.
arXiv (CS.LG) 2026-06-24

Adversarial dynamical systems characterize when data-driven learning succeeds or fails

arXiv:2407.06312v2 Announce Type: replace-cross Abstract: Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or generalize, leaving open a central question: When can system behavior be learned reliably from data, and when is such learning impossible? We answer this question using adversarial dynamical systems to identify the boundary between accessible and inaccessible regimes. In Koopman operator learning, a leading framework for representing nonlinear dynamics through linear spectral objects, we design optimal data-driven spectral algorithms with convergence and certification guarantees under conditions arising broadly in physical systems. This yields a convergence theory for Koopman-operator approximations and resolves a longstanding open problem in Koopman spectral analysis. Conversely, by constructing adversarial systems, we prove matching impossibility results: without these conditions, no single-sequence limiting procedure can guarantee learning, regardless of data quality. These results sharply characterize when data-driven spectral learning can succeed and when it must fail. We validate the framework on oscillators, chaotic fluid flows and Arctic sea ice concentration forecasting. In the latter, we uncover hidden modes of Arctic sea ice decline, deliver long-range forecasts with geographic error bounds, and outperform state-of-the-art dynamical and deep learning models at substantially lower computational cost, enabling real-time deployment on standard CPUs.

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

Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift

The robustness of machine learning models can be compromised by spurious correlations between non-causal features in the input data and target labels. A common way to test for such correlations is to train on data where the label is strongly tied to some non-causal cue, then evaluate on examples where that tie no longer holds. This idea is well established for classification tasks, but for semantic segmentation the specific failure modes are not well understood. We show that a model may achieve reasonable overlap while assigning the wrong semantic label, swapping one plausible foreground class for another, even when object boundaries are largely correct. We focus on this semantic label-flip behaviour and quantify it with a simple diagnostic (Flip) that counts how often ground truth foreground pixels are assigned the wrong foreground identity while remaining predicted as foreground. In a setting where category and scene are correlated during training, increasing the correlation consistently widens the gap between common and rare test conditions and increases these within-object label swaps on counterfactual groups. Overall, our results motivate assessing segmentation robustness under distribution shift beyond overlap by decomposing foreground errors into correct pixels, flipped-identity pixels, and missed-to-background pixels. We also propose an entropy-based, ground truth label-free `flip-risk' score, which is computed from foreground identity uncertainty, and show that it can flag flip-prone cases at inference time. Code is available at https://github.com/acharaakshit/label-flips.

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

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

arXiv:2605.30837v2 Announce Type: replace-cross Abstract: Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed single-detector pipeline, committing every request to one detector's blind spots. We reframe defense as detector allocation: given a heterogeneous pool, decide per request which detectors to run and whether to escalate to an LLM judge. Our framework SCOUT (Scalable and Controllable Outcome-prediction for Uncertainty-aware Triage) makes this decision dynamic by predicting each detector's per-sample reliability and latency from how it behaved on similar past inputs, and exposes a single safety-utility threshold to the operator (where utility bundles benign-pass rate and wall-clock). To evaluate this setting, we build SCOUT-450, a benchmark that captures the structurally complex, agent-facing injections that older prompt-injection sets under-represent. On SCOUT-450, a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge, at a 5.1-point benign-utility drop. SCOUT also transfers to three external benchmarks (BIPIA, IPI, and IHEval), improving the safety-utility frontier.

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

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

arXiv:2510.10981v3 Announce Type: replace-cross Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time.

07.
medRxiv (Medicine) 2026-06-23

Multivariate Echocardiographic Phenotyping of Hypertensive Heart Failure Using Unsupervised Machine Learning: A Pilot Study

Background Heart failure in hypertensive patients is heterogeneous and poorly captured by traditional left ventricular ejection fraction (LVEF) based classification. Multivariate echocardiographic data combined with unsupervised machine learning may provide a more precise phenotypic characterization. This pilot study evaluated the feasibility of unsupervised clustering of routine transthoracic echocardiographic data to identify phenotypic subgroups of hypertensive heart failure. Methods This retrospective pilot study analyzed transthoracic echocardiography reports from hypertensive patients with clinical heart failure. After data cleaning and exclusion of incomplete records, 102 patients with 11 echocardiographic variables were included. Variables describing left ventricular geometry, systolic function, and diastolic performance were standardized and subjected to K-means clustering. Optimal cluster number was determined using the elbow method and silhouette analysis. Cluster characteristics were assessed using descriptive statistics and Kruskal Wallis testing. Concordance with LVEF based heart failure categories was evaluated. Results Three distinct echocardiographic phenotypes were identified. Cluster 0 (n = 50) demonstrated preserved LVEF with concentric remodeling, consistent with heart failure with preserved ejection fraction (HFpEF) phenotype. Cluster 1 (n = 37) showed marked ventricular dilation and reduced systolic function, consistent with heart failure with reduced ejection fraction (HFrEF). Cluster 2 (n = 15) exhibited concentric hypertrophy with intermediate LVEF, consistent with heart failure with mildly reduced ejection fraction (HFmrEF) like phenotype. All echocardiographic variables differed significantly across clusters (p < 0.001). While Cluster 0 showed strong concordance with HFpEF (96%), Clusters 1 and 2 demonstrated substantial overlap across LVEF categories, indicating partial discordance between structural phenotypes and LVEF based classification. Conclusion Application of unsupervised machine learning to routine echocardiographic data identifies distinct heart failure phenotypes in hypertensive patients. These phenotypes demonstrate significant structural heterogeneity beyond LVEF based classification, supporting the utility of data-driven approaches for refined cardiac phenotyping. This pilot study provides a foundation for larger prospective studies.

08.
medRxiv (Medicine) 2026-06-22

Evidence-guided AI regularization for suicidal ideation prediction in pediatric bipolar disorder

Background: Suicide prediction models in psychiatry often rely on purely data-driven feature selection, which can produce unstable and clinically opaque predictor sets in modest-sized samples. We developed Evidence-Based AI LASSO (EBAL), an evidence-guided regularization framework that incorporates curated clinical evidence into feature-specific penalty factors for interpretable prediction. Methods: Baseline data from 136 youth with confirmed bipolar spectrum disorder in the Greater Houston Area Bipolar Registry were analyzed using 20 candidate clinical predictors. Forty higher-level evidence documents on suicidality and related predictor domains were curated through a structured evidence synthesis workflow and indexed as an auditable evidence corpus. An open-weight large language model assigned feature-specific penalty factors using a prespecified scoring rubric, and these penalties were used to fit a weighted LASSO model. EBAL was compared with a standard evidence-agnostic LASSO using nested leave-one-out cross-validation. Results: For suicidal ideation, EBAL achieved an AUROC of 0.768, balanced accuracy of 0.757, sensitivity of 0.758, and specificity of 0.757. The standard LASSO achieved an AUROC of 0.760 and balanced accuracy of 0.715. EBAL improved balanced accuracy (+0.042, p=0.010) and Matthews correlation coefficient (+0.079, p=0.010), while retaining fewer stable predictors than standard LASSO (11/20 vs 18/20). The strongest positive predictors were current depressed mood, duration of mood disorder illness, and comorbid generalized anxiety disorder. For suicidal behavior, both models performed near chance and retained all candidate predictors. Limitations: The study was cross-sectional, single-site, and modest in sample size, with no external validation cohort. Conclusions: EBAL produced a sparser and more clinically coherent model for suicidal ideation in pediatric bipolar disorder, but did not improve prediction of suicidal behavior. These findings support evidence-guided regularization as a transparent strategy for aligning psychiatric prediction models with prior clinical knowledge while preserving interpretability.

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

SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360$^\circ$ Panorama Generation

Panoramic imagery is increasingly used in world-generation, games, and simulation, where users may need not only photorealistic scenes but also stylized and non-photorealistic environments. Large-scale text-to-image diffusion and flow models provide broad style and semantic priors for this goal, but planar image training misaligns them with the wrap-around topology and polar regions of $360^\circ$ panoramas represented in equirectangular projection (ERP). We present SHERPA, a lightweight adaptation framework that combines frequency-selective Circular RoPE, Circular Latent Encoding/Decoding, image-side FFN adapters, and a Dual-Path Training Scheme. Circular RoPE replaces only the seam-sensitive high-frequency horizontal RoPE band with integer-periodic harmonics while preserving the pretrained lower-frequency spectrum. The Paired Panorama Path supervises geometry, while the Unpaired Style Path uses self-supervised yaw consistency for target-free stylized prompts. As a result, SHERPA generates $360^\circ$ panoramas across both photorealistic panorama domains and open-domain stylized prompts.

10.
bioRxiv (Bioinfo) 2026-06-22

Multivariate Random Forests for Cross-Modal Multi-Omics Integration

Multi-omics studies are widely used across many areas of biomedical research. In many diseases, some signals are shared across data types, while others are strongest in a single omics layer. Current multi-omics clustering methods often either merge all data types into a single representation, which can blur biology that is strong in one layer, or rely on linear structure that may miss more complex relationships across data types. We introduce multiRF, a random-forest-based method that handles complex data types and separates shared and modality-specific structure for multi-omics data. multiRF learns sample similarities across omics layers from multivariate random forests, combines them across data types, and uses the resulting weights to estimate the part of each omics layer that is predictable from the others. The remaining residual is treated as modality-specific signal, allowing shared and modality-specific similarities to be clustered separately. In simulations, multiRF recovered shared clusters as well as or better than established integrative methods while more reliably separating modality-specific signal under nonlinear data structures. In TCGA head and neck squamous cell carcinoma, the shared component aligned with the main subtype structure across established reference classifications, while gene- and miRNA-specific components revealed additional immune and developmental biology. In the ADNI cohort with matched blood DNA methylation and structural MRI, the shared cross-modal aging signal was associated with future conversion to mild cognitive impairment or Alzheimer's disease, and a DNAm-specific residual signal showed exploratory additional information. These results show that multiRF can recover a common disease axis while retaining biologically meaningful signals specific to one data type. multiRF is available as an open-source R package at https://github.com/novawz/multiRF.

11.
arXiv (CS.AI) 2026-06-19

Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery

arXiv:2606.19812v1 Announce Type: new Abstract: Autonomous Large Language Model (LLM) agents are increasingly deployed in electronic discovery (e-discovery), where compounding errors across multi-step reasoning chains can constitute legal malpractice. Unlike single-turn retrieval, agentic workflows operating over privileged document corpora exhibit a class of failure we term "trajectory collapse": an early misclassification silently propagates, rendering an entire privilege review invalid. This paper makes three contributions. First, we propose a structured taxonomy of agentic failures in legal information retrieval, organized by functional stage. Second, we introduce a four-layer verification architecture – spanning planning, reasoning, execution, and uncertainty quantification – designed to intercept these failures before they compound. Third, we present a preliminary simulation study on a synthetic e-discovery corpus that demonstrates how mandatory Human-on-the-Loop (HOTL) escalation thresholds reduce privilege-waiver risk relative to fully autonomous baselines. Our results suggest that calibrated uncertainty thresholds can reduce privilege-waiver risk by up to 61% versus fully autonomous deployment, while routing fewer than one quarter of documents to attorney review.

12.
bioRxiv (Bioinfo) 2026-06-16

Programmatic access to ICTV virus taxonomy through a public ontology API

The International Committee on Taxonomy of Viruses (ICTV) is responsible for developing and maintaining a universal virus taxonomy. As the reference framework for organising the viral world, it is essential for virology and related fields. Despite its widespread use in research and public health, programmatic access to ICTV taxonomy has remained limited, posing challenges for integration, versioning, and interoperability across databases and bioinformatics resources requiring up-to-date virus taxonomy. To address this, we developed a public and sustainable solution leveraging ontology-based APIs. Successive ICTV Master Species List (MSL) releases were transformed into a structured ontology and deployed as a unified representation through the Ontology Lookup Service (OLS). The framework also provides ICTV-NCBI mappings and helper libraries for integration into downstream systems. This enables, for the first time, public programmatic retrieval of current and historical virological taxon names, taxonomic relationships, metadata, and persistent identifiers through stable endpoints. More broadly, this work illustrates a general strategy for transforming structured biological datasets into semantically enriched graph resources exposed through scalable public APIs. These developments enhance interoperability, reduce manual curation, and support FAIR-aligned taxonomic data management in virology and pandemic preparedness.

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

Contextual Invertible World Models: A Neuro-Symbolic Agentic Framework for Colorectal Cancer Drug Response

arXiv:2603.02274v3 Announce Type: replace-cross Abstract: Precision oncology is currently limited by the small-N, large-P paradox, where high-dimensional genomic data is abundant but pharmacological response samples are sparse. While deep learning achieves predictive accuracy, it frequently fails to provide the mechanistic clarity required for clinical adoption. We present the Contextual Invertible World Model (CIWM), a Neuro-Symbolic Agentic Framework that bridges this gap by integrating a quantitative machine learning emulator with a Large Language Model reasoning layer. Utilising a stringently curated, high-fidelity data engineering pipeline on the Sanger GDSC dataset (\( N=83 \)), we isolate true biological signals from in vitro artifacts to establish a rigorous baseline predictive correlation for complex transcriptomics (\( r=0.268 \)). Through Inverse Reasoning, we perform in silico CRISPR perturbations across the colorectal landscape. The framework autonomously overturns classical mechanistic assumptions, identifying a hierarchical dominance of mutant KRAS over the APC/Wnt-axis in driving 5-fluorouracil resistance (\( \Delta=-0.0469 \)) via a "KRAS Shield" mapped to MAPK/PI3K networks. Furthermore, the agentic layer identified a "PIK3CA Paradox", revealing that repairing PIK3CA inadvertently increases chemoresistance (\( \Delta=+0.0085 \)) by triggering a compensatory feedback loop that hyperactivates the dominant MAPK survival pathway.

14.
arXiv (CS.AI) 2026-06-11

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning

arXiv:2606.11092v2 Announce Type: replace-cross Abstract: Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball positions and strike timings; in contrast, task reward-driven RL struggles to explore and discover valid kicks from scratch. We therefore introduce RoboNaldo, a three-stage motion-guided curriculum RL framework for high-impulse humanoid interaction. A single human-kick reference is used as a scaffold and progressively shifts optimization towards shooting performance. The curriculum first learns a stable whole-body kicking prior, then adapts the kick to free-kick settings where the ball is stationary at random positions, and finally extends it to moving-ball shooting through a locomotion-command and kick-trigger interface. A high-level heuristic planner controls this interface during training, while alternative high-level controllers can drive the same low-level policy at inference. In simulation, RoboNaldo demonstrates free-kick shot error 48.6% lower and shoot velocity 2.96x than prior work baselines. In real world on a Unitree G1 with onboard perception, RoboNaldo attains 0.73 m and 0.86 m average target shooting error from 3 m away in free-kick and moving-ball cases, accordingly. And the post-contact ball velocity reaches 13.10 m/s, which is 59-71% of reported professional open-play shot speed. Project page: https://opendrivelab.com/RoboNaldo.

15.
Nature (Science) 2026-06-17

Emergent decadal predictability in Antarctic contribution to sea-level rise

Despite large uncertainties associated with future mass loss from the Antarctic Ice Sheet, ice-sheet models show that the rate of sea-level rise from Antarctic ice loss in 2025 is strongly predictive of the rate for the next several decades, regardless of emission pathway or model complexity. This finding is robust across all models that were considered in the Intergovernmental Panel on Climate Change Sixth Assessment Report global mean sea-level projections, including the low-likelihood, high-impact scenarios of sea-level rise. Given this strong near-term decadal predictability, ice-sheet models that can accurately reproduce present-day ice-mass loss provide a reliable basis for near-term sea-level planning and adaptation through to mid-century. The predictability breaks down by the end of the twenty-first century as feedbacks, such as those related to marine ice-sheet retreat, begin to emerge, leading to accelerating ice loss. Drawing on these results, we identify key feedback mechanisms that can account for the transition between near-term decadal predictability and the longer-term, feedback-driven evolution, and suggest priorities for ice-sheet model development aimed at resolving long-term sea-level rise uncertainty. Although Antarctic ice loss projections diverge widely by 2100, this Perspective shows that present-day rates robustly predict mid-century sea level rise, providing a firm basis for near-term planning, while highlighting priorities for model development aimed at resolving longer-term sea level rise uncertainty.

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

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

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

17.
PLOS Computational Biology 2026-06-15

WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments

作者:

by Hongkang Shi, Linbo Li, Shiping Zhu, Haibo He, Minghui Zhu, Jianfei Zhang Variety breeding has long been a cornerstone of high-quality agriculture, and recent advances in artificial intelligence have opened new avenues for accelerating biological breeding. In this study, we applied multiple object tracking (MOT) technology to silkworm breeding to achieve efficient, non-invasive, and dynamic individual monitoring. Unlike pedestrian or vehicle tracking, silkworms pose unique challenges for MOT due to their small size, dense distribution, and high inter-individual similarity, which complicate accurate tracking and behavioral analysis. To address these issues, we propose WormSORT, an enhanced tracking method based on a tracking-by-detection framework with an optimized data association strategy. A pre-trained detection model identifies silkworms in each frame, and deep feature vectors are extracted using a re-identification network. Identity association is first performed using Intersection over Union (IoU) matching, followed by deep feature similarity for unmatched cases, improving both tracking accuracy and reliability. To further enhance tracking stability, we introduce a candidate input padding mechanism, including IoU padding and feature padding, ensuring that high-confidence unmatched trajectories and detections remain involved in the matching process. To validate the proposed tracking strategy, we constructed two multiple silkworm tracking (MST) datasets: MST-50, containing approximately 50 individuals over 1000 frames, and MST-100, containing approximately 100 individuals over 1200 frames. Experimental results demonstrate that WormSORT outperforms existing methods, including DeepSORT, StrongSORT, OCSORT, ByteTrack, and BotSORT, achieving superior tracking performance. This study provides a valuable reference for silkworm tracking and behavioral analysis, contributing to the advancement of high-quality silkworm rearing and management.

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

Autoregressive Direct Preference Optimization

arXiv:2602.09533v2 Announce Type: replace Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradley-Terry (BT) model may limit its full potential, as the reference and learnable models are assumed to be autoregressive only after deriving the objective function. Motivated by this limitation, we revisit the theoretical foundations of DPO and propose a novel formulation that explicitly introduces the autoregressive assumption prior to applying the BT model. By reformulating and extending DPO, we derive a novel variant, termed Autoregressive DPO (ADPO), that explicitly integrates autoregressive modeling into the preference optimization framework. Without violating the theoretical foundations, the derived loss takes an elegant form: it shifts the summation operation in the DPO objective outside the log-sigmoid function. Furthermore, through theoretical analysis of ADPO, we show that there exist two length measures to be considered when designing DPO-based algorithms: the token length $\mu$ and the feedback length $\mu'$. To the best of our knowledge, we are the first to explicitly distinguish these two measures and analyze their implications for preference optimization in LLMs.

19.
arXiv (CS.CV) 2026-06-12

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

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

Optimal Transport for Machine Learners

arXiv:2505.06589v2 Announce Type: replace-cross Abstract: Modern machine learning repeatedly manipulates probability measures: empirical datasets, generated samples, latent distributions, class-conditional laws, particle systems, weights of wide networks and attention patterns. Optimal transport is useful in this setting because it compares such objects by asking how mass should move. It therefore combines a statistically meaningful notion of discrepancy with a geometry of interpolation, dual certificates and variational dynamics. This makes OT a common language for losses, generative modeling, domain adaptation, robust learning, barycenters, gradient flows and mean-field descriptions of learning algorithms. This book presents the main OT techniques with these machine-learning uses in mind. It starts from finite assignment and the Monge map viewpoint, passes to Kantorovich couplings and dual potentials, and then explains the algorithmic ideas that make transport usable: linear programming, semi-discrete cells, Sinkhorn scaling and low-dimensional projections. The same objects are then reused as a geometry of measures, giving Wasserstein distances, barycenters, gradient flows, dynamic formulations and Gaussian/Bures formulas. The final chapters emphasize the variants most relevant to modern ML: divergences and adversarial losses, entropic and unbalanced relaxations, robust or spectral ground geometries, Gromov and quantum extensions, and transport-based views of generative models, mean-field networks and attention dynamics. The goal is to keep the mathematics explicit while exposing the computational and geometric intuitions needed to turn OT into a working toolbox for machine learners.

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

Toward Human-Centered AI-Assisted Terminology Work

Generative AI is likely to transform terminology work by creating new opportunities for automation. At the same time, it raises concerns about the future of terminologists and terminological resources, as efficiency pressures may encourage excessive automation based on the perception that human expertise can be replaced by AI. However, large language models remain unreliable for terminological purposes due to errors, hallucinations, and various forms of bias, making terminologists indispensable for ensuring the accuracy and reliability of terminological data. This paper argues that human-centered AI, an approach that emphasizes that AI's primary goal should be to contribute to human well-being, provides a framework for maximizing the benefits of generative AI while mitigating its risks. It contends that high levels of automation and meaningful human control are compatible and desirable, and that AI should enhance terminologists' capabilities while preserving their agency and decision-making authority. The implications of AI-assisted terminology work are examined through three interrelated dimensions: the augmented terminologist, ethical AI, and human-centered design. In particular, the paper examines how AI integration reshapes the role of the terminologist, affects professional values and working conditions, requires the management of AI-generated bias, and calls for the design of AI tools around the terminologist's needs. The paper concludes that a human-centered orientation is necessary to ensure that AI strengthens, rather than undermines, the essential role of terminology work in supporting specialized communication and the accurate transmission of knowledge across languages and cultures.

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

ESBMC-PLC: Formal Verification of IEC 61131-3 Ladder Diagram Programs Using SMT-Based Model Checking

PLCs execute safety-critical programs across industrial sectors. The dominant PLC notation, ladder diagram (LD) per IEC 61131-3, remains absent from formal verification: SMT-based model checkers cannot process LD's rung-and-coil graphics. This paper presents ESBMC-PLC, the first open-source formal verifier with native LD support (PLCopen XML format), implemented as a new ESBMC frontend. ESBMC-PLC translates LD rungs to GOTO IR, models the PLC scan cycle as a while(true) loop with nondeterministic inputs, and checks safety properties via SMT-based bounded model checking or k-induction. A five-property YAML language (mutual_exclusion, invariant, absence, response, reachability) avoids temporal logic. A survey of 22 studies (2020-2026) identifies four research gaps; ESBMC-PLC closes two of them. Evaluation on 13 benchmarks (6 domains, 3 sources - including deployed CONTROLLINO PLCs and MathWorks Simulink PLC Coder) shows correct classification across 61 properties: all 9 author-constructed programs (Categories A/B) as expected, all 4 vendor programs (Category C) correctly unlabeled, with 8 bugs found (actionable counterexamples), 7 unbounded k-induction proofs, all runs under 60ms on Apple Silicon. Feature comparison with PLCverif shows that ESBMC-PLC is the only open-source tool that combines native LD, k-induction, and SMT bit-vector semantics.

23.
arXiv (CS.CV) 2026-06-25

Learning Action Priors for Cross-embodiment Robot Manipulation

Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy jointly. This design inherits strong visual and linguistic priors from the VLM, but leaves the action module to learn physical motion almost from scratch. As a result, the policy lacks an explicit motion prior, forcing early optimization to simultaneously discover temporal action dynamics and cross-modal alignment, a challenge further amplified in cross-embodiment settings. In this work, we propose to pretrain the action module with motion priors before cross-modal VLA alignment. Specifically, we introduce a two-stage training framework that equips the action module with cross-embodiment temporal motion structure before VLA training begins. In Stage~1, a lightweight flow-matching-based encoder-decoder action module efficiently learns temporal motion structure solely from unconditioned action trajectories, without processing visual or language tokens. In Stage~2, this learned prior is transferred to VLA training through decoder reuse and early-stage latent distillation, aligning visual-language features with the action embedding space while still allowing end-to-end policy refinement. In addition, the trained encoder serves as a compact history compressor, summarizing state-action histories into a single temporal context token for history-aware modeling at negligible cost. Extensive experiments across 13 diverse cross-embodiment tasks on both simulated and real-world platforms validate the effectiveness of our approach. Compared with VLA training without action priors, our model achieves faster convergence, higher success rates, and substantially stronger performance on data-scarce real-world tasks. Moreover, scaling up the action data in Stage~1 yields a more generalizable action prior that directly improves downstream VLA performance.

24.
bioRxiv (Bioinfo) 2026-06-11

GermRL: Alleviating The Germline Bias In Autoregressive Antibody Language Models Through Reinforcement Learning

Antibodies are powerful therapeutics whose antigen specificity arises from sequence diversity shaped during development. Recently, language models trained on large antibody repertoire datasets have enabled the generation and screening of novel candidates, but these models retain a strong germline bias. As AI adoption increases in therapeutic workflows, it is crucial to develop models that harness the diversity of antibodies necessary for the discovery of mutations that encode desirable properties. Previous work explored the germline bias in masked antibody language models, yet the bias in generative autoregressive language models has not yet been addressed. Here, we present GermRL, a lightweight and modular reinforcement learning (RL) framework capable of alleviating the germline bias in pre-trained antibody autoregressive language models through group relative policy optimization (GRPO). GermRL achieves consistent one-shot generation of antibodies that satisfy specified mutation thresholds from germline while maintaining structural plausibility. Under the lowest and highest mutation thresholds tested (5 and 35 mutations from germline), GermRL scores 0.992 and 0.950 pass@1, respectively, compared to 0.398 and 0.034 for the pre-trained language model. Within GermRL, we introduce a key pair of modifications to GRPO that increase training efficiency by discouraging reward hacking under our antibody application. Furthermore, comparison of RL generated and natural antibody sequences reveals how RL based optimization can explore alternative evolutionary mutational patterns and residue compositional strategies while preserving key global properties of natural antibodies, including identifiable germline assignments, embedding-level similarity and comparable developability profiles. Thus, RL-trained generative models optimized to promote antibody mutations through diversity from germline provide a promising framework for navigating the antibody sequence landscape, enabling exploration of novel yet biologically plausible candidates for therapeutic design.

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

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

arXiv:2606.04145v2 Announce Type: replace-cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality. As Gao et al. (2023) showed, this proxy diverges from world feedback (downstream eval metrics) under sustained optimization pressure, a phenomenon known as reward overoptimization. Existing platform schedulers ignore this divergence: non-clairvoyant schedulers optimize JCT without any quality signal, SLAQ-style quality-aware schedulers use training loss (a weaker proxy that drops monotonically through hacking), and classical per-job early stopping requires human monitoring and does not free shared GPUs. We propose EvalStop, a composable scheduling primitive that terminates jobs on k consecutive eval-score declines, releases GPUs, preserves the best checkpoint, and delegates to any base scheduler. We frame scheduler-level early stopping as a detection problem and evaluate it in a discrete-event simulator whose RLHF workload mixes reward-hacking and structurally healthy runs, with ground-truth labels hidden from schedulers. On RLHF-heavy workloads (80% RLHF, 64 GPUs), EvalStop achieves precision 98% / recall 99% / FPR 1.5% while improving JCT by 9% and cutting wasted compute by 22% over SRTF-Est (p