探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2509.06216

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

作者:

Ahmed E. Hassan↗Hao Li↗Dayi Lin↗Bram Adams↗Tse-Hsun Chen↗Yutaro Kashiwa↗Dong Qiu↗

arXiv:2509.06216v3 Announce Type: replace-cross Abstract: Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

阅读与讨论 → 访问原文 →

02.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.16636

Free energy of non-convex multi-species spin glasses with centered Ising spins

作者:

Hong-Bin Chen↗Victor Issa↗Jean-Christophe Mourrat↗

arXiv:2606.16636v1 Announce Type: new Abstract: We identify the limit free energy of all multi-species spin glasses with centered $\pm 1$ spins. The result was previously known only under a convexity assumption on the covariance function of the Hamiltonian. We also obtain a one-species reduction of the formula for balanced multi-species models.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2602.02877

A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization

作者:

Xiyuan Wei↗Linli Zhou↗Bokun Wang↗Chih-Jen Lin↗Tianbao Yang↗

arXiv:2602.02877v2 Announce Type: replace Abstract: This paper studies optimization for a family of problems termed $compositional entropic risk minimization$, in which each data's loss is formulated as a Log-Expectation-Exponential (Log-E-Exp) function. The Log-E-Exp formulation serves as an abstraction of the Log-Sum-Exponential (LogSumExp) function when the explicit summation inside the logarithm is taken over a gigantic number of items and is therefore expensive to evaluate. While entropic risk objectives of this form arise in many machine learning problems, existing optimization algorithms suffer from several fundamental limitations including non-convergence, numerical instability, and slow convergence rates. To address these limitations, we propose a geometry-aware stochastic algorithm, termed $SCENT$, for the dual formulation of entropic risk minimization cast as a min–min optimization problem. The key to our design is a $stochastic proximal mirror descent (SPMD)$ update for the dual variable, equipped with a Bregman divergence induced by a negative exponential function that faithfully captures the geometry of the objective. Our main contributions are threefold: (i) we establish an $O(1/\sqrt{T})$ convergence rate of the proposed SCENT algorithm for convex problems; (ii) we theoretically characterize the advantages of SPMD over standard SGD update for optimizing the dual variable; and (iii) we demonstrate the empirical effectiveness of SCENT on extreme classification, partial AUC maximization, contrastive learning and distributionally robust optimization, where it consistently outperforms existing baselines. Code is available at https://github.com/Optimization-AI/SCENT.

阅读与讨论 → 访问原文 →

04.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.15066

Quantum simulation of the Liouville equation in classical mechanics with discontinuous potential via Schrödingerization

作者:

Shi Jin↗Shuyi Zhang↗

arXiv:2606.15066v1 Announce Type: new Abstract: We develop quantum simulation algorithms for the Liouville equation of classical mechanics with discontinuous potential. Such discontinuities represent potential barriers at which classical particles undergo energy preserving transmission or reflection, and the resulting interface conditions must be incorporated into the numerical flux. We combine Hamiltonian-preserving schemes by Jin and Wen in Commun. Math. Sci. 3(3), 285-315 (2005) with the Schrödingerization method, which embeds the resulting nonunitary semi-discrete dynamics into a unitary Schrödinger type system in one additional auxiliary variable [arXiv:2212.14703, arXiv:2212.13969]. For one-, two-, and $n$-dimensional problems with grid aligned interfaces, we construct sparse matrix representations of the transmission and reflection fluxes using step and hat functions, derive the corresponding Hamiltonians of the Schrödingerized systems, and analyze their sparse-access query complexity. In the sparse-access oracle model, the resulting algorithms have a polynomial dependence on the inverse accuracy and avoid the exponential dependence on the phase-space dimension suffered by classical grid based Hamiltonian-preserving schemes, up to the cost of implementing the oracles and the postselection overhead. We also describe the postselected recovery of the physical solution state and the quantum readout of macroscopic observables such as density and averaged velocity through overlap estimation. Numerical experiments based on classical simulation of the Schrödingerized dynamics validate the proposed formulation and illustrate the correct transmission/reflection behavior at potential barriers.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2507.04219

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

作者:

Yan Scholten↗Sophie Xhonneux↗Leo Schwinn↗Stephan G\"unnemann↗

arXiv:2507.04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally contradicts the principle of minimizing its use. As a remedy, we propose a novel unlearning method-Partial Model Collapse (PMC), which does not require unlearning targets in the unlearning objective. Our approach is inspired by recent observations that training generative models on their own generations leads to distribution collapse, effectively removing information from model outputs. Our central insight is that model collapse can be leveraged for machine unlearning by deliberately triggering it for data we aim to remove. We theoretically analyze that our approach converges to the desired outcome, i.e. the model unlearns the data targeted for removal. We empirically demonstrate that PMC overcomes four key limitations of existing unlearning methods that explicitly optimize on unlearning targets, and more effectively removes private information from model outputs while preserving general model utility. Overall, our contributions represent an important step toward more comprehensive unlearning that better aligns with real-world privacy constraints. Code available at https://www.cs.cit.tum.de/daml/partial-model-collapse/.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17391

NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama

作者:

Logan Mann↗Abdur Rahman↗Mohammad Saifullah↗Taaha Kazi↗Vasu Sharma↗

Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, with cross-lingual evaluation across four Indic languages (Hindi, Tamil, Telugu, Marathi). We introduce N-VSSM, a Narrative Variational State-Space Model that maintains a structured 256-dimensional latent world state over more than 200 episodes via a Mamba-2 backbone with an event-conditioned posterior and an 8B decoder. N-VSSM holds plot-beat F1 >= 0.84 across all horizons at 4x lower compute than the closed-frontier band. A learned Cultural Transfer Function lifts cross-language fidelity by +0.20 to +0.23 Likert points. In a within-subjects writer study (n = 12 professional authors, 240 trials), N-VSSM is preferred over Claude Opus 4.5 on long-arc consistency 71% of the time and rated +1.3 Likert points higher on controllability.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2605.16865

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection

作者:

Jiarui Liu↗Lechen Zhang↗Yongjin Yang↗Yinghui He↗Yingheng Wang↗Weihao Xuan↗Zhijing Jin↗Mona Diab↗

Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning targets from humans or external systems diverge from the model's autoregressive distribution, forcing the optimizer to imitate low-probability token sequences. To address this problem, we propose MixSD, a simple external-teacher-free method for distribution-aligned knowledge injection. Instead of training on fixed targets, MixSD constructs supervision dynamically by mixing tokens from two conditionals of the base model itself: an expert conditional that observes the injected fact in context, and a naive conditional that reflects the model's original prior. The resulting supervision sequences preserve the factual learning signal while remaining substantially closer to the base model's distribution. We evaluate MixSD on two synthetic corpora that we construct to study factual recall and arithmetic function acquisition in a controlled setting, together with established benchmarks for open-domain factual question answering and knowledge editing. Across multiple model scales and settings, MixSD consistently achieves a better memorization-retention trade-off compared to SFT and on-policy self distillation baselines, retaining up to 100% of the base model's held-out capability while maintaining near-perfect training accuracy, whereas standard SFT retains as little as 1%. We further show that MixSD produces substantially lower-NLL supervision targets under the base model and reduces harmful movement along Fisher-sensitive parameter directions. These results suggest that aligning supervision with the model's native generation distribution is a simple and effective principle for knowledge injection that mitigates catastrophic forgetting.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16059

Mojo: A Promising Tool for Scalable Financial AI Efficiency

作者:

Henry Han↗

arXiv:2606.16059v1 Announce Type: cross Abstract: For thirty years, quantitative finance has paid a costly two-language tax: models researched in Python are rewritten in C++ for production, often introducing numerical discrepancies. GPU-accelerated deep learning exacerbates this problem, as nondeterministic floating-point reductions can produce drift in long backtests, challenging regulatory reproducibility and auditability expectations. This article surveys Mojo, Modular's 2026 Python-like systems language, as a structural response for capital markets engineering. While closing the Python-to-C++ performance gap, Mojo uniquely combines native interoperability with the low-level systems control required to construct bit-exact deterministic kernels. Its MLIR compilation infrastructure further allows a single codebase to target scalar, SIMD, multicore, and GPU execution, reducing the translation bottleneck between research and production. We benchmark four core financial AI workloads: Monte Carlo option pricing, LLM sentiment inference, multi-asset backtesting, and portfolio Value at Risk. On Apple Silicon, Mojo demonstrates 20x to 180x speedups over pure Python on directly measured kernels; larger-scale GPU workload results are projections calibrated from published benchmarks. Alongside transparent performance data, we introduce mojo-deterministic, an open-source library of reproducible reduction kernels, and provide a candid assessment of the problems Mojo does and does not yet solve.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12489

Masked Neural Detection for Constrained Channel Coding in Molecular Communication

作者:

Melih \c{S}ahin↗Ozgur B. Akan↗

arXiv:2606.12489v1 Announce Type: cross Abstract: Molecular communication (MC) suffers from severe diffusion memory because molecules released for one symbol may arrive during later symbols. Neural sequence detectors, especially sliding bidirectional recurrent neural networks (SBRNNs), can substantially outperform threshold detectors in such channels. This raises a central question for MC channel coding: does a code whose advantage was established under threshold detection retain it when both coded and uncoded transmission are evaluated with neural detection? This letter answers this question for run-length-limited ISI-mitigation (RLIM) codes, a class of constrained codes previously shown to provide large BER gains in MC. Across the tested operating points, the best RLIM-SBRNN receiver beats the best uncoded receiver, chosen between threshold and SBRNN detection, in $46$ of $59$ cases, with a mean gain of $10.36\times$ over those wins. We also propose an RLIM-tailored training mask for compact SBRNN detectors, improving the unmasked RLIM-SBRNN in $227$ of $236$ comparisons with $3.267\times$ mean gain when masking is beneficial. Finally, the compact masked RLIM-SBRNN is competitive with channel-state-aware MLSE despite using no channel knowledge.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18265

Synthetic Resonance: A Framework for Growth-Oriented Human-AI Relationships

作者:

Richard A. Fabes↗

arXiv:2606.18265v1 Announce Type: cross Abstract: As human relationships with artificial intelligence systems become increasingly frequent and sustained, existing language and theory fail to accurately capture the nature of these affiliations. Common descriptors such as mutual understanding, connection, or friendship risk anthropomorphizing systems that lack subjective experience, while dominant frameworks tend to reduce AI to either a tool or a threat. In this paper, I introduce the concept of synthetic resonance as an integrative framework for understanding human-AI relationships. Synthetic resonance describes how relationships humans define as meaningful can emerge between a human and an AI system without the need to attribute shared feelings or mutual awareness. I argue that synthetic resonance is best understood as a structured, dynamic pattern of interaction that can produce a sense of relationship without the presence of a second experiencing subject. By clarifying this distinction, the concept of synthetic resonance offers a more precise way of conceptualizing human-AI relationships and highlights their potential value and ethical implications. I also call for more research that tests the processes and outcomes of synthetic resonance.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2505.03201

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

作者:

Kien Tran Duc Tuan↗Tam Nguyen Trong↗Son Nguyen Hoang↗Khoat Than↗Anh Nguyen Duc↗

arXiv:2505.03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key limitation of IG is its sensitivity to the choice of baseline (reference) images. Multi-baseline extensions such as Expected Gradients (EG) assume uniform weighting over baselines, implicitly treating all baseline images as equally informative. In high-dimensional vision models, this assumption often leads to noisy or unstable explanations. This paper proposes Weighted Integrated Gradients (WG), a principled approach that evaluates and weights baselines to enhance attribution reliability. WG introduces an unsupervised criterion for baseline suitability, enabling adaptive selection and weighting of baselines on a per-input basis. The method preserves the core axiomatic properties of IG in a generalized weighted-baseline form. Under an expected, proxy-based fitness–relevance monotonicity assumption, WG provides a probabilistic justification for assigning larger weights to more informative baselines. Experiments on commonly used image datasets and models show that WG improves over EG under our protocol, with up to 36% gains across evaluated convolutional and Transformer architectures. These gains come with additional fitness-evaluation cost, so WG should be viewed as an attribution-fidelity trade-off rather than a faster alternative to EG. By moving beyond the assumption that all baselines contribute equally, Weighted Integrated Gradients offers a clearer and more reliable approach to explaining computer-vision models, improving both understanding and practical usability in explainable AI.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13111

M\"OVE: A Holistic LLM Benchmark for the German Public Sector

作者:

Camilla Dalerci↗Thilo Michael↗Robin Schaefer↗Daniel Weinland↗

We present M\"OVE (Modelle für die \"Offentliche Verwaltung Evaluieren), a holistic benchmark for evaluating large language models (LLMs) in the context of the German public sector. While LLMs are increasingly adopted in public administration, model selection remains largely ad hoc, and existing benchmarks offer limited guidance: they are predominantly English-centric, US-centric in content, and focus exclusively on task performance. M\"OVE addresses these gaps by evaluating 39 models across two complementary dimensions. Performance criteria cover summarization, question answering, and topic extraction. Governance criteria assess hallucination tendencies, energy consumption, provider transparency, and alignment with German constitutional values and knowledge about positions by German political parties. In total, we utilize ten German-language datasets, including gold- and silverstandard datasets that we constructed to reflect public-administration domains. We employ a multi-metric evaluation strategy combining classical NLP metrics, embedding-based methods, and LLM-as-a-judge approaches. Our results show that no single model dominates across all criteria: top performers differ between tasks, and model size alone is a poor predictor of quality. We further evaluate the benchmark itself, analyzing its statistical precision, LLM judge reliability, the impact of our private datasets on model rankings, the sensitivity of our results to prompt formulation, and the validity of our energy consumption estimates. M\"OVE is designed as a living benchmark under active development; results are publicly available at https://moeve.bundesdruckerei.de/.

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.03181

Generalised simultaneous transmission of arbitrary quantum states and classical information

作者:

Nicholas Zaunders↗Timothy C. Ralph↗

arXiv:2606.03181v3 Announce Type: replace Abstract: We present a protocol which allows for arbitrary optical quantum states to simultaneously carry and transmit classical data, without sacrificing the integrity of either the quantum or classical information. Our scheme encodes classical information via displacements in the phase space prior to transmission and retrieves each classical symbol via a Gaussian continuous-variable teleportation. The original quantum state is then restored by guessing the the original displacement and performing the appropriate inverse operation. In the limit of sufficiently high classical signal and high squeezing, we show that our scheme is capable of perfectly reconstructing both the input classical signal and the input quantum state without loss of coherence. An example is given in terms of the transmission of a dual-rail Bell state.

阅读与讨论 → 访问原文 →

14.

medRxiv (Medicine) 2026-06-15 DOI: HASH:db51a01315cb5939534537486164bef2

Scalable estimation of temporal clustering in accelerometry: a kernel-independent dispersion index grounded in the Hawkes process

作者:

Zheng↗Danilevicz↗I. M↗Paw↗

Background. Self-exciting (Hawkes) point processes are a natural model for the temporal clustering of human physical activity (PA) recorded by accelerometers, yet they have seldom been used in this setting—in part because the usual maximum-likelihood fitting is challenging due to potential estimation bias and convergence failures on these data. A moment-based alternative—estimating the Hawkes branching ratio from the dispersion index, the variance-to-mean ratio of event counts—is kernel-independent and computationally trivial, but it has not been evaluated for accelerometry or adapted to the intensity-marked recordings accelerometers provide. Methods. Treating each minute above a sedentary threshold as an event, we estimated the Hawkes branching ratio $n$ by maximum likelihood and, as a kernel-independent and far cheaper alternative, from the dispersion index. We compared four dispersion-based estimators—event-count-based, intensity-mark-weighted using the mark-moment ratio, and time-of-day (TOD) adjusted variants of each—against the marked and unmarked maximum-likelihood estimates. Estimators were evaluated for mutual agreement, goodness of fit, and finite-window results in two National Health and Nutrition Examination Survey (NHANES) accelerometry cohorts (hip-worn, $n=2{,}560$; wrist-worn, $n=3{,}132$). We related the resulting temporal clustering measures to all-cause mortality using survey-weighted Cox models, adjusting for PA frequency, Peak30 (the average of the 30 highest PA values), and demographic covariates. Results. Event-count-based dispersion estimates agreed strongly with maximum-likelihood branching ratios ($rapprox0.74$ in both cohorts); the intensity-marked variant incorporating PA intensity variability agreed less well. Marked and unmarked Hawkes models yielded similar excitation and decay parameters, suggesting PA intensity added little clustering information beyond event timing. In the survival analysis, temporal clustering was associated with all-cause mortality independently of PA frequency and Peak30; the direction of association differed between the hip- and wrist-worn cohorts. Conclusions. A scalable dispersion-index estimator recovers the Hawkes branching ratio and matches maximum-likelihood estimates without requiring kernel specification or iterative optimization. It offers a practical tool for quantifying temporal clustering in accelerometry, enabling decomposition of temporal PA patterns into its exogenous initiation and endogenous persistence. Such temporal patterns carry health-relevant information beyond PA intensity and volume. Keywords: dispersion index; Hawkes process; branching ratio; temporal clustering; point process estimation; accelerometry; mortality

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2504.17070

MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems

作者:

Mohaiminul Al Nahian↗Zainab Altaweel↗David Reitano↗Sabbir Ahmed↗Shiqi Zhang↗Adnan Siraj Rakin↗

arXiv:2504.17070v3 Announce Type: replace-cross Abstract: Robots need task planning methods to achieve goals that require more than one action. Recently, large pretrained models have demonstrated impressive performance in task planning. For instance, large language models (LLMs) can generate task plans using action and goal descriptions. Despite the rapid progress of large models in robot intelligence, their security implications remain only partially understood, leaving important gaps in the exploration of potential vulnerabilities in LLM-driven robotic planning systems. To investigate such risks, in this paper, we develop MuTRAP, the first multi-trigger trojan attack specifically designed and targeted for LLM-assisted robot task planners. MuTRAP follows the standard practice of LLM usage in robotics where the backbone LLM is typically frozen and hosted in a central server limiting attacker's reach. In contrast, MuTRAP injects backdoor using a small set of task-specific parameters. In addition, we develop a trigger optimization method for selecting multiple-trigger words that are most effective for different robot applications. For instance, one can use unique trigger word "herical" to activate a specific malicious behavior, e.g., cutting hand on a kitchen robot. Through MuTRAP that demonstrates the vulnerability of current LLM-based planners, our goal is to promote the development of secured robot intelligence. Details and demos are provided in: https://mutrap.github.io/MuTRAP/

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12207

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends

作者:

Jinshan Lai↗Jianwei Hu↗Baoyang Jiang↗Fengchun Zhang↗Leyuan Wang↗Haotian Li↗Yida Wang↗Tingxuan Huang↗Xi Ren↗Qiang Ma↗

arXiv:2606.12207v1 Announce Type: cross Abstract: Embodied intelligence now spans navigation, household assistance, manipulation, autonomous driving, aerial agents, and multimodal large-model control. This expansion has made benchmark construction a central bottleneck for reliable evaluation. Unlike static datasets, embodied benchmarks combine task specifications, environments, robot data, demonstrations, annotations, metrics, evaluation scripts, and release policies into a single evaluation system. This survey reviews the literature through a five-stage construction pipeline: requirement and task construction, data acquisition, data cleaning and annotation, benchmark suite generation and metric definition, and evaluation execution with diagnostic feedback. For each stage, the survey analyzes the transition from manual curation to traditional automation, foundation-model assistance, and agentic closed-loop workflows. It also compares qualitative construction costs across human labor, data and asset acquisition, compute and simulation, validation and debugging, governance and maintenance, and rework risk. The main conclusion is that automation does not simply reduce benchmark cost. Instead, it often shifts cost toward validation, auditability, version control, and long-term governance. Progress in embodied evaluation will therefore depend not only on larger benchmark suites, but also on construction pipelines that are diagnosable, auditable, and responsibly refreshable.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2509.07605

Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniques

作者:

Ali Nawaz↗Amir Ahmad↗Shehroz S. Khan↗

arXiv:2509.07605v2 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored rebalancing techniques to address this issue, less attention has been given to evaluating the performance of binary classifiers under imbalance when no such techniques are applied. Therefore, the goal of this study is to assess the performance of binary classifiers "as-is", without performing any explicit rebalancing. Specifically, we systematically evaluate the robustness of a diverse set of binary classifiers across both real-world and synthetic datasets, under progressively reduced minority class sizes, using one-shot and few-shot scenarios as baselines. Our approach also explores varying data complexities through synthetic decision boundary generation to simulate real-world conditions. In addition to standard classifiers, we include experiments using undersampling, oversampling strategies, and one-class classification (OCC) methods to examine their behavior under severe imbalance. The results confirm that classification becomes more difficult as data complexity increases and the minority class size decreases. While traditional classifiers deteriorate under extreme imbalance, advanced models like TabPFN and boosting-based ensembles retain relatively higher performance and better generalization compared to traditional classifiers. Visual interpretability and evaluation metrics further validate these findings. Our work offers valuable guidance on model selection for imbalanced learning, providing insights into classifier robustness without dependence on explicit rebalancing techniques.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19256

X+Slides: Benchmarking Audience-Conditioned Slide Generation

作者:

Haodong Chen↗Xuanhe Zhou↗Wei Zhou↗Xinyue Shao↗Yanbing Zhu↗Bo Wang↗Jiawei Hong↗Anya Jia↗Fan Wu↗

arXiv:2606.19256v1 Announce Type: new Abstract: Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and technical depth, while overlooking the target audience as a critical real-world factor. For instance, specialists demand rigorous proofs, whereas decision-makers prioritize actionable conclusions. To bridge this gap, we introduce X+Slides, a benchmark specifically designed for audience-conditioned slide generation. Built on a diverse corpus spanning 113 topics and seven presentation scenes, X+Slides employs a dynamic evaluation framework constructed from 8,133 deduplicated, source-grounded probes. By assigning audience-specific utility weights to the same source-grounded probes, X+Slides reports four complementary metrics: Audience Coverage measures how much audience-essential information is conveyed, Domain-wise Coverage shows which information types are covered, Efficiency measures delivered utility per unit of attention cost, and Correctness verifies whether slide claims are supported by the source. Experiments on DeepPresenter, SlideTailor, and NotebookLM show that current systems can recover a substantial but still incomplete part of audience-essential information: at $\tau_A=0.7$, DeepPresenter reaches a best Audience Coverage of 0.714, SlideTailor reaches 0.594, and the NotebookLM ablation reaches 0.853 while showing clear grounding differences. These results indicate that visual quality and broad topic coverage should not be treated as evidence support without source-grounded evaluation.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2509.03647

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

作者:

Dani Roytburg↗Matthew Bozoukov↗Matthew Nguyen↗Jou Barzdukas↗Simon Fu↗Narmeen Oozeer↗

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in evaluation pipelines, particularly for tasks like preference tuning and model routing. We investigate whether lightweight steering vectors can mitigate this problem at inference time without retraining. We introduce a curated dataset that distinguishes self-preference bias into justified examples of self-preference and unjustified examples of self-preference, and we construct steering vectors using two methods: Contrastive Activation Addition (CAA) and an optimization-based approach. Our results show that steering vectors can reduce unjustified self-preference bias by up to 97\%, substantially outperforming prompting and direct preference optimization baselines. Yet steering vectors are unstable on legitimate self-preference and unbiased agreement, implying self-preference spans multiple or nonlinear directions. This underscores both their promise and limits as safeguards for LLM-as-judges and motivates more robust interventions.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-24 DOI: arXiv:2605.15062

Training-Time Optical Priors for Wireless Capsule Endoscopy Classification: Hemoglobin-Aware Input Fusion with Cross-Vendor Evaluation

作者:

Chengshuai Yang↗Lei Xing↗Keyaan Zawad Alam↗Gregory Entin↗Roopa Vemulapalli↗Lisa Casey↗Raiyan Tripti Zaman↗

Background. RGB-trained classifiers for wireless capsule endoscopy (WCE) conflate hemoglobin contrast with bile staining and illumination falloff, limiting sensitivity to small-vessel vascular findings such as Lymphangiectasia. We introduce a physics-informed framework that injects an analytic, Monte-Carlo-inspired hemoglobin prior into a standard classifier purely at training time – to our knowledge the first use of an explicit optical light-transport prior in WCE classification. Methods. On Kvasir-Capsule (47,238 frames, 43 patients, 11 evaluable classes; patient-disjoint split) we test, across 6 seeds against an RGB-only EfficientNet-B0 baseline: (i) a 5-channel input-fusion variant feeding the prior P_blood alongside RGB; (ii) a distillation variant that runs on plain 3-channel RGB at inference; and (iii) a three-stream extension adding a temporal Transformer and an autoencoder-residual stream. We replicate across ResNet-18 and ConvNeXt-Tiny and report cross-vendor zero-shot transfer on the public Galar cohort. Results. Input fusion lifts cross-seed macro-AUC 0.760 -> 0.783 (5/6 seeds positive); distillation reaches 0.773; the three-stream model reaches 0.804 (+0.044 over baseline, paired DeLong p < 1e-4). Lymphangiectasia AUC rises 0.238 -> 0.337, sign-consistent across all 6 seeds. A four-variant ablation reveals a parameterization-mechanism boundary: only the spatial-channel form lifts. Cross-vendor zero-shot on Galar retains ~60% of the ConvNeXt-Tiny lift.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2508.17742

EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models

作者:

Wei Xiong↗Jiangtong Li↗Jie Li↗Kun Zhu↗Changjun Jiang↗

arXiv:2508.17742v3 Announce Type: replace-cross Abstract: Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress. Current evaluations rely on inconsistent protocols that render cross-model comparisons unreliable, while a lack of diagnostic analyses obscures the internal mechanisms driving transfer efficiency and scaling behaviors. To address this, we introduce EEG-FM-Bench, a unified system for the standardized evaluation of EEG-FMs. The benchmark integrates 14 datasets across 10 paradigms and incorporates diverse experimental settings, including multiple fine-tuning strategies, task organizations, and classifier configurations, supported by tools for gradient and representation analysis. Our experiments and analysis reveal several critical insights: (1) multi-task learning often acts as a useful regularizer that mitigates overfitting in data-scarce EEG contexts, although negative transfer can arise under specific task paradigms; (2) pre-training efficiency is currently limited by gradient conflicts between reconstruction objectives and downstream tasks; (3) under released checkpoints and a matched downstream protocol, model or data scale alone does not fully explain transfer performance, while objective alignment, adaptation compatibility, and EEG-specific design appear to be important factors. This benchmark enables fair comparison and reproducible analysis, providing a step toward fairer comparison and more interpretable analysis of EEG-FMs. Code is available at https://github.com/xw1216/EEG-FM-Bench.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16811

Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier

作者:

Keizo Kato↗Chenhui Chu↗Yugo Murawaki↗Sado Kurohashi↗

For the development of Large language models (LLMs), recent approaches to generating pseudo intermediate reasoning have shown remarkable progress. But they typically rely on large numbers of correctly annotated answers to assess reasoning quality. This paper presents a semi-supervised framework that scales reasoning learning from minimal supervision, turning reasoning verification itself into a data creation mechanism. We train a lightweight reasoning-correctness classifier on only a few labeled samples, which judges whether intermediate reasoning traces generated by an LLM are valid. Furthermore, an entropy-based confidence threshold filters out unreliable samples, and the remaining high-confidence reasoning traces are used to fine-tune the model. Experiments on Verifiable Math Problems (Orca-Math subset) and Question Answering on Image Scene Graphs (GQA) with Visual Programming show that our method achieves accuracy comparable to using 10-15x more labeled data. Ablation analyses confirm that both the classifier and entropy filtering are essential for scalable and noise-resistant pseudo-labeling. By replacing expensive answer-level supervision with lightweight reasoning verification, our method provides a practical path toward constructing large-scale reasoning resources and paves the way for future autonomous reasoning systems that learn from minimal human input.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17507

LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline

作者:

Xiwei Xu↗Chen Wang↗Jacky Jiang↗Phil Yang↗Qian Fu↗Mohan Dhall↗Wenjie Zhang↗Liming Zhu↗

arXiv:2606.17507v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground model outputs in authorised curriculum artefacts and marking guidelines issued by education authorities. This paper presents a curriculum-grounded, configurable LLM-as-Judge pipeline for question-level marking, co-developed with an industrial partner, to support exam preparation for university admission. The pipeline identifies the relevant topics, subtopics, and cognitive demand of a question, and assembles verifiable and authorised context to support LLM judgement. Curriculum intent is operationalised through concrete syllabus artefacts, including prescribed verbs and outcomes, performance band descriptors, glossary definitions, and marking-guideline principles. A staged LLM workflow is employed to first generate question-specific rubrics, capturing structured expectations of performance, and then derive and evaluate marking criteria used to allocate marks to student responses. This design improves consistency, transparency, and alignment with official marking practices. Preliminary evaluation shows that the proposed LLM-as-Judge pipeline delivers marking outcomes comparable to human tutors, while yielding justifications that are more traceable to authorised curriculum artefacts and marking standards. The pipeline has also been integrated into an online study platform, where early deployment data provide initial insights into operational usage and manual overrides.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.00924

StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer

作者:

Guantian Zheng↗

arXiv:2605.00924v2 Announce Type: replace-cross Abstract: AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rests on a fundamental paradox: as language models are trained on human-written corpora, the statistical boundary between AI and human writing will inevitably dissolve as models improve. Commercial incentives have further distorted this landscape – detection services and "de-AIification" tools often operate within the same supply chain, replacing evaluation of content quality with judgment of content origin. We present StyleShield, the first flow matching framework for conditional text style transfer, operating directly in continuous token embedding space via a DiT backbone with zero-initialized cross-attention adapters conditioned on frozen Qwen-7B representations. At inference, we adapt the SDEdit paradigm from image synthesis to text embeddings, with a single parameter gamma providing smooth continuous control over the evasion-preservation trade-off. On a multi-domain Chinese benchmark, StyleShield achieves 94.6% evasion against the training detector and >=99% against three unseen detectors, maintaining 0.928 semantic similarity. We further introduce RateAudit, a document-level scheduling algorithm that demonstrates detection-rate verdicts can be set to arbitrary values, directly questioning the reliability of score-based evaluation.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17420

Feynman Kac Reweighted Schrödinger Bridge Matching for Surface-Based Tau PET Harmonization

作者:

Jianwei Zhang↗Xinyu Nie↗Jiaxin Yue↗Yonggang Shi↗

arXiv:2606.17420v1 Announce Type: cross Abstract: Tau PET imaging is central to tracking Alzheimer's disease progression, but systematic differences between scanners, protocols, and radiotracers across sites introduce nonbiological variability that inflates biomarker variance, reduces sensitivity to disease effects, and can bias downstream clinical assessments. Harmonization methods aim to remove these site-induced shifts while preserving biologically meaningful signal, yet existing approaches struggle when source and target cohorts differ in subgroup composition, risking conflation of site effects with biological variation such as tau-positivity status. We propose the Feynman Kac Reweighted Schröodinger Bridge Matching (FKRSBM) model to address this problem. Rather than routing data through a Gaussian noise prior as in diffusion-based methods, FKRSBM learns a direct stochastic transport process between source and target distributions via entropy-regularized optimal transport. To enforce biologically consistent transport, FKRSBM incorporates a subgroup-aware endpoint proposal derived from a Feynman Kac reweighting of the reference bridge measure, implemented entirely through stratified importance sampling at the data level and requiring no changes to the underlying bridge-matching solver or network architecture. For surface-based neuroimaging, FKRSBM employs a spherical convolutional backbone operating on cortical meshes to perform vertex-level harmonization. We evaluate the method on tau PET SUVR maps, harmonizing PI-2620 data from the HABS-HD cohort into the AV-1451 domain of ADNI. Compared against ComBat, CycleGAN, a diffusion-based method (DF), and unregularized Diffusion Schröodinger Bridge Matching (DSBM), FKRSBM achieves superior distributional alignment, reduced tau-positivity sign mismatch, stronger APOE subgroup alignment, and improved downstream disease classification performance.

阅读与讨论 → 访问原文 →