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 (CS.LG) 2026-06-11

Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift

arXiv:2602.14913v2 Announce Type: replace Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to counter this performance loss under a bounded label-conditional covariate shift model. Using tools from domain adaptation, we derive a lower bound on target coverage in terms of the source-domain loss of the classifier and a Wasserstein measure of the shift. Using this result, we provide a method to design pseudo-calibrated sets that inflate the conformal threshold by a slack parameter to keep target coverage above a prescribed level. Finally, we propose a source-tuned pseudo-calibration algorithm that interpolates between hard pseudo-labels and randomized labels as a function of classifier uncertainty. Numerical experiments show that our bounds qualitatively track pseudo-calibration behavior and that the source-tuned scheme mitigates coverage degradation under distribution shift while maintaining nontrivial prediction set sizes.

02.
arXiv (CS.CL) 2026-06-15

CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

03.
arXiv (CS.CL) 2026-06-16

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple summaries while verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical question answering, existing benchmarks do not sufficiently reflect this setting: they often evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. The benchmark is constructed through an expert-informed pipeline combining discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation, followed by review and revision of every single QA sample by 11 medical experts. Benchmarking 22 open- and closed-source LLMs reveals several challenges, including that LLMs struggle more with evidence grounding than content answering, multi-turn errors compound across turns, and single-turn clinical QA performance does not reliably transfer to this setting. These findings establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems. The dataset will be made publicly available through PhysioNet credentialed access.

04.
arXiv (quant-ph) 2026-06-11

Coupled integrated photonic quantum memristors using a single photon source made of a colour center

arXiv:2602.14736v2 Announce Type: replace Abstract: Photonic quantum memristors provide a measurement-induced route to nonlinear and history-dependent quantum dynamics. Experimental demonstrations have so far focused on isolated devices or simple cascaded devices configurations. Here, we experimentally realize and characterize a network of two coupled photonic quantum memristors with crossed feedback, implemented on a silicon nitride photonic integrated circuit and fed by a room-temperature single-photon source based on a silicon-vacancy color center SiV$^-$ in a nanodiamond. Each memristor consists of an integrated Mach-Zehnder interferometer whose transfer function is adaptively updated by photon detection events on another memristor, thus generating novel non-Markovian input-output dynamics with an enhanced memristive behaviour compared to single devices. In particular, we report inter-memristor input-output hysteresis curves exhibiting larger form factors and displaying self-intersecting loops, respectively revealing marked bistability and self-intersecting hysteresis geometry. Furthermore, numerical simulations show how these features emerge from the interplay between memory depth and relative input phase, for both intra- and inter-memristor input-output relations. We experimentally test the performance of our system in the NARMA task. Our results establish coupled integrated photonic quantum memristors as scalable nonlinear building blocks and highlight their potential for implementing compact quantum neuromorphic and reservoir computing architectures.

05.
arXiv (CS.AI) 2026-06-19

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

arXiv:2606.20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and ``Flat'' RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

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

Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking

Most advances in human mesh recovery (HMR) have focused on pelvis-centered recovery, overlooking metric 3D localization and detection accuracy in the camera coordinate system - two key factors for real-world applications such as human-robot interaction and social scene understanding. Current evaluation protocols often ignore these aspects, emphasizing per-person, root-centered recovery rather than camera-space perception. As a result, existing approaches rely on fixed camera assumptions or handcrafted post-processing, limiting their robustness and practical deployment. We introduce Multi-HMR 2, a simple yet robust DETR-based framework for Multi-person Camera-centric Human detection, mesh Recovery, and tracking. Multi-HMR 2 predicts a scene-consistent camera together with human meshes, enabling metric 3D localization without ground-truth intrinsics. Moreover, by distilling image-based memory features from SAM2, Multi-HMR 2 extends to tracking, achieving consistent identity association without video supervision. Despite its conceptual simplicity - no handcrafted components, no video input, and no ground-truth cameras - Multi-HMR 2 achieves state-of-the-art pelvis-centered performance while substantially improving detection accuracy and metric 3D localization.

07.
medRxiv (Medicine) 2026-06-10

Towards the Virtual Amyotrophic Lateral Sclerosis Patient: Inferring Cortical Excitability through Whole-Brain Dynamical Modeling

Amyotrophic lateral sclerosis (ALS) is increasingly recognized as a multisystem neurodegenerative disorder in which motor-neuron degeneration is accompanied by widespread alterations in cortical dynamics. Among its most reproducible neurophysiological signatures is cortical hyperexcitability, yet how this local excitability imbalance shapes distributed whole-brain activity remains poorly understood. Here, we combined source-reconstructed resting-state MEG data, tractography-informed whole-brain modeling, and simulation-based inference to investigate whether ALS-related alterations in large-scale brain dynamics can be mechanistically explained by changes in cortical excitability. First, we characterized empirical brain dynamics using complementary features spanning regional activity amplitude and variability, functional connectivity, and avalanche-based metrics. These analyses revealed significant alterations in ALS patients relative to healthy controls, as well as associations with clinical impairment and disease staging. To mechanistically interpret these changes, we employed a reduced Wong-Wang whole-brain model in which local recurrent excitation modulates emergent large-scale neural dynamics. Simulations showed that increasing excitability systematically reproduced the empirical dynamical signatures observed in ALS. We then applied a simulation-based inference framework to estimate latent excitability parameters directly from empirical observations. Whole-brain model inversion revealed increased excitability in ALS patients compared with controls. The recovered excitability parameter was associated with disease staging, supporting its clinical relevance as a model-derived descriptor of ALS progression. Finally, by extending the model to estimate frontal and non-frontal excitability separately, we found that ALS-related alterations were predominantly associated with increased frontal excitability, whereas non-frontal regions appeared comparatively less affected. The recovered parameters related to disease staging. Together, these findings provide a mechanistic framework linking altered large-scale brain dynamics in ALS to selective cortical hyperexcitability, explaining how local excitability changes can give rise to global network reorganization. More broadly, they show how computational model inversion can recover latent multiscale pathophysiological processes from empirical neural recordings, offering a non-perturbative alternative to complex experimental paradigms typically required to causally probe local-to-global mechanisms.

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

MLaGA: Multimodal Large Language and Graph Assistant

arXiv:2506.02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis. Prevailing LLM-based graph methods excel in adapting LLMs to text-rich graphs, wherein node attributes are text descriptions. However, their applications to multimodal graphs–where nodes are associated with diverse attribute types, such as texts and images–remain underexplored, despite their ubiquity in real-world scenarios. To bridge the gap, we introduce the Multimodal Large Language and Graph Assistant (MLaGA), an innovative model that adeptly extends LLM capabilities to facilitate reasoning over complex graph structures and multimodal attributes. We first design a structure-aware multimodal encoder to align textual and visual attributes within a unified space through a joint graph pre-training objective. Subsequently, we implement a multimodal instruction-tuning approach to seamlessly integrate multimodal features and graph structures into the LLM through lightweight projectors. Extensive experiments across multiple datasets demonstrate the effectiveness of MLaGA compared to leading baseline methods, achieving superior performance in diverse graph learning tasks under both supervised and transfer learning scenarios.

09.
arXiv (CS.CL) 2026-06-16

Scaling Human and G2P Supervision for Robust Phonetic Transcription

Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech. A common alternative is using Grapheme-to-Phoneme (G2P) models to auto-generate phonetic labels from text transcripts at scale. We study how automatic phonetic transcription performance scales with human and G2P supervision in English. Using a curated 80-hour benchmark spanning native, non-native and post-stroke speech, we identify a supervision quality threshold: G2P supervision helps only when fewer than 20-30 hours of human annotation are available. Beyond this threshold, it provides no significant benefit and can reduce cross-dialect robustness. What is effective after this threshold is ASR pretraining which we use to achieve a 2.3x reduction in weighted phone feature error rate over prior systems, with strong gains on non-native and aphasic speech. These results suggest that quantity-driven G2P scaling may yield diminishing returns for robust generalization.

10.
bioRxiv (Bioinfo) 2026-06-18

Robust Conditional Diffusion with Noisy Templates for Antibody Sequence-Structure Design

Antibodies specifically recognize antigens and play a central role in therapeutic discovery. Designing antibodies for a given antigen remains challenging because antigen-antibody complex data are limited, whereas the sequence and conformational spaces of complementarity-determining regions (CDRs) are large. Retrieved CDR templates from databases or candidate libraries can narrow the design space and improve controllability, but retrieval for novel antigens is often sparse and imperfect; treating retrieved templates as hard conditions can bias the denoising process and cause negative transfer. To address this problem, we propose Robust Conditional Diffusion with Noisy Templates for antibody sequence-structure design (NT-ABDiff), a joint diffusion framework that treats candidate CDR-only templates as optional and potentially unreliable conditions. NT-ABDiff uses reliability-aware template modulation to estimate the context-conditioned usefulness of each candidate and to adaptively reweight and fuse multiple templates during conditioning. We further train the model with mixed-quality and corrupted templates as conditional perturbation regularization, encouraging the denoiser to exploit informative templates while remaining stable when templates are uninformative. Experiments under controlled template shifts and a train-set retrieval evaluation show that NT-ABDiff improves CDR-H3 sequence recovery and structural accuracy over strong baselines, while retaining robustness to missing, mismatched, and corrupted templates. Under a stringent random-template CDR-H3 evaluation, NT-ABDiff improves amino-acid recovery (AAR) from 30.03% to 39.47% and reduces RMSD from 3.160 to 2.915A; with train-set retrieval candidates, it achieves 39.50% AAR and 2.76 {ring} A RMSD. Code, processed splits, {ring} configuration files, and evaluation scripts are available at https://github.com/ShiDeng7rz/NT-ABDiff.

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

Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents (Extended Revision: From Behavioral Architecture to Epistemic Accountability)

作者:

arXiv:2510.05107v5 Announce Type: replace Abstract: The central challenge for AI agents is not only performance but accountability. Agents that act through opaque prompt sequences may produce correct outputs, but they provide little basis for verifying why an action was permitted, where an error occurred, or how responsibility should be assigned. This paper presents the Structured Cognitive Loop as an architecture for accountable behavior in large language model agents. SCL separates cognition, memory, control, and action into distinct modules. The language model proposes. External memory preserves verified state. A lightweight controller checks preconditions, prevents redundant actions, and authorizes execution before tools are used. We evaluate SCL against ReAct and common LangChain agent variants across travel planning, conditional email drafting, and constraint guided image generation. Across 360 episodes, SCL achieves 86.3 percent task success compared with 70.5 to 76.8 percent for prompt based baselines. It also improves goal fidelity, reduces redundant tool calls, increases reuse of intermediate state, and lowers unsupported assertions. This extended revision situates SCL within a broader architecture of epistemic accountability. Subsequent extensions integrate context aware Human in the Loop control, Pool Gated Retrieval, and the Horizon Warrant Commitment framework. Together these components define an agent architecture in which the model proposes, structure decides, evidence is warranted before use, and human judgment is embedded in the trace rather than imposed after the fact. The result is a foundation for AI agents whose decisions are not only effective but also authorized, inspectable, and accountable.

12.
arXiv (CS.AI) 2026-06-15

FPGA-Based Neural Network Accelerators for Space Applications: A Survey

arXiv:2504.16173v3 Announce Type: replace-cross Abstract: Space missions are becoming increasingly ambitious, necessitating high-performance onboard spacecraft computing systems. In response, field-programmable gate arrays (FPGAs) have garnered significant interest due to their flexibility, cost-effectiveness, and radiation tolerance potential. Concurrently, neural networks (NNs) are being recognized for their capability to execute space mission tasks such as autonomous operations, sensor data analysis, and data compression. This survey serves as a valuable resource for researchers aiming to implement FPGA-based NN accelerators in space applications. By analyzing existing literature, identifying trends and gaps, and proposing future research directions, this work highlights the potential of these accelerators to enhance onboard computing systems.

13.
arXiv (math.PR) 2026-06-16

Logarithmic Large Deviations for Heavy-Tailed Sums

arXiv:2606.16487v1 Announce Type: new Abstract: We establish logarithmic large-deviation bounds for sums of independent nonnegative random variables with regularly varying tails. The normalization is chosen at the extreme-value scale and the speed is $\log n$. In contrast with Cramér's theorem, the resulting rate function is determined only by the tail index. The proof transfers a maximum large-deviation principle to sums in the one-big-jump region.

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

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects. Building on this dataset, we design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability. Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning. Experiments demonstrate that these exceed the performance of methods without alignment and align with whole-object images.

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

LLM Judges Have Dark Current: A Psychometric Datasheet for LLM-as-a-Judge Evaluation

LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce. Yet these judges are often reported as scalar accuracy, win-rate, or agreement devices. We argue that a judge should instead be reported as a measurement instrument. We introduce a Judge Datasheet protocol that measures dark current under true-vacuum inputs, stable cross-sensitivity to same-quality surface variation, positional false preference, target sensitivity on a controlled quality ladder, and the criterion or operating point induced by tie instructions. The direction-stability decomposition reveals that apparent Delta0 preference can be stable surface response or disguised position bias. In a three-judge open-weight case study, Llama-3.1-8B shows high dark current and presentation-conflicted Delta0 behavior, Qwen2.5-14B is vacuum-clean and target-sensitive but mixes stable and positional over-discrimination, and Qwen2.5-32B is vacuum-clean with low stable cross-sensitivity and low positional false preference. A strict tie criterion eliminates Qwen32B Delta0 false preference but absorbs marginal Delta1 target signals into ties while preserving Delta5 sensitivity. The results show that prompting moves the criterion, not the resolution. We do not claim that the downstream mechanism hypothesis that motivated this work is confirmed; the contribution is a metrological protocol for measuring the measuring device before downstream claims are made.

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

DeceptionX: Explainable Deception Detection with Multimodal Large Language Models

Deception detection is a critical and highly challenging task within affective computing and behavioral analysis. Existing deep learning methods typically treat this task as a straightforward classification problem; however, this black-box approach lacks interpretability and fails to capture the complex logical deduction processes utilized by human experts when identifying lies. While Multimodal Large Language Models (MLLMs) have shown potential, applying them effectively requires a bridge between low-level audiovisual cues and high-level logical reasoning. In this paper, we propose DeceptionX, a novel MLLM framework that shifts the paradigm of deception detection from black-box classification to an interpretable Observe-Think-Summarize reasoning process. To address the scarcity of high-quality reasoning data, we first constructed DeceptChain, a high-quality dataset developed through a human-in-the-loop process. This dataset synthesizes fine-grained visual and auditory evidence (such as micro-expressions and vocal tremors) into structured chain-of-thought reasoning data. Furthermore, we propose a three-stage training pipeline and a Discrepancy-Aware Redundancy Elimination~(DARE) strategy for DeceptionX to further enhance the model's generalization capabilities. Extensive experiments demonstrate that DeceptionX not only outperforms existing MLLM baselines and state-of-the-art methods on standard real-world benchmarks but also provides transparent, expert-level reasoning paths, bridging the critical gap between accuracy and interpretability in multimodal deception detection.

17.
PLOS Medicine 2026-05-06

Point-of-care early infant HIV diagnosis at birth in a pragmatic cluster-randomized trial in Mozambique and Tanzania: A comparative cost and cost-effectiveness study

by Kira Elsbernd, Issa Sabi, Ilesh V. Jani, Chishamiso Mudenyanga, Siriel Boniface, Arlete Mahumane, Joaquim Lequechane, Falume Chale, Bindiya Meggi, Kassia Pereira, Raphael Edom, Anange F. Lwilla, W. Chris Buck, Nyanda Elias Ntinyinya, Michael Hoelscher, Till Baernighausen, Arne Kroidl, Stefan Kohler, the LIFE Study Consortium Background Timely access to early infant diagnosis (EID) is crucial for newborns with HIV, as late diagnosis can delay lifesaving antiretroviral treatment (ART). We assessed the comparative cost and cost-effectiveness of integrating point-of-care EID at birth into routine care in primary healthcare settings. Methods and findings This pre-specified secondary analysis was nested in the cluster-randomized LIFE study conducted at 28 primary healthcare facilities in Mozambique and Tanzania from October 2019 to September 2021. We estimated the health system cost of point-of-care birth plus 4–8-week HIV testing (very early infant diagnosis; VEID) compared to standard-of-care (SoC) testing at 4–8 weeks only, both with immediate ART initiation. We assessed the cost-effectiveness of VEID relative to SoC with respect to ART initiation within one week of life using Bayesian hierarchical models. As this is an intermediate outcome, incremental cost-effectiveness ratios (ICERs) cannot be directly compared to available life-year-based cost-effectiveness thresholds. To contextualize results, we derived the minimum life-years gained per early ART initiation required for VEID to meet standard thresholds in a break-even analysis.VEID was associated with a higher cost and resulted in earlier ART initiation than SoC in both countries. In Mozambique, VEID increased the proportion of infants initiating ART within one week of life by 90.0 (95% CrI [67.5, 98.5]) percentage points at an incremental cost of $2,632 (95% CrI [$2,249, $3,062]) per infant with HIV. In Tanzania, VEID increased early ART initiation by 59.9 (95% CrI [20.9, 89.5]) percentage points at an incremental cost of $6,263 (95% CrI [$5,394, $7,243]) per infant with HIV. The ICER was $2,924 and $10,458 in Mozambique and Tanzania, respectively and was sensitive to intrauterine transmission rate. These findings were limited by the lack of long-term health outcome data and reliance on an intermediate outcome. Based on the break-even analysis, we estimated that VEID would need to yield 6–32 life-years gained per additional early ART initiation to meet standard thresholds. Conclusions Adding birth testing improved early ART initiation but was unlikely to be cost-effective relative to standard thresholds given current prices, vertical transmission rates, and knowledge of long-term health benefits. Cost-effectiveness could be achieved at current costs if early ART translates to substantial long-term health benefits or if targeted to infants at high risk of vertical transmission.

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

Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models

Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats. A practical middle ground keeps paper-based, problem-oriented tasks but records the assessment-relevant answers as single capital letters in a table that a machine can read. The open question is whether this reading can be made accurate and, above all, fair enough for unsupervised grading. Earlier automated approaches reached only about 88%–91% recognition – too low – and failed on the cases that matter most: answers placed outside the cell, crossed out, or written in cursive. We show that general-purpose vision-language foundation models (VLMs), which interpret the page rather than match pixel templates, close this gap. On a benchmark of 61 anonymised exams (3141 answer positions) the best model reaches 98.4% accuracy, well above the previous baseline. Crucially, we centre the evaluation on fairness: we distinguish false negatives (a correct answer marked wrong, which disadvantages the student) from false positives, and a lightweight prompt that supplies the reference solution as context lowers the false-negative rate to 0.58%. Under an exemplary grading scheme only three of the 61 exams would be graded worse, all caught by a student self-review step. Fully automated, fairness-aware exam grading at scale is therefore defensible; we release the anonymised benchmark to support reproducibility.

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

Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming

arXiv:2606.12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code – a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submissions on the Universal Online Judge (UOJ) and evaluated through UOJ's native judging infrastructure. Our results show that under one-shot evaluation, even the strongest models fail to identify errors in more than 50% of a set of submissions that have been found to be incorrect by UOJ users. While test-time scaling improves success rates to above 90%, the substantial computational costs incurred from model inference limit its practicality for large-scale deployment. Despite these limitations, we find that the best-performing models under test-time scaling can uncover errors in over 5% of full-score submissions across roughly 30 problems, suggesting that frontier LLMs can already provide complementary signals beyond standard judging systems.

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

XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment

Personalized image aesthetic assessment (PIAA) seeks to model, at the individual level, the subjective nature of aesthetic judgments toward artworks and photographs. Aesthetic preference is known to be both deeply personal and partially consistent across visual domains. Yet existing PIAA datasets and methods are largely confined to a single domain, or provide too few samples per annotator within each domain to enable personalization across domains. Consequently, the cross-domain generalization of personalized aesthetic preferences remains largely unexplored. To address this gap, we introduce XPASS-Vis, the first dataset explicitly designed for cross-domain PIAA. XPASS-Vis comprises 6,526 stimuli from three visual domains – art, fashion, and landscape – rated by 129 annotators, yielding 87,836 user-stimulus interactions, each annotated with an overall aesthetic score and nine aesthetic-emotion ratings. Notably, each annotator rated more than 200 stimuli per domain, providing sufficient per-domain coverage to support personalization both within and across domains. Moreover, we establish baseline models for cross-domain PIAA under unsupervised domain adaptation (UDA), where a model trained on a labeled source domain is transferred to an unlabeled target domain. A systematic evaluation of representative UDA approaches shows that the best-performing method recovers approximately 60\% (Spearman's $\rho$ = .28) of the supervised upper bound under a fully unsupervised setting. This provides encouraging evidence that personalized aesthetic preferences are, to a meaningful extent, transferable across visual domains. At the same time, a substantial gap remains, highlighting the need for PIAA-specific adaptation strategies. XPASS-Vis and the accompanying baselines provide a foundation for future research on cross-domain PIAA. All datasets and code will be made publicly available upon acceptance.

21.
arXiv (CS.LG) 2026-06-18

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials

arXiv:2602.14789v2 Announce Type: replace Abstract: The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms. For example, stable solutions of gradient descent (GD) correspond to flat minima, which have been associated with favorable features. While prior work often relies on linearization to determine stability, it remains unclear whether linearized dynamics faithfully capture the full nonlinear behavior. Recent work has shown that GD may stably oscillate near a linearly unstable minimum and still converge once the step size decays, indicating that linear analysis can be misleading. In this work, we explicitly study the effect of nonlinear terms. Specifically, we derive an exact criterion for stable oscillations of GD near minima in the multivariate setting. Our condition depends on high-order derivatives, generalizing existing results. Extending the analysis to stochastic gradient descent (SGD), we show that nonlinear dynamics can diverge in expectation even if a single batch is unstable. This implies that stability can be dictated by a single batch that oscillates unstably, rather than an average effect, as linear analysis suggests. Finally, we prove that if all batches are linearly stable, the nonlinear dynamics of SGD are stable in expectation.

22.
arXiv (CS.AI) 2026-06-18

Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models

arXiv:2606.18324v1 Announce Type: cross Abstract: SWave is a complex-valued recurrent language model (169.26M parameters, D=384, L=16, T=2048) trained on FineWeb-Edu using 2xH100 NVL. It was designed around three founding premises: that representing language as complex waves rather than real-valued numbers enables richer information encoding; that a Cayley-parameterised unitary transition provides a mathematical guarantee against state decay or explosion; and that a hidden state which rotates rather than shrinks preserves signal integrity over arbitrarily long contexts. The core of SWave evolved substantially across three development phases. The Resonance Head was found to structurally admit imaginary-channel collapse as a global loss minimum (a failure mode we term cos-domination collapse) and was superseded by an untied head with independent real and imaginary embedding tables from the Phase-Associative Memory (PAM) architecture. This resolved the degenerate minimum and enabled stable 200,000-step training (best-step PPL 22.0 at step 89,861). ComplexNorm and the Wave Propagation Scan proved load-bearing throughout all three phases and were retained to the final architecture. ProtectGatedScan was reframed as a structural prior rather than a learned behaviour. The four multi-scale retention concepts showed no measurable improvement under controlled evaluation and were found non-load-bearing. The ComplexGatedUnit was superseded by a real-valued squared-ReLU channel mixer with fewer parameters. The auxiliary training objectives showed no benefit once structural constraints were resolved. The investigation yields a formal characterisation of cos-domination collapse, a parallel scan with a log-space backward pass for numerical stability, six transferable engineering principles for complex-valued recurrent training, and a plan-to-code traceability methodology for catching structural divergences that conventional test suites miss.

23.
arXiv (CS.CV) 2026-06-15

Visual Quality Score Assessment of Large White Goods in Remanufacture with Multi-View Deformable-DETR

Remanufacturing large white goods is essential for a circular economy, yet visual quality assessment remains a manual bottleneck for training and pricing. Conventional detection methods require extensive annotation and struggle with small defects in high-resolution multi-view data. We present a multi-view framework based on Deformable-DETR for automated quality scoring that aggregates information across redundant views to extract fine-grained features. To enhance robustness with limited labels, we employ self-supervised pretraining followed by supervised fine-tuning on expert-annotated scores. Additionally, a linear projection over frozen feature maps identifies regions of interest to explain model decisions. Evaluated on an industrial multi-view dataset, our approach delivers precise quality assessments while reducing reliance on manual annotation and per-part customization, enabling scalable and transparent inspection for remanufacturing lines.

24.
arXiv (math.PR) 2026-06-16

A small noise approximation for Muller's Ratchet

arXiv:2606.15842v1 Announce Type: new Abstract: We consider an infinite system of SDEs with Fleming-Viot noise indexed by $k=0,1,2,\dots$, whose parameters $\alpha,\lambda$, and $\nu$ are the (deleterious) selection coefficient, the (uni-directional) mutation rate, and a quantity which determines the size of the system's fluctuations. The SDE's unique weak solution $X(t) = (X_k(t))_{k=0,1,2,...}$ models what is known in population genetics as Muller's ratchet. Here, $X_k(t)$ stands for the frequency of individuals carrying $k$ deleterious mutations. Since the mutation process is uni-directional, $t\mapsto \inf\{k: X_k(t)> 0\}$ is non-decreasing for almost every path of $X$, and we refer to an increase as a click of Muller's ratchet. A long standing question concerns the clicking rate of Muller's ratchet. Using Duhamel's principle for semigroups, we give a partial answer by approximating $E(\sum_{k=1}^\infty kX_k(t) )$ and $E\big(X_0(t)\big)$ up to $O(1/\nu^2)$ for fixed $\alpha$, $\lambda$ and $t>0$. Our results suggest that $\psi:=\nu \alpha e^{-\lambda/\alpha}$ is a crucial quantity also when the mutation/selection ratio $\theta = \lambda/\alpha$ is moderately large: for large $\nu \alpha$, clicking of the ratchet on the time scale $\frac 1\alpha \log \theta$ becomes rare as soon as $\psi$ becomes large.

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

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

作者:

Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat honesty – bounding what an agent may claim at termination – as a first-class metric for unattended autonomy, distinct from capability. We present Autopilot, an execution model that makes silent fabricated success structurally impossible rather than merely rarer. Autopilot externalizes all working state into a durable, gated finite-state machine that a scheduler advances one stateless tick at a time; a hard floor forbids any terminal "done" claim whose falsifiable gate did not actually execute and pass. We prove a No-False-Success theorem – under gate soundness, floor enforcement, and plan coverage, termination implies the goal holds – whose only trust points are empirically measurable, and show the worst case degrades to an honest stall, never a fabricated success. Because each tick rehydrates only the state machine, per-step context cost is constant in the horizon. Across a 3,150-cell paired corpus (70 tasks $\times$ 3 systems $\times$ 3 models $\times$ 5 seeds, including 50 SWE-bench Lite tasks across 11 OSS repos), Autopilot fabricates on 0.95% of cells [95% CI 0.38–1.62] while Reflexion and StateFlow baselines fabricate on 8.10% [6.48–9.81] and 25.05% [22.48–27.62] respectively. The headline contrast lives in the hard regime: on SWE-bench Lite, the firewall reduces fabrication from 33.7% (StateFlow) to 0.67%, a paired difference of $-33.07$ pp [95% CI $-36.53, -29.73$]. The mechanism is the gate, not the model: all ten Autopilot fabrications come from the strongest model, while two weaker mid-tier models never fabricate across 700 paired cells. The firewall trades coverage for honesty by design – an honest stall is recoverable; a confident wrong output shipped downstream is not.