中 EN
登录 注册账户

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。

登录 注册账户
01.
arXiv (CS.AI) 2026-06-15

Regulating the Machine Contributor: Governance and Policy Alignment in Open Source

作者:
Jassem Manita↗Aziz Amari↗

arXiv:2606.14594v1 Announce Type: cross Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-2026 record of agent-driven incidents, AI-generated nuisance volume, and platform-level shutdowns shows that the gap is operationally consequential. Several open-source organisations have responded with contribution policies, but the result is fragmented, and its alignment with emerging AI governance frameworks (EU AI Act, NIST AI RMF with the UC Berkeley Agentic AI Profile, ISO/IEC 42001 and 23894) is unmapped at the contribution level. We compare policies across six organisations (SymPy, LLVM, matplotlib, OpenInfra, the Apache Software Foundation, and the Linux Foundation) using Most-Similar Systems Design with indicator-based coding and process tracing for SymPy and LLVM. From this we derive a six-dimensional taxonomy (disclosure, responsibility, human oversight, licensing, enforcement, maintainer workload), an ordinal Policy Maturity Score, and a mapping of documented agent incidents onto the dimensions each policy fails to govern. Aligning the dimensions with the regulatory frameworks above identifies overlapping gaps neither side currently closes, and we close by sketching the shape of a harmonised tiered framework and the empirical evaluation needed to calibrate it.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-17

First, do NOHARM: towards clinically safe large language models

作者:
David Wu↗Fateme Nateghi Haredasht↗Saloni Kumar Maharaj↗Priyank Jain↗Jessica Tran↗Matthew Gwiazdon↗Arjun Rustagi↗Jenelle Jindal↗Jacob M. Koshy↗Vinay Kadiyala↗Anup Agarwal↗Bassman Tappuni↗…

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CV) 2026-06-19

BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models

作者:
Thomas Klassert↗Adrian Ulges↗Biying Fu↗

Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image generation models are significantly influenced by biases. This work investigates the inherent biases and language-induced biases present in text-to-image models within the context of occupation-related image generation, complementing established metrics with human preference feedback. We present a comprehensive evaluation of five current text-to-image models: Midjourney v6.1, Stable Diffusion 3 Medium, DALL-E 3, Playground v2.5, and FLUX.1-dev , focusing on gender and ethnicity bias, image quality, and prompt alignment. To facilitate this evaluation, we developed the "Battle-Arena for Fair Image Synthesis" (BAFIS), a platform designed to collect human feedback on bias in generated images. Furthermore, we created a dataset comprising 21,140 synthetic images generated using multilingual prompts, which serves as a basis for our analysis. We further place our results within a broader social context by comparing them to official statistics from the German Federal Employment Agency. Our findings reveal systematic biases in text-to-image models, with established evaluation metrics in partial correlation with subjective user ratings. Thus, our research emphasizes the need for including human preferences to develop fairer and more inclusive text-to-image models.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-12

Authorship Attribution in Multilingual Machine-Generated Texts

作者:
Lucio La Cava↗Dominik Macko↗R\'obert M\'oro↗Ivan Srba↗Andrea Tagarelli↗

As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult. While early efforts in MGT detection have focused on binary classification, the growing landscape and diversity of LLMs require a more fine-grained yet challenging authorship attribution (AA), i.e., being able to identify the precise generator (LLM or human) behind a text. However, AA remains nowadays confined to a monolingual setting, with English being the most investigated one, overlooking the multilingual nature and usage of modern LLMs. In this work, we introduce the problem of Multilingual Authorship Attribution, which involves attributing texts to human or multiple LLM generators across diverse languages. Focusing on 18 languages – covering multiple families and writing scripts – and 8 generators (7 LLMs and the human-authored class), we investigate the multilingual suitability of monolingual AA methods in terms of their cross-lingual transferability, and the impact of generators on attribution performance. Our results reveal that while certain monolingual AA methods can be adapted to multilingual settings, significant limitations and challenges remain, particularly in transferring across diverse language families, underscoring the complexity of multilingual AA and the need for more robust approaches to better match real-world scenarios.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.LG) 2026-06-17

Predictive Analytics in E-Commerce for CustomerBehavior Forecasting using hybrid Ret-DNN withXGBoost Model

作者:
Degala Pushpa Sri↗Mayank Atreya↗Lakshmi. H↗Navin Chhibber↗Mukesh Soni↗

arXiv:2606.17931v1 Announce Type: new Abstract: In recent years, electronic (E) commerce services have rapidly increased in the daily lives of people, which helpsthem to purchase products online. However, retail platforms have struggled to understand customer behavior and make it difficult to predict their future purchases. To overcome these challenges, this study proposes a hybrid Retail Deep NeuralNetwork (Ret-DNN) with an Extreme Gradient Boosting(XGBoost) model for capturing temporal features and tabular dynamics of retail data. First, data were sourced from a UnitedKingdom (UK)-based online retailer that contains transactions with almost 500,000 records. Then, the collected data were pre-processed using a series of techniques, such as data cleaning, outlier handling, temporal feature extraction, feature encoding, and z-score normalization, to ensure that the data were ready for model training and testing. Subsequently, the preprocessed data were fed into the Ret-DNN model, which acts as a feature extractor to understand the complete context of customer transactions. Further, the extracted data were fed as input into the XGBoost model, which predicted the final output as the purchase probability of customers. Finally, the proposed Ret-DNN XGBoost model achieved better results by attaining aMean Absolute Error (MAE) 0.2193 when compared to the existing Ret-DNN model. Keywords: Customer behavior forecasting, extreme gradientboosting, electronic commerce, predictive analytic, retail deepneural networks.

阅读与讨论 → 访问原文 →
06.
PLOS Computational Biology 2026-06-17

Machine learning-driven identification of virulence determinants in <i>Borrelia burgdorferi</i> associated with human dissemination

作者:
Hoa Thanh Nguyen↗

by Hoa Thanh Nguyen, Catherine A. Brissette Lyme disease, the most common tick-borne infectious disease in the United States, presents with highly variable clinical outcomes, ranging from localized erythema migrans to severe disseminated complications affecting the heart, joints, and nervous system. The bacterial determinants underlying this phenotypic variation remain largely unknown, limiting our ability to predict disease progression and optimize treatment strategies. Here, we applied machine learning (ML) approaches to identify specific amino acid residues within surface-exposed virulence factors that predict human dissemination phenotypes. Utilizing the published whole genome sequences from 299 clinical Borrelia burgdorferi isolates collected from the United States and Slovenia over a 30-year period (1992–2021), we extracted and characterized translated amino acid sequences (variants) of seven known virulence factors (BB_0406, BBK32, DbpA, OspA, OspC, P66, and RevA). Protein variants were classified based on their association with disseminated versus localized infections using clinical metadata. Cramér’s V analysis revealed possible strong associations between dissemination phenotypes and five adhesins: BBK32, DbpA, OspC, P66, and RevA. We developed ML models using five algorithms with multiple feature selection strategies, achieving robust predictive performance for DbpA, OspC, and RevA variants (all performance metrics > 0.7). Feature importance analysis identified 57, 29, and 42 key predictive residues for DbpA, OspC, and RevA, respectively. Notably, B-cell epitope prediction revealed significant enrichment of ML-identified residues within predicted epitope regions for OspC (11 overlapping residues, OR = 3.57, p = 0.006) and RevA (12 overlapping residues, OR = 2.37, p = 0.048), suggesting these residues may influence immune recognition and bacterial persistence. This study establishes the first computational framework linking Borrelia protein sequence variants to clinical dissemination phenotypes, providing molecular insights into Lyme disease pathogenesis that may inform the development of improved diagnostics and therapeutic targets.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CV) 2026-06-24

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

作者:
Peng Wang↗Xiao Li↗Can Yaras↗Zhihui Zhu↗Laura Balzano↗Wei Hu↗Qing Qu↗

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this work, we attempt to unveil this mystery by investigating the structures of intermediate features. Motivated by our empirical findings that linear layers mimic the roles of deep layers in nonlinear networks for feature learning, we explore how deep linear networks transform input data into output by investigating the output (i.e., features) of each layer after training in the context of multi-class classification problems. Toward this goal, we first define metrics to measure within-class compression and between-class discrimination of intermediate features, respectively. Through theoretical analysis of these two metrics, we show that the evolution of features follows a simple and quantitative pattern from shallow to deep layers when the input data is nearly orthogonal and the network weights are minimum-norm, balanced, and approximate low-rank: Each layer of the linear network progressively compresses within-class features at a geometric rate and discriminates between-class features at a linear rate with respect to the number of layers that data have passed through. To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks. Empirically, our extensive experiments not only validate our theoretical results numerically but also reveal a similar pattern in deep nonlinear networks which aligns well with recent empirical studies. Moreover, we demonstrate the practical implications of our results in transfer learning. Our code is available at https://github.com/Heimine/PNC_DLN.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-16

Ranking Abuse via Strategic Pairwise Data Perturbations

作者:
Junyi Yao↗Zihao Zheng↗Jiayu Long↗

arXiv:2604.17805v2 Announce Type: replace-cross Abstract: Pairwise ranking systems based on Maximum Likelihood Estimation (MLE), such as the Bradley-Terry model, are widely used to aggregate preferences from pairwise comparisons. However, their robustness under strategic data manipulation remains insufficiently understood. In this paper, we study the vulnerability of MLE-based ranking systems to adversarial perturbations. We formulate the manipulation task as a constrained combinatorial optimization problem and propose an Adaptive Subset Selection Attack (ASSA) to efficiently identify high-impact perturbations. Experimental results on both synthetic data and real-world election datasets show that MLE-based rankings exhibit a sharp phase-transition behavior: beyond a small perturbation budget, a limited number of strategic voters can significantly alter the global ranking. In particular, our method consistently outperforms random and greedy baselines under constrained budgets. These findings reveal a fundamental sensitivity of MLE-based ranking mechanisms to structured perturbations and highlight the need for more robust aggregation methods in collective decision-making systems.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CV) 2026-06-12

SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale

作者:
Nils Blank↗Paul Mattes↗Maximilian Xiling Li↗Jakub Suliga↗Thomas Roth↗Moritz Reuss↗Pankhuri Vanjani↗Rudolf Lioutikov↗

This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with structured spatial annotations and assigns each annotation a reliability score. Structured spatial annotations, such as bounding boxes, object trajectories, and manipulation phase labels, benefit a broad range of robotics applications from training grounded robot policies and embodied foundation models to motion planning and hierarchical task composition. Existing automated pipelines generate such annotations at scale but provide no reliable quality signal: detector confidence is poorly calibrated for annotation correctness, forcing a choice between accepting noisy labels or discarding useful samples. In contrast to existing automated pipelines, SPARC leverages the spatio-temporal structure inherent to robot tasks to generate a reliability signal, reducing noisy labels and retaining more useful samples. We further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations. On 1.7k human-annotated demonstrations spanning diverse embodiments and scenarios, SPARC significantly outperforms detection-only baselines in localization accuracy while retaining three times more samples at high-precision operating points. Our experiments demonstrate that models finetuned on our annotations achieve state-of-the-art results on object-grounding and pointing benchmarks among similarly sized models, while remaining competitive on broader spatial-reasoning suites without manually verified or annotated training data. Furthermore, policies trained on SPARC-generated annotations outperform baselines in cluttered, visually ambiguous real-world scenes. Code, data, and models are available at intuitive-robots.github.io/sparc-labeling.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CV) 2026-06-17

ProCUA-SFT Technical Report

作者:
Jaehun Jung↗Ximing Lu↗Brandon Cui↗Muhammad Khalifa↗Shaokun Zhang↗Hao Zhang↗Jin Xu↗Amala Sanjay Deshmukh↗Karan Sapra↗Andrew Tao↗Yejin Choi↗Jan Kautz↗…

Training computer-use agents (CUAs) – models that interact with graphical desktops through screenshots and keyboard/mouse actions – requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content – 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs – and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld – an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-11

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

作者:
Xin Chen↗Jie Zhang↗Florian Tram\`er↗

arXiv:2602.05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts. Adapting automated jailbreak optimizers does not close this gap: jailbreaks shape models toward generic compliance, while prompt injection requires emitting specific tool calls with correct parameters. The success signal is binary, and randomly sampled suffixes almost never trigger it, so standard optimizers have no gradient to follow. We present AutoInject, a black-box reinforcement learning (RL) framework that learns adversarial suffixes for prompt injection. A learned comparison-based reward scores each candidate against the best suffix seen so far, turning the binary signal into a dense reward suitable for RL optimization. The framework supports both online query-based attacks and offline-trained transferable suffixes that need no utility access at deployment, and incorporates a utility objective when task-completion feedback is available. On AgentDojo, AutoInject outperforms template attacks, GCG, TAP, and adaptive attack across production models, with statistically significant improvements under McNemar's test with p

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-16

Computational Safety for Generative AI: A Hypothesis Testing Perspective

作者:
Pin-Yu Chen↗

arXiv:2502.12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts. Examples of such tools include large language models (LLMs) and text-to-image (T2I) diffusion models. As the performance of various leading GenAI models approaches saturation due to similar training data sources and neural network architecture designs, the development of reliable safety guardrails has become a key differentiator for responsibility and sustainability. This paper presents a formalization of the concept of computational safety, which is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI through the lens of signal processing theory and methods. In particular, we explore two exemplary categories of computational safety challenges in GenAI that can be formulated as hypothesis testing problems. For the safety of model input, we show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts. For the safety of model output, we elucidate how statistical signal processing can be used to detect AI-generated content. Finally, we discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-11

Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases

作者:
Zhao Tan↗Yiji Zhao↗Shiyu Wang↗Chang Xu↗Yuxuan Liang↗Xiping Liu↗Shirui Pan↗Ming Jin↗

Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records. However, existing Text-to-SQL methods are not designed for continuous morphological intents such as shapes or anomalies, while time series models struggle to handle ultra-long histories. To address these challenges, we propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline. Analogous to active sonar, it utilizes a feature index to ping candidate windows via SQL, followed by generated Python programs to lock on and verify candidates against raw signals. To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories. Our experiments highlight the unique challenges within this domain and demonstrate that Sonar-TS effectively navigates complex temporal queries where traditional methods fail. This work presents the first systematic study of NLQ4TSDB, offering a general framework and evaluation standard to facilitate future research.

阅读与讨论 → 访问原文 →
14.
medRxiv (Medicine) 2026-06-24

Differential COVID-19 Outcomes Across Lysosomal Disorders

作者:
Byer↗B. K↗Butzin-Dozier↗McGrath↗B. M↗Muenzer↗Clarke↗Haendel↗M. A↗O'Neil↗S. T↗

Background Lysosomal disorders (LDs) are a heterogeneous group of rare inherited disorders characterized by multi-system involvement and high comorbidity burden, which raises concerns about severe COVID-19 outcomes. Conversely, because SARS-CoV-2 relies on endolysosomal pathways for cellular entry and replication, certain LDs may exert a protective effect against viral pathogenesis. Prior clinical evidence investigating LDs and severe SARS-CoV-2 infection has been limited by small sample sizes and inconsistent findings. Therefore, to resolve these conflicting biological hypotheses and estimate population-level outcomes, we conducted a large-scale retrospective cohort study using nationwide U.S. harmonized electronic health record data from the National Clinical Cohort Collaborative (N3C). This design utilized longitudinal records starting January 1, 2018, to evaluate COVID-19 infections captured between January 1, 2020, and July 11, 2024. Results The study included 16,380 individuals, comprising 5,460 patients with lysosomal disorders and 10,920 matched controls. Patients with LDs had significantly higher odds of COVID-19 hospitalization compared with controls (OR = 1.86, 95% CI: 1.70-2.04). Elevated odds were observed across the evaluated categories, but varied substantially. Notably, neurodegenerative LDs such as neuronal ceroid lipofuscinosis (OR = 9.32) and metachromatic leukodystrophy (OR = 2.33) remained associated with hospitalization after adjustment for comorbidities. Contrarily, the elevated odds for Fabry disease and Gaucher disease were no longer significant after adjustment. Mortality among hospitalized patients with LDs was comparable to that of matched controls (one-year survival: 82.1% vs 82.0%), suggesting that LD status does not independently worsen survival once hospitalization occurs. Conclusions Patients with LDs were at an increased odds of COVID-19 hospitalization, driven by a combination of elevated comorbidity burden and disorder-specific effects, which vary significantly across LD categories. This study clarifies that excess risk is concentrated in the transition to hospitalization. These patients may thus require personalized clinical care to mitigate the negative consequences of COVID-19.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.AI) 2026-06-16

Probing Low Frame Rate Degradation in Neural Audio Codecs

作者:
Alex Gichamba↗Moise Busogi↗

arXiv:2606.16969v1 Announce Type: cross Abstract: Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost scales linearly with the sequence length. Recent work has demonstrated that codecs can operate at 12.5 Hz and below, but the mechanisms underlying low frame rate degradation remain insufficiently understood. We investigate these mechanisms through a controlled frame rate ablation. We reproduce a quality cliff at 6.25 Hz reported in previous works and evaluate candidate explanations: phonemic collisions and codebook saturation, neither of which shows evidence of a fundamental barrier. The cliff is instead caused by suboptimal training configuration: fixed clip duration during training yields too few tokens at low frame rates, starving the decoder of inter-token context. Once corrected, WER degrades smoothly with phonemic load down to 3.1 Hz and 1.6 Hz, suggesting the inference-time efficiency gains of low frame rate codecs are more accessible than previously assumed.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-17

The Discrete-Log Clock: How a Transformer Learns Modular Multiplication

作者:
Huu Danh Nguyen↗

arXiv:2606.17399v1 Announce Type: cross Abstract: When small transformers grok modular multiplication, prior work reports that the learned embedding has a "dense" Fourier spectrum requiring all frequencies. This contrasts with modular addition, where only a sparse set of key frequencies suffices. We show this density is an artifact of analyzing in the wrong basis. The natural Fourier transform for multiplication is not the standard additive DFT but the multiplicative character transform, which decomposes functions on the multiplicative group $(\mathbb{Z}/p\mathbb{Z})^*$ into its irreducible representations. Applying this transform to a grokked transformer trained on $a \cdot b \bmod 113$, we find the embedding spectrum becomes highly sparse (Gini coefficient 0.58 vs. 0.07 in the additive basis) with only 4 key frequencies carrying significant energy. Furthermore, 96.9% of MLP neurons are cleanly tuned to a single multiplicative frequency, and neuron activation heatmaps reveal 2D-periodic structure when reordered by the discrete logarithm. These results demonstrate the transformer reduces multiplication to addition in discrete-log space, implementing a "Discrete-Log Clock" algorithm analogous to Nanda et al.'s Clock algorithm for addition. The methodology generalizes: matching the analysis basis to the algebraic structure of the task reveals interpretable structure where standard tools see noise.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-16

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

作者:
Yue Yu↗Yang Jiao↗Jiayu Wang↗Qi Dai↗Jingjing Chen↗

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CL) 2026-06-16

Creative Collision: Directorial Persona Steering and Competition in Large Language Models

作者:
Subramanyam Sahoo↗Justin Shenk↗

Activation steering has emerged as a powerful tool for shaping the behaviour of large language models at inference time, yet most prior work injects a single semantic direction into the residual stream. We study the richer setting in which two semantically opposing steering vectors are superimposed – a regime we call Creative Collision. Concretely, we construct directorial persona vectors for Steven Spielberg (optimistic, redemptive moral valence) and Martin Scorsese (dark, morally ambiguous) via mean-difference activation contrast on curated screenplay-derived corpora, then interpolate between them with a scalar mixing parameter $\alpha \in [0,1]$ and a steering coefficient $\lambda$. Across five evaluation axes – moral valence, generation coherence, surface style, directional dominance, and vector geometry – three principal findings emerge: (i)~Spielberg's representational signature exhibits robust directional dominance, suppressing Scorsese's moral influence across almost the entire interpolation range; (ii)~intermediate collision points paradoxically improve generation coherence relative to pure single-director steering at high $\lambda$; and (iii)~both personas localise maximally to layer~28 of a 40-layer decoder-only transformer, revealing a shared moral-tone substrate. These results illuminate the geometry of competing semantic directions in transformer residual streams and have direct implications for controllable creative generation and value-aligned narrative synthesis.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CL) 2026-06-15

Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling

作者:
Xing Yue↗Linjuan Wu↗Daoxin Zhang↗Yongliang Shen↗Weiming Lu↗

Open-ended reward modeling requires judges that can follow subtle, domain-specific preferences when verifiable answers are unavailable. Existing rubric-based methods often address this by generating criteria online for each query, but the extra generation step can add inference overhead and produce rigid or misaligned guidance. We introduce Eval-Skill, an exploration-guided method that synthesizes reusable evaluation skills for reward modeling and reframes reward guidance as context evolution rather than parameter training or per-query rubric generation. Using only 100 cases per domain for skill evolution, Eval-Skill synthesizes reusable domain-level evaluation skills through two progressive stages, workflow generation followed by principle generation, with exploration and selection interleaved across both stages. Once generated, a skill is directly injected into the judge context. Across multiple RM benchmarks, Eval-Skill consistently improves diverse judge backbones; on RewardBench 2, it yields significant gains over vanilla judging for each main backbone (+13.44% for Qwen3-8B, and 18.51% for DeepSeek-V4-Flash). Further analyses of evolution-time scaling, generalizability, and transferability show that compact evaluation skills offer an efficient new paradigm for LLM-based evaluation. Code is available at https://github.com/xing-stellus-yue/Eval-Skill.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.LG) 2026-06-16

TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation

作者:
Zhiqiang Zhou↗Junliang Dai↗Xu Ling↗

arXiv:2606.15074v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-16

Communication-Efficient Verifiable Attention for LLM Inference

作者:
Ziqun Chen↗Ming Wu↗Michael Heinrich↗Jason Zeng↗Huiying Lan↗Tianwei Zhang↗Rui Tan↗

arXiv:2606.16352v1 Announce Type: cross Abstract: Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TSDP) approach uses Trusted Execution Environment (TEE) to compute non-linear components and verify the integrity of linear components offloaded to an untrusted GPU. However, directly applying TSDP to Transformer-based LLMs incurs significant TEE computation and TEE-GPU communication overhead. This paper presents Communication-efficient TEE-GPU Attention (\textsc{VeriAttn}) for accelerating verifiable LLM inference. \textsc{VeriAttn} offloads both linear and non-linear computations of attention to the GPU, while TEE performs verification. Moreover, for prefill, \textsc{VeriAttn} uses a two-level pipeline to overlap data movement, TEE pre-/post-processing, and GPU computation. For decoding, when the key-value cache exceeds available GPU memory, \textsc{VeriAttn} partitions attention across TEE and GPU to reduce repeated key-value transfers. Evaluation on an Intel TDX platform shows that \textsc{VeriAttn} achieves 2.60-3.38$\times$ and 3.86-5.42$\times$ acceleration over TSDP for 6k-token prompts and 10k-token outputs during prefill and decoding, respectively.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CV) 2026-06-16

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

作者:
Pratheswaran Hariharan↗Haiping Xu↗Donghui Yan↗

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. However, these systems can still produce overconfident predictions and hallucination-like outputs, particularly when the visual evidence is weak, ambiguous, or semantically inconsistent. Most existing approaches focus on improving multimodal representation alignment or retrieval-augmented generation, while providing limited mechanisms to quantify instance-level prediction reliability or identify incorrect visual outputs. This work proposes a retrieval-augmented reliability-aware inference framework for trustworthy multimodal visual understanding. The proposed framework constructs an external visual evidence database using pretrained visual embeddings and nearest-neighbor retrieval over normalized feature representations. Retrieved evidence is used to estimate prediction trustworthiness through multiple reliability indicators, including similarity strength, class-support agreement, evidence margin, entropy-based uncertainty, and an aggregate reliability score. Based on these signals, a decision gate determines whether the system should accept the prediction, answer with caution, or abstain/fallback when evidence is insufficient. A multimodal response-generation layer then produces a final user-facing response conditioned on the reliability decision. Experiments on ImageNet-100 demonstrate that the proposed reliability-aware framework improves accepted prediction accuracy from 85.84\% to 88.88\% at 89.04\% coverage. The hallucination-like accepted wrong-answer rate is reduced from 14.16\% to 11.12\%. These results show that integrating retrieval evidence, reliability estimation, and selective decision gating can improve calibration and reduce overconfident visual errors without retraining large multimodal models.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.AI) 2026-06-12

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

作者:
Ashutosh Hathidara↗Sai Shruthi Sistla↗Sebastian Schreiber↗Sahil Bansal↗

arXiv:2606.12451v1 Announce Type: new Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval approaches rely on compact encoders that may under-capture specialized tool semantics, parametric tool retrieval addresses this by encoding each tool as a virtual token appended to the LLM vocabulary, fine-tuned in two stages (memorization then retrieval SFT) to use the LLM as a retriever, achieving strong performance on standard ToolBench retrieval benchmarks. Yet these benchmarks use verbose, fully-specified queries, and their evaluation applies constrained decoding that restricts outputs to valid token paths, neither reveals whether the model actually understands its tools. We introduce ToolSense, an open-source LLM-powered diagnostic framework that takes any tool catalog as input and automatically generates three benchmarks: a Realistic Retrieval Benchmark (RRB) with queries at three ambiguity tiers, an MCQ probing benchmark, and a QA probing benchmark. Applying ToolSense to ToolBench (~47k tools) and evaluating five parametric model training configurations reveals a knowledge-retrieval dissociation: on RRB queries, several configurations collapse by ~50-64 percentage points compared to fully-specified ToolBench benchmarks, falling below the embedding-model baseline. Additionally, despite strong retrieval performance, some models score near-random on factual probes, suggesting a knowledge-retrieval dissociation. We open-source the ToolSense framework and the ToolBench diagnostic benchmarks at https://github.com/SAP/toolsense.

阅读与讨论 → 访问原文 →
25.
bioRxiv (Bioinfo) 2026-06-22

EventHorizon: A Foundation Model for Clinical Flow Cytometry

作者:
Medina Grespan↗Morrison↗O'Fallon↗Shean↗Spies↗N. C↗Ng↗

Flow cytometry is an essential tool for diagnosis of hematologic malignancies, but existing clinical workflows are highly dependent on expert manual interpretation. Existing machine learning approaches typically require extensive labeled data and are sensitive to variability in panel design, instrumentation, and laboratory workflows, limiting their generalizability. We present EventHorizon, a self-supervised foundation model for clinical flow cytometry that produces unified specimen-level representations from heterogeneous multi-panel data. EventHorizon employs a two-stage hierarchical transformer architecture with marker-aware tokenization, enabling seamless integration of cells measured across different antibody panels into a single shared latent space. We pre-train the model using a DINO-inspired self-distillation strategy with a variety of flow cytometry-specific augmentations on a dataset of more than 100,000 clinical specimens across 17 distinct panels. We evaluate the resulting embeddings on three clinically relevant classification tasks spanning common and rare panels, demonstrating that simple k-nearest neighbor probing of frozen EventHorizon embeddings achieves performance comparable to a fully supervised baseline model and a prior panel-specific self-supervised model. To ensure EventHorizon is not simply shortcut learning on features such as the markers/panels run for a given specimen, we perform a graph-theoretic analysis of EventHorizon's latent space which argues that specimen embeddings are organized primarily by biological diagnosis. Taken together, these results demonstrate that EventHorizon produces biologically meaningful, panel-agnostic specimen representations from clinical flow cytometry data which, with further development and validation, could provide a potential basis for scalable, reproducible diagnostic support across diverse clinical laboratory settings.

阅读与讨论 → 访问原文 →