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.CV) 2026-06-16

MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios

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

02.
medRxiv (Medicine) 2026-06-16

Supplementation with Arabinoxylan Dietary Fiber at Low Doses Produces Behavioral, Metabolic, and Gut Microbial Changes in Healthy, Overweight Adults: A Randomized Placebo-Controlled Trial

Background: Dietary fiber comprises a heterogeneous group of compounds with distinct physicochemical properties and biological effects. As such, functional outcomes observed for one fiber cannot be generalized to others. Some fermentable fibers, such as arabinoxylan, may exert biologically selective effects across multiple physiological domains, highlighting the need to evaluate individual ingredients for their domain-specific activity in controlled human studies. Methods: In this randomized, double-blind, parallel, 3-arm, placebo-controlled trial, healthy, overweight adults were assigned to consume one of two low doses of an arabinoxylan dietary fiber (3.5g or 5g) or placebo over the intervention period. Self-reported appetite sensations were assessed as the primary outcome using validated visual analogue scales. Secondary and exploratory endpoints included lipid parameters, gastrointestinal outcomes, mood-related measures, and gut microbiota composition and fermentation-derived metabolites. Analyses were conducted in the full analysis set and a high-compliance population to assess responses under sustained intake conditions, as per the intended dosing regimen. Results: The primary endpoint of appetite sensations did not differ between either arabinoxylan group and placebo. In contrast, evidence of microbial fermentation and selective microbiota engagement was observed. These responses occurred alongside consistent and favorable changes in lipid parameters under conditions of sustained intake, including reductions in low-density lipoprotein cholesterol and triglycerides. Additional outcomes, including gastrointestinal symptoms and mood, demonstrated domain-specific responses. Conclusion: This study demonstrates that supplementation with low doses of arabinoxylan dietary fiber elicit biologically selective, domain-specific effects across metabolic, microbial, gastrointestinal, and behavioral outcomes, particularly under conditions of sustained intake. These responses occurred independently of changes in appetite sensation, indicating that functional effects were not mediated through appetite-related pathways. Collectively, the findings highlight the ingredient's biological versatility and contextual responsiveness across physiological systems, and suggest its prebiotic potential through alignment with ISAPP's definition of a prebiotic, supporting further investigation of specific mechanistic pathways. Clinical trial registration: https://clinicaltrials.gov/study/NCT06884449, identifier: NCT06884449

03.
arXiv (CS.AI) 2026-06-18

Signals of Provenance: Practices & Challenges of Navigating Indicators in AI-Generated Media for Sighted and Blind Individuals

arXiv:2505.16057v2 Announce Type: replace-cross Abstract: AI-Generated (AIG) content has become increasingly widespread by recent advances in generative models and the easy-to-use tools that have significantly lowered the technical barriers for producing highly realistic audio, images, and videos through simple natural language prompts. In response, platforms are adopting provable provenance with platforms recommending AIG to be self-disclosed and signaled to users. However, these indicators may be often missed, especially when they rely solely on visual cues and make them ineffective to users with different sensory abilities. To address the gap, we conducted semi-structured interviews (N=28) with 15 sighted and 13 BLV participants to examine their interaction with AIG content through self-disclosed AI indicators. Our findings reveal diverse mental models and practices, highlighting different strengths and weaknesses of content-based (e.g., title, description) and menu-aided (e.g., AI labels) indicators. While sighted participants leveraged visual and audio cues, BLV participants primarily relied on audio and existing assistive tools, limiting their ability to identify AIG. Across both groups, they frequently overlooked menu-aided indicators deployed by platforms and rather interacted with content-based indicators such as title and comments. We uncovered usability challenges stemming from inconsistent indicator placement, unclear metadata, and cognitive overload. These issues were especially critical for BLV individuals due to the insufficient accessibility of interface elements. We provide practical recommendations and design implications for future AIG indicators across several dimensions.

04.
arXiv (CS.CL) 2026-06-15

Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep Dense Exploration (DDE), a strategy that focuses exploration on $pivots$-deep, recoverable states within unsuccessful trajectories. We instantiate DDE with DEEP-GRPO, which introduces three key innovations: (1) a lightweight data-driven utility function that automatically balances recoverability and depth bias to identify pivot states; (2) local dense resampling at each pivot to increase the probability of discovering correct subsequent trajectories; and (3) a dual-stream optimization objective that decouples global policy learning from local corrective updates. Experiments on mathematical reasoning benchmarks demonstrate that our method consistently outperforms GRPO, tree-based methods, and other strong baselines. Code is available at https://github.com/AgentCombo/DEEP-GRPO

05.
arXiv (CS.LG) 2026-06-15

Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification

arXiv:2605.29228v2 Announce Type: replace Abstract: Protein structure classification (PSC) uses supervised learning to predict a protein's CATH/SCOP(e) class from the protein's sequence or 3D structural feature(s). We already modeled 3D structures as (static) protein structure networks (PSNs), demonstrating the competitiveness of PSN-based features to sequence or direct (i.e. non-network) 3D structural features in the PSC task. More recently, we demonstrated the power of features extracted from dynamic PSNs over features extracted from static PSNs (and thus by transitivity over sequence and direct 3D structural features) in the same task. That dynamic PSN approach used traditional machine learning (ML), combining manual (pre-engineered) features with an off-the-shelf classifier. Here, we evaluate whether automatic deep learning (DL) from the dynamic PSNs yields improvements. Our evaluation on 72 datasets spanning ~44,000 CATH- or SCOPe-labeled dynamic PSNs reveals that in terms of PSC accuracy, traditional ML and DL are (close to) tied for a large majority of the datasets, while DL is on average 10+ times slower. We are the first to evaluate traditional ML vs. DL in the dynamic PSN-based PSC task.

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

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex mathematical and logical tasks. However, the field faces the fundamental gap between token-level behavioral analysis and internal reasoning mechanisms, and the instability of reinforcement learning (RL) for reasoning optimization relying on costly external verifiers. We identify and formally define Entropy-Gradient Inversion, a robust negative correlation between token entropy and logit gradients that acts as a definitive geometric fingerprint for LRM reasoning capability. Building on this, we propose Correlation-Regularized Group Policy Optimization (CorR-PO), which embeds this inversion signature into RL reward regularization. Extensive experiments on various reasoning benchmarks across multiple model scales show CorR-PO consistently outperforms state-of-the-art baselines, confirming that stronger inversion directly correlates with superior reasoning performance.

07.
arXiv (CS.CV) 2026-06-19

Evaluation of Image Matching for Art Skills Assessment

While some individuals possess a natural talent for drawing, mastering this skill requires dedicated training and practice. Determining one's skill in the art of drawing requires proper comprehensive assessment. In this paper, we propose a method to measure drawing skill by by matching the hand-drawn image with the original template. Existing techniques often involve complex processes. However, advancements in computer vision allow us to train computers to perform these comparisons at a human-like level, thereby resolving the tedious and overwhelming traditional process. Using computer vision applications, determining image similarity involves identifying the level of similarities in an image with a reference image. We have implemented and analyzed the SIFT feature and Siamese network to measure image similarity. Our results indicate that it is feasible to assess art skill levels. Through feature analysis, we found that SIFT-based key point matching provides a more effective means of detecting drawing skills.

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

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping

arXiv:2506.01396v2 Announce Type: replace Abstract: Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model predictions, e.g., for minority groups. Gradient clipping, which is often used in DP learning, can suppress larger gradients from challenging samples. We show that this problem is amplified by adaptive clipping, which will often shrink the clipping bound to tiny values to match a well-fitting majority, while significantly reducing the accuracy for others. We propose bounded adaptive clipping, which introduces a tunable lower bound to prevent excessive gradient suppression. Our method improves worst-class accuracy by over 10 percentage points on Skewed and Fashion MNIST compared to unbounded adaptive clipping, 7 points compared to Automatic clipping, and 5 points compared to constant clipping. The code is available at https://github.com/TrustworthyMLHelsinki/adaptive-clipping-fairness.

09.
medRxiv (Medicine) 2026-06-22

Three multimodal large language models fail at clinically actionable breast pathology in three different directions

Background. Breast cancer treatment depends on histopathological features, such as grade and receptor-defined subtype; however, specialist pathologist access is constrained when the workforce is limited. Commercial multimodal large language models (MLLMs) accept hematoxylin and eosin (H&E) image tiles through paid interfaces without local hardware or fine-tuning. However, prior pathology evaluations addressed only coarse tasks. Whether they reach treatment-determining accuracy and whether vendors agree remain unclear. Methods. We aimed to evaluate three vendor-designated flagship MLLMs (Claude Sonnet 4.6, Gemini 2.5 Pro, GPT-5.5) in 427 invasive breast cancer cases. Each case went to all three with identical H&E tiles and prompts, and the subtype was inferred in the second call. The reference was an institutional sign-out report of an immunohistochemistry-derived subtype. We calculated the concordance, sensitivity, specificity, Cohen's kappa, and pairwise McNemar and Bowker tests. Findings. Claude ranked highest by raw histologic-type concordance but lowest by kappa, classifying all 23 lobular and seven micropapillary carcinomas as invasive breast carcinoma of no special type. The models anchored the Nottingham grade to three modal grades. None of the models reliably identified human epidermal growth factor receptor 2-positive disease. The failure direction was vendor-specific: Claude and GPT-5.5 were under-detected, whereas Gemini was over-called. Twelve prompt variants (4,056 calls) did not recover sensitivity. Interpretation. No current commercial MLLM reaches deployment-ready accuracy for any treatment-determining feature of breast pathology. As each vendor fails in its own fixed direction, changing vendors alters the type of error rather than removing it; therefore, the value of these models is assistive rather than autonomous. At USD 0.20-0.50 per case, they may serve as supervised draft generators that leave the diagnosis with the pathologist.

10.
arXiv (CS.CV) 2026-06-16

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However, measuring information loss during modality conversion is inherently challenging due to the modal gap between visual content and text output. In this paper, we argue that the quality of an image caption is positively correlated with the similarity between images retrieved via text search using that caption. Based on this insight, we further propose Cross-modal Identity Mapping (CIM), a reinforcement learning framework that enhances image captioning without requiring additional annotations. Specifically, the method quantitatively evaluates the information loss from two perspectives: Gallery Representation Consistency and Query-gallery Image Relevance. Supervised under these metrics, LVLM minimizes information loss and aims to achieve identity mapping from images to captions. The experimental results demonstrate the superior performance of our method in image captioning, even when compared with Supervised Fine-Tuning. Particularly, on the COCO-LN500 benchmark, CIM achieves a 20% improvement in relation reasoning on Qwen2.5-VL-7B.

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

A Perception vs. Distortion Perspective on Score-Based Generative Channel Estimation

arXiv:2606.16815v1 Announce Type: cross Abstract: Driven by their remarkable success in computer vision and inverse problem solving, score-based models are increasingly applied to wireless communications, where they show promise across a range of physical-layer tasks. However, despite this growing interest, the current literature often lacks a rigorous analysis of when score-matching offers a tangible advantage over traditional discriminative learning. This paper aims to address this gap through the use-case of channel estimation, a fundamental inverse problem in wireless systems. We present a theoretically grounded interpretation of score-based channel estimation through the lens of the perception-distortion tradeoff, identifying the conditions where score matching excels as well as its key limitations. In particular, by modeling downstream wireless tasks (e.g., capacity maximization) as functionals of the channel estimation process, we quantify the excess risk incurred by standard distortion-minimization approaches. Extensive numerical results show that under high predictive uncertainty, the large excess risk gap can be offset by score-based estimation, enabling near Bayesian-optimal precoding via the learned posterior, whereas in the low predictive uncertainty regime, discriminative distortion-minimization approaches are preferable due to lower complexity and more efficient use of model capacity.

12.
medRxiv (Medicine) 2026-06-15

Mucosal and Systemic Antibodies Associated with Clinical Protection in a Pertussis Controlled Human Infection Model

Background The engagement of mucosal and systemic immunity in preventing Bordetella pertussis colonization and infection in humans, the impact of prior vaccination on host immunity and protective outcomes, and the dynamics of the host response following exposure remain poorly understood. Methods Healthy adults were challenged with increasing colony-forming units (CFUs) doses, 106-108, of B. pertussis D420 intranasally (NCT05136599). Shedding (PCR and culturing) and symptom development were monitored up to 21 days post-challenge. Serum and nasal wash IgA and IgG were measured before challenge (baseline) and up to 6 months post-challenge. Findings Antibodies increased post-challenge only in infected individuals, primarily nasal IgA. Participants who remained uninfected had higher baseline levels of filamentous hemagglutinin (FHA)- specific mucosal IgA and IgG, and higher serum IgA against fimbriae 2/3 (FIM). FHA was negatively associated with bacterial load and was a key discriminator between shedders and non-shedders, up to one week post-challenge. By day 14 post-challenge, pertussis toxin (PT) IgG and FIM IgA in both serum and mucosal samples were negatively associated with bacterial colonization. The majority (96.7%) of acellular pertussis (aP) vaccine recipients (n=23, median age 2.0 years) became infected, compared to 69.4% of those who received whole-cell pertussis vaccine (n=36; median age 32.0 years), and their antibody responses remained distinct following infection. Interpretation Nasal FHA antibodies emerged as early predictors of protection against pertussis infection, while PT IgG and FIM IgA antibodies may reflect clearance after infection. aP-primed individuals were more susceptible to infection, despite their younger age and more recent vaccination. Funding CDC Contract #75D30122C15467 and CDC IPA Agreement #24IPA2417512 Disclaimer: The findings and conclusions in this report are those of the authors and do not necessarily represent the official position of the Centers for Disease Control and Prevention, US Department of Health and Human Services.

13.
arXiv (CS.AI) 2026-06-19

Denoising Implicit Feedback for Cold-start Recommendation

arXiv:2606.19658v1 Announce Type: new Abstract: Implicit feedback is widely used in recommender systems due to its accessibility and generality, yet it usually presents noisy samples (e.g., clickbait, position bias). Meanwhile, recommenders inevitably face the item cold-start problem due to the continuous influx of new items. We identify that cold items are more prone to noisy samples due to the aforementioned factors, and researchers often overlook the significance of denoising implicit feedback for cold items. Previous denoising studies usually identify noisy samples based on heuristic patterns, such as higher loss values, and mitigate noise through sample selection or re-weighting. However, these methods have limited adaptability and are ineffective in cold-start scenarios. To achieve denoising implicit feedback for cold-start recommendation, we propose a model-agnostic denoising method called DIF. First, user preferences for content remain stable, which allows us to infer pseudo-labels indicating whether a user is interested in a cold item through content-similar warm items. Furthermore, to improve pseudo-label accuracy, we model the confidence of pseudo-labels based on the content similarity between the cold item and warm items, and then aggregate multiple pseudo-labels for each sample. Finally, we explicitly estimate the uncertainty of the noisy sample label by considering its relative entropy and the cold-start status of the item, which adaptively guides the role of pseudo-labels to correct the noisy labels at the sample level. DIF's superiority is supported by both theoretical justification and extensive experiments on real-world datasets. The method has been deployed on a billion-user scale short video application Kuaishou and has significantly improved various commercial metrics within cold-start scenarios.

14.
medRxiv (Medicine) 2026-06-12

Order-Based Bayesian Network Modeling of Early Detection and Post-Diagnosis Control for Cardiovascular Disease Risk in Type 2 Diabetes

Patients diagnosed with type 2 diabetes (T2D) are at increased risk of developing cardiovascular disease (CVD), the leading cause of morbidity and mortality in this population. Early detection and glycemic control within the first year after diagnosis reduce CVD risk. However, gaps remain in how to operationalize early detection of T2D using Electronic Health Record (EHR) data and quantify its relationship with subsequent CVD risk using longitudinal observations. We developed a probabilistic graph model to analyze the interdependencies between early detection of T2D, post-diagnosis glycemic control, and CVD occurrence. Using a temporally structured Bayesian Network (BN) learned from EHR data of 9,450 primary care patients between 2017 and 2023, we quantified probabilistic dependencies between demographics, diagnostic delay surrogates, glycemic control, and post-diagnosis CVD occurrence. Percentile based thresholds defined risk groups, where individuals with predicted probabilities in the bottom decile ([≤] 10th percentile) were classified as low risk, and those in the top decile ([≥] 90th percentile) as high risk. Results demonstrated heterogeneity in predicted risks across glycemic and cardiovascular outcomes. Predicted probability of developing CVD within the first year after T2D diagnosis ranged from a mean of 5.2% in the low-risk group to 28.9% in the high-risk group, while predicted probabilities of mean Hemoglobin A1c (HbA1c) [≥] 8% during the first year post-diagnosis ranged from 1.6% in low-risk to 55.1% in high-risk group. Patients with HbA1c at diagnosis [≥] 8% had higher predicted probabilities of first-year post-diagnosis mean HbA1c [≥] 8% (53.3% vs. 1.9%) and high HbA1c coefficient of variation (18.7% vs. 3.1%) compared with those with HbA1c [≤] 6.5%. Incorporating early clinical outcomes refined later risk predictions, with long-term CVD risk reaching 33.5% among high-risk individuals. The proposed model achieved predictive performance comparable to conventional machine learning approaches while providing interpretable relationships for risk stratification in primary care populations.

15.
arXiv (quant-ph) 2026-06-19

Optimizing resource allocation for accuracy in noisy variational quantum algorithms

arXiv:2606.20153v1 Announce Type: new Abstract: For quantum algorithms to achieve their full potential, we need methodologies to optimize them, such as reaching a given output accuracy with minimal resource costs. Here, we develop such a methodology for a class of Noisy Intermediate-Scale Quantum (NISQ) algorithms. We leverage simulations of a Variational Quantum Eigensolver (VQE) to propose a phenomenological model of such algorithms that captures the complex relationship between algorithmic accuracy, algorithmic resource costs, and the noise that exists in realistic quantum hardware. For this, we take the algorithmic resource cost to be the total number of quantum gate-operations in the algorithm; minimizing this cost typically makes the algorithm faster and more energy-efficient. We consider the subtle trade-off between quantum circuit size (small circuits are too imprecise, but large ones are too noisy), and the number of iterations of that quantum circuit for the full algorithm to sufficiently converge. Using a noise-metric-resource methodology, we identify the sweet spot (of circuit size versus iterations) that minimizes the algorithmic resource costs for a desired algorithm accuracy. It also gives the circuit size that maximizes algorithm accuracy for a fixed resource cost. Our methodology provides a practical guideline for near-term deployment of variational algorithms on realistic noisy hardware, including hardware that uses error mitigation.

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

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have emerged as the dominant paradigm, they suffer from a critical bottleneck: data efficiency. Current methods treat the development dataset as a static benchmark, wasting significant compute budget on uninformative data. In this work, we introduce APEX (Automatic Prompt Engineering eXpert), a novel framework that optimizes the data usage alongside the prompt search. APEX dynamically stratifies the dataset into Easy, Hard, and Mixed tiers based on the optimization lineage. By prioritizing the Mixed tier, which identifies the data where the LLM has mixed performance, we identify two high-leverage subsets: the addressable frontier for generating informative mutations and the rank-sensitive frontier for distinguishing candidate quality. We evaluate APEX across three diverse benchmarks: IFBench, SimpleQA Verified, and FACTS Grounding. Under a fixed budget of 5,000 evaluation calls, due to its data efficiency, APEX outperforms the initial prompt by an average of 11.2% on Gemini 2.5 Flash and 6.8% on Gemma 3 27B, demonstrating that a data-centric approach is key to efficient and effective prompt optimization.

17.
arXiv (CS.AI) 2026-06-16

Is Code Better Than Language for Algorithmic Reasoning

arXiv:2606.15589v1 Announce Type: cross Abstract: For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism. We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer. On a 40-task verifiable algorithmic benchmark, deterministic code execution outperforms natural-language reasoning by +31.6pp. We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp). These results suggest that, in our evaluated setting, changing the intermediate representation alone does not explain the tool-use advantage, providing evidence for the performance gains requiring reliable external execution. We formalize this intuition with a simple statistical decision-theoretic model that characterizes when execution dominates end-to-end risk in our disentangled trace-generation/execution regime. We validate our theory using a reconstruction intervention that leverages a proxy language model to infer natural-language reasoning traces from code representations, recovering performance comparable to the original natural-language reasoning pipeline. All experiments are at https://github.com/TerryTong-Git/ToolProj.

18.
arXiv (quant-ph) 2026-06-24

Active interference suppression in frequency-division-multiplexed quantum gates via off-resonant microwave tones

arXiv:2601.14547v3 Announce Type: replace Abstract: The increasing number of control lines connecting quantum processors to external electronics constitutes a major bottleneck in the realization of large-scale quantum computers. Frequency-division multiplexing is expected to enable control of multiple qubits through a single microwave cable; however, interference from off-resonant microwave tones hinders precise qubit control. Here, we propose an active interference suppression method for frequency-division-multiplexed simultaneous gates on microwave-controlled qubits. We demonstrate that the deliberate incorporation of off-resonant microwave tones improves single-qubit gate fidelity. In particular, the gate infidelity scales inversely with the square of the number of microwave tones when off-resonant orthogonal or quasi-orthogonal tones are incorporated. Furthermore, we show that fast oscillations, neglected under the rotating wave approximation, degrade the gate fidelity, and that this degradation can be mitigated through optimized frequency allocation. The proposed approach is simple and effective for improving the performance of frequency-division-multiplexed quantum gates.

19.
arXiv (CS.CV) 2026-06-18

When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift

Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, with recent methods increasingly focusing on improving generalization to unseen manipulations. This is typically evaluated using the Area Under the ROC Curve (AUC) measured separately across multiple datasets. However, such an evaluation fails to reflect real-world scenarios where detectors face a mixture of data sources and varying artifact types. To address this limitation, we introduce a novel metric, Cross-dataset AUC (Cross-AUC) that averages per-domain AUCs with a measure of prediction polarization for taking into account the robustness to domain shift. The polarization extent is quantified by the Wasserstein Distance between class score distributions. Cross-AUC not only assesses the generalization capabilities of deepfake detectors under domain shifts more realistically, but it is also interpretable as it better explains the reason behind a drop in performance. Experiments performed on seven benchmark datasets demonstrate its practical relevance.

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

Generative causal testing to bridge data-driven models and scientific theories in language neuroscience

Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is unclear what features of the language stimulus drive the response in each brain area. We present generative causal testing (GCT), a framework for generating concise explanations of language selectivity in the brain from predictive models and then testing those explanations in follow-up experiments using LLM-generated stimuli.This approach is successful at explaining selectivity both in individual voxels and cortical regions of interest (ROIs), including newly identified microROIs in prefrontal cortex. We show that explanatory accuracy is closely related to the predictive power and stability of the underlying predictive models. Finally, we show that GCT can dissect fine-grained differences between brain areas with similar functional selectivity. These results demonstrate that LLMs can be used to bridge the widening gap between data-driven models and formal scientific theories.

21.
arXiv (CS.AI) 2026-06-15

Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry

arXiv:2606.13934v1 Announce Type: new Abstract: Humans cannot always intuit what scenarios are most challenging to LLMs. Hoping to capture challenging edge cases, developers either design problems to be difficult for humans or curate extensive benchmarks. What if we could instead anticipate which scenarios a model will fail on? In this paper, we use an LLM's representational geometry to predict which concept combinations it will fail on. We attribute this compositional failure to interference between salient features. In tasks that require systematic composition - toy programmatic settings, multihop reasoning, multilingual factual recall - we find that when a pair of concepts is encoded near-orthogonally, the model reliably composes them. When their linear encodings are close, producing interference, the model fails to compose them. Our method reliably anticipates failure modes across different compositional tasks, without evaluating specific inputs. These results lay the groundwork to use representational geometry to identify high-risk examples, construct targeted stress tests, and provide a scalable foundation for active learning in real-world deployment.

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

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

23.
arXiv (CS.AI) 2026-06-11

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

arXiv:2606.11357v1 Announce Type: cross Abstract: With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. However, practical LLM deployment on current client NPUs remains difficult: widely used quantization formats such as AWQ do not map cleanly onto many existing NPU software stacks, which are often proprietary and expose limited low-level control. In this work, we present TileFuse, a close-to-metal mixed-precision kernel library for AMD XDNA2 NPUs that targets transformer linear layers in quantized LLM inference. TileFuse brings practical low-bit formats such as AWQ-style W4A16 and W8A16 directly onto XDNA2, rather than forcing the model to be reshaped around an NPU-specific quantization scheme. TileFuse co-designs weight layout, metadata placement, mixed-precision microkernels, and array-level dataflow. Specifically, it fuses unpacking, dequantization, and GEMM/GEMV execution into a single kernel flow, introduces an interleaved pre-tiling layout that supports GEMM dimensions up to 32K, and redesigns GEMV dataflow to utilize the full 4x8 AIE array. Across kernel-level evaluations, TileFuse improves performance by up to 121.6% for GEMM and 281% for GEMV over full-precision baselines, while delivering more than 2x performance and energy-efficiency gains over strong iGPU baselines on GEMM. In end-to-end LLM experiments on Ryzen AI laptops, TileFuse achieves up to 2.0x lower prefilling latency with more than 64.6% lower energy consumption. Together, these results show that XDNA2 is a practical target for AWQ-style edge LLM inference and that native NPU support for off-the-shelf quantization can make NPUs substantially more usable in real client deployments.

24.
arXiv (CS.CV) 2026-06-17

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

25.
arXiv (CS.CL) 2026-06-19

From Construction to Injection: Edit-Based Fingerprints for Large Language Models

Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse. In black-box deployment, verification is hindered by defensive filtering of suspected fingerprint queries, as well as by downstream model modifications that may weaken embedded ownership evidence. These risks require fingerprints to be robust in both construction and injection. For construction, prior paradigms face an imperceptibility trade-off: natural-language fingerprints may be accidentally activated, whereas garbled fingerprints are statistically exposed and easier to filter. For injection, existing methods struggle to preserve persistent trigger–target behaviors under model modification. We propose an end-to-end injected fingerprinting framework to address these challenges. Code-mixing Fingerprints (CF) use lowest-perplexity code-mixing under a high-complexity constraint to mitigate this two-sided imperceptibility trade-off. Multi-Candidate Editing (MCEdit) constructs structurally redundant, margin-separated trigger–target mappings to enable graceful degradation under model modification. Extensive evaluations on imperceptibility, detectability, and harmlessness demonstrate robust ownership verification with negligible impact on utility.