PyTorchKR Papers

최신 논문

총 139,333편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2505.05568공식 코드 · Papers with Code

Griffin: Towards a Graph-Centric Relational Database Foundation Model

We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Griffin unifies the data encoder and task decoder to handle diverse tasks. Additionally, we enhance the architecture by incorporating a cross-attention module and a novel aggregator. Griffin utilizes pretraining on both single-table and RDB datasets, employing advanced encoders for categorical, numerical, and metadata features, along with innovative components such as cross-attention modules and enhanced message-passing neural networks (MPNNs) to capture the complexities of relational data. Evaluated on large-scale, heterogeneous, and temporal graphs extracted from RDBs across various domains (spanning over 150 million nodes), Griffin demonstrates superior or comparable performance to individually trained models, excels in low-data scenarios, and shows strong transferability with similarity and diversity in pretraining across new datasets and tasks, highlighting its potential as a universally applicable foundation model for RDBs. Code available at https://github.com/yanxwb/Griffin.

arXiv:2505.05538공식 코드 · Papers with Code

Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet

Electrocardiogram (ECG) classification is crucial for automated cardiac disease diagnosis, yet existing methods often struggle to capture local morphological details and long-range temporal dependencies simultaneously. To address these challenges, we propose Cardioformer, a novel multi-granularity hybrid model that integrates cross-channel patching, hierarchical residual learning, and a two-stage self-attention mechanism. Cardioformer first encodes multi-scale token embeddings to capture fine-grained local features and global contextual information and then selectively fuses these representations through intra- and inter-granularity self-attention. Extensive evaluations on three benchmark ECG datasets under subject-independent settings demonstrate that model consistently outperforms four state-of-the-art baselines. Our Cardioformer model achieves the AUROC of 96.34$\pm$0.11, 89.99$\pm$0.12, and 95.59$\pm$1.66 in MIMIC-IV, PTB-XL and PTB dataset respectively outperforming PatchTST, Reformer, Transformer, and Medformer models. It also demonstrates strong cross-dataset generalization, achieving 49.18% AUROC on PTB and 68.41% on PTB-XL when trained on MIMIC-IV. These findings underscore the potential of Cardioformer to advance automated ECG analysis, paving the way for more accurate and robust cardiovascular disease diagnosis. We release the source code at https://github.com/KMobin555/Cardioformer.

arXiv:2504.04430공식 코드 · Papers with Code

AGITB: A Signal-Level Benchmark for Evaluating Artificial General Intelligence

Despite remarkable progress in machine learning, current AI systems continue to fall short of true human-like intelligence. While Large Language Models (LLMs) excel in pattern recognition and response generation, they lack genuine understanding - an essential hallmark of Artificial General Intelligence (AGI). Existing AGI evaluation methods fail to offer a practical, gradual, and informative metric. This paper introduces the Artificial General Intelligence Test Bed (AGITB), comprising twelve rigorous tests that form a signal-processing-level foundation for the potential emergence of cognitive capabilities. AGITB evaluates intelligence through a model's ability to predict binary signals across time without relying on symbolic representations or pretraining. Unlike high-level tests grounded in language or perception, AGITB focuses on core computational invariants reflective of biological intelligence, such as determinism, sensitivity, and generalisation. The test bed assumes no prior bias, operates independently of semantic meaning, and ensures unsolvability through brute force or memorization. While humans pass AGITB by design, no current AI system has met its criteria, making AGITB a compelling benchmark for guiding and recognizing progress toward AGI.

arXiv:2503.11711공식 코드 · Papers with Code

Privacy-Preserved Automated Scoring using Federated Learning for Educational Research

Data privacy remains a critical concern in educational research, requiring strict adherence to ethical standards and regulatory protocols. While traditional approaches rely on anonymization and centralized data collection, they often expose raw student data to security vulnerabilities and impose substantial logistical overhead. In this study, we propose a federated learning (FL) framework for automated scoring of educational assessments that eliminates the need to share sensitive data across institutions. Our approach leverages parameter-efficient fine-tuning of large language models (LLMs) with Low-Rank Adaptation (LoRA), enabling each client (school) to train locally while sharing only optimized model updates. To address data heterogeneity, we implement an adaptive weighted aggregation strategy that considers both client performance and data volume. We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline using NGSS-aligned multi-label science assessment data from nine middle schools. Results show that our model achieves the highest accuracy (94.5%) among FL approaches, and performs within 0.5-1.0 percentage points of the centralized model on these metrics. Additionally, it achieves comparable rubric-level scoring accuracy, with only a 1.3% difference in rubric match and a lower score deviation (MAE), highlighting its effectiveness in preserving both prediction quality and interpretability.

arXiv:2505.05848공식 코드 · Papers with Code

RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects

Modern 3D reconstruction and novel view synthesis approaches have demonstrated strong performance on scenes with opaque Lambertian objects. However, most assume straight light paths and therefore cannot properly handle refractive and reflective materials. Moreover, datasets specialized for these effects are limited, stymieing efforts to evaluate performance and develop suitable techniques. In this work, we introduce a synthetic RefRef dataset and benchmark for reconstructing scenes with refractive and reflective objects from posed images. Our dataset has 50 such objects of varying complexity, from single-material convex shapes to multi-material non-convex shapes, each placed in three different background types, resulting in 150 scenes. We also propose an oracle method that, given the object geometry and refractive indices, calculates accurate light paths for neural rendering, and an approach based on this that avoids these assumptions. We benchmark these against several state-of-the-art methods and show that all methods lag significantly behind the oracle, highlighting the challenges of the task and dataset.

arXiv:2505.05812공식 코드 · Papers with Code

Towards order of magnitude X-ray dose reduction in breast cancer imaging using phase contrast and deep denoising

Breast cancer is the most frequently diagnosed human cancer in the United States at present. Early detection is crucial for its successful treatment. X-ray mammography and digital breast tomosynthesis are currently the main methods for breast cancer screening. However, both have known limitations in terms of their sensitivity and specificity to breast cancers, while also frequently causing patient discomfort due to the requirement for breast compression. Breast computed tomography is a promising alternative, however, to obtain high-quality images, the X-ray dose needs to be sufficiently high. As the breast is highly radiosensitive, dose reduction is particularly important. Phase-contrast computed tomography (PCT) has been shown to produce higher-quality images at lower doses and has no need for breast compression. It is demonstrated in the present study that, when imaging full fresh mastectomy samples with PCT, deep learning-based image denoising can further reduce the radiation dose by a factor of 16 or more, without any loss of image quality. The image quality has been assessed both in terms of objective metrics, such as spatial resolution and contrast-to-noise ratio, as well as in an observer study by experienced medical imaging specialists and radiologists. This work was carried out in preparation for live patient PCT breast cancer imaging, initially at specialized synchrotron facilities.

arXiv:2505.05528공식 코드 · Papers with Code

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a critical concern. In this work, we introduce \textbf{X-Transfer}, a novel attack method that exposes a universal adversarial vulnerability in CLIP. X-Transfer generates a Universal Adversarial Perturbation (UAP) capable of deceiving various CLIP encoders and downstream VLMs across different samples, tasks, and domains. We refer to this property as \textbf{super transferability}--a single perturbation achieving cross-data, cross-domain, cross-model, and cross-task adversarial transferability simultaneously. This is achieved through \textbf{surrogate scaling}, a key innovation of our approach. Unlike existing methods that rely on fixed surrogate models, which are computationally intensive to scale, X-Transfer employs an efficient surrogate scaling strategy that dynamically selects a small subset of suitable surrogates from a large search space. Extensive evaluations demonstrate that X-Transfer significantly outperforms previous state-of-the-art UAP methods, establishing a new benchmark for adversarial transferability across CLIP models. The code is publicly available in our \href{https://github.com/HanxunH/XTransferBench}{GitHub repository}.

arXiv:2505.05522공식 코드 · Papers with Code

Continuous Thought Machines

Biological brains demonstrate complex neural activity, where the timing and interplay between neurons is critical to how brains process information. Most deep learning architectures simplify neural activity by abstracting away temporal dynamics. In this paper we challenge that paradigm. By incorporating neuron-level processing and synchronization, we can effectively reintroduce neural timing as a foundational element. We present the Continuous Thought Machine (CTM), a model designed to leverage neural dynamics as its core representation. The CTM has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique weight parameters to process a history of incoming signals; and (2) neural synchronization employed as a latent representation. The CTM aims to strike a balance between oversimplified neuron abstractions that improve computational efficiency, and biological realism. It operates at a level of abstraction that effectively captures essential temporal dynamics while remaining computationally tractable for deep learning. We demonstrate the CTM's strong performance and versatility across a range of challenging tasks, including ImageNet-1K classification, solving 2D mazes, sorting, parity computation, question-answering, and RL tasks. Beyond displaying rich internal representations and offering a natural avenue for interpretation owing to its internal process, the CTM is able to perform tasks that require complex sequential reasoning. The CTM can also leverage adaptive compute, where it can stop earlier for simpler tasks, or keep computing when faced with more challenging instances. The goal of this work is to share the CTM and its associated innovations, rather than pushing for new state-of-the-art results. To that end, we believe the CTM represents a significant step toward developing more biologically plausible and powerful artificial intelligence systems.

arXiv:2505.05156공식 코드 · Papers with Code

Regression-based Melody Estimation with Uncertainty Quantification

Existing machine learning models approach the task of melody estimation from polyphonic audio as a classification problem by discretizing the pitch values, which results in the loss of finer frequency variations present in the melody. To better capture these variations, we propose to approach this task as a regression problem. Apart from predicting only the pitch for a particular region in the audio, we also predict its uncertainty to enhance the trustworthiness of the model. To perform regression-based melody estimation, we propose three different methods that use histogram representation to model the pitch values. Such a representation requires the support range of the histogram to be continuous. The first two methods address the abrupt discontinuity between unvoiced and voiced frequency ranges by mapping them to a continuous range. The third method reformulates melody estimation as a fully Bayesian task, modeling voicing detection as a classification problem, and voiced pitch estimation as a regression problem. Additionally, we introduce a novel method to estimate the uncertainty from the histogram representation that correlates well with the deviation of the mean of the predicted distribution from the ground truth. Experimental results demonstrate that reformulating melody estimation as a regression problem significantly improves the performance over classification-based approaches. Comparing the proposed methods with a state-of-the-art regression model, it is observed that the Bayesian method performs the best at estimating both the melody and its associated uncertainty.

arXiv:2505.04752공식 코드 · Papers with Code

Towards a Vision-Language Episodic Memory Framework: Large-scale Pretrained Model-Augmented Hippocampal Attractor Dynamics

Modeling episodic memory (EM) remains a significant challenge in both neuroscience and AI, with existing models either lacking interpretability or struggling with practical applications. This paper proposes the Vision-Language Episodic Memory (VLEM) framework to address these challenges by integrating large-scale pretrained models with hippocampal attractor dynamics. VLEM leverages the strong semantic understanding of pretrained models to transform sensory input into semantic embeddings as the neocortex, while the hippocampus supports stable memory storage and retrieval through attractor dynamics. In addition, VLEM incorporates prefrontal working memory and the entorhinal gateway, allowing interaction between the neocortex and the hippocampus. To facilitate real-world applications, we introduce EpiGibson, a 3D simulation platform for generating episodic memory data. Experimental results demonstrate the VLEM framework's ability to efficiently learn high-level temporal representations from sensory input, showcasing its robustness, interpretability, and applicability in real-world scenarios.

arXiv:2505.04658공식 코드 · Papers with Code

Cross-organ all-in-one parallel compressed sensing magnetic resonance imaging

Recent advances in deep learning-based parallel compressed sensing magnetic resonance imaging (p-CSMRI) have significantly improved reconstruction quality. However, current p-CSMRI methods often require training separate deep neural network (DNN) for each organ due to anatomical variations, creating a barrier to developing generalized medical image reconstruction systems. To address this, we propose CAPNet (cross-organ all-in-one deep unfolding p-CSMRI network), a unified framework that implements a p-CSMRI iterative algorithm via three specialized modules: auxiliary variable module, prior module, and data consistency module. Recognizing that p-CSMRI systems often employ varying sampling ratios for different organs, resulting in organ-specific artifact patterns, we introduce an artifact generation submodule, which extracts and integrates artifact features into the data consistency module to enhance the discriminative capability of the overall network. For the prior module, we design an organ structure-prompt generation submodule that leverages structural features extracted from the segment anything model (SAM) to create cross-organ prompts. These prompts are strategically incorporated into the prior module through an organ structure-aware Mamba submodule. Comprehensive evaluations on a cross-organ dataset confirm that CAPNet achieves state-of-the-art reconstruction performance across multiple anatomical structures using a single unified model. Our code will be published at https://github.com/shibaoshun/CAPNet.

arXiv:2505.04331공식 코드 · Papers with Code

Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment

Individual brains exhibit striking structural and physiological heterogeneity, yet neural circuits can generate remarkably consistent functional properties across individuals, an apparent paradox in neuroscience. While recent studies have observed preserved neural representations in motor cortex through manual alignment across subjects, the zero-shot validation of such preservation and its generalization to more cortices remain unexplored. Here we present PNBA (Probabilistic Neural-Behavioral Representation Alignment), a new framework that leverages probabilistic modeling to address hierarchical variability across trials, sessions, and subjects, with generative constraints preventing representation degeneration. By establishing reliable cross-modal representational alignment, PNBA reveals robust preserved neural representations in monkey primary motor cortex (M1) and dorsal premotor cortex (PMd) through zero-shot validation. We further establish similar representational preservation in mouse primary visual cortex (V1), reflecting a general neural basis. These findings resolve the paradox of neural heterogeneity by establishing zero-shot preserved neural representations across cortices and species, enriching neural coding insights and enabling zero-shot behavior decoding.

arXiv:2505.03827공식 코드 · Papers with Code

MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation

Stress haunts people in modern society, which may cause severe health issues if left unattended. With social media becoming an integral part of daily life, leveraging social media to detect stress has gained increasing attention. While the majority of the work focuses on classifying stress states and stress categories, this study introduce a new task aimed at estimating more specific stressors (like exam, writing paper, etc.) through users' posts on social media. Unfortunately, the diversity of stressors with many different classes but a few examples per class, combined with the consistent arising of new stressors over time, hinders the machine understanding of stressors. To this end, we cast the stressor estimation problem within a practical scenario few-shot learning setting, and propose a novel meta-learning based stressor estimation framework that is enhanced by a meta-knowledge inheritance mechanism. This model can not only learn generic stressor context through meta-learning, but also has a good generalization ability to estimate new stressors with little labeled data. A fundamental breakthrough in our approach lies in the inclusion of the meta-knowledge inheritance mechanism, which equips our model with the ability to prevent catastrophic forgetting when adapting to new stressors. The experimental results show that our model achieves state-of-the-art performance compared with the baselines. Additionally, we construct a social media-based stressor estimation dataset that can help train artificial intelligence models to facilitate human well-being. The dataset is now public at \href{https://www.kaggle.com/datasets/xinwangcs/stressor-cause-of-mental-health-problem-dataset}{\underline{Kaggle}} and \href{https://huggingface.co/datasets/XinWangcs/Stressor}{\underline{Hugging Face}}.

arXiv:2505.03785공식 코드 · Papers with Code

mAIstro: an open-source multi-agentic system for automated end-to-end development of radiomics and deep learning models for medical imaging

Agentic systems built on large language models (LLMs) offer promising capabilities for automating complex workflows in healthcare AI. We introduce mAIstro, an open-source, autonomous multi-agentic framework for end-to-end development and deployment of medical AI models. The system orchestrates exploratory data analysis, radiomic feature extraction, image segmentation, classification, and regression through a natural language interface, requiring no coding from the user. Built on a modular architecture, mAIstro supports both open- and closed-source LLMs, and was evaluated using a large and diverse set of prompts across 16 open-source datasets, covering a wide range of imaging modalities, anatomical regions, and data types. The agents successfully executed all tasks, producing interpretable outputs and validated models. This work presents the first agentic framework capable of unifying data analysis, AI model development, and inference across varied healthcare applications, offering a reproducible and extensible foundation for clinical and research AI integration. The code is available at: https://github.com/eltzanis/mAIstro

arXiv:2504.21650공식 코드 · Papers with Code

HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation

The rapid advancement of diffusion models holds the promise of revolutionizing the application of VR and AR technologies, which typically require scene-level 4D assets for user experience. Nonetheless, existing diffusion models predominantly concentrate on modeling static 3D scenes or object-level dynamics, constraining their capacity to provide truly immersive experiences. To address this issue, we propose HoloTime, a framework that integrates video diffusion models to generate panoramic videos from a single prompt or reference image, along with a 360-degree 4D scene reconstruction method that seamlessly transforms the generated panoramic video into 4D assets, enabling a fully immersive 4D experience for users. Specifically, to tame video diffusion models for generating high-fidelity panoramic videos, we introduce the 360World dataset, the first comprehensive collection of panoramic videos suitable for downstream 4D scene reconstruction tasks. With this curated dataset, we propose Panoramic Animator, a two-stage image-to-video diffusion model that can convert panoramic images into high-quality panoramic videos. Following this, we present Panoramic Space-Time Reconstruction, which leverages a space-time depth estimation method to transform the generated panoramic videos into 4D point clouds, enabling the optimization of a holistic 4D Gaussian Splatting representation to reconstruct spatially and temporally consistent 4D scenes. To validate the efficacy of our method, we conducted a comparative analysis with existing approaches, revealing its superiority in both panoramic video generation and 4D scene reconstruction. This demonstrates our method's capability to create more engaging and realistic immersive environments, thereby enhancing user experiences in VR and AR applications.

arXiv:2504.17821공식 코드 · Papers with Code

VideoVista-CulturalLingo: 360$^\circ$ Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension

Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and predominantly feature videos rooted in Western cultural contexts. In this paper, we present VideoVista-CulturalLingo, the first video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension. Our work differs from existing benchmarks in the following ways: 1) Cultural diversity, incorporating cultures from China, North America, and Europe; 2) Multi-linguistics, with questions presented in Chinese and English-two of the most widely spoken languages; and 3) Broad domain, featuring videos sourced from hundreds of human-created domains. VideoVista-CulturalLingo contains 1,389 videos and 3,134 QA pairs, and we have evaluated 24 recent open-source or proprietary video large models. From the experiment results, we observe that: 1) Existing models perform worse on Chinese-centric questions than Western-centric ones, particularly those related to Chinese history; 2) Current open-source models still exhibit limitations in temporal understanding, especially in the Event Localization task, achieving a maximum score of only 45.2%; 3) Mainstream models demonstrate strong performance in general scientific questions, while open-source models demonstrate weak performance in mathematics.

arXiv:2504.17343공식 코드 · Papers with Code

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

The rapid growth of online video platforms, particularly live streaming services, has created an urgent need for real-time video understanding systems. These systems must process continuous video streams and respond to user queries instantaneously, presenting unique challenges for current Video Large Language Models (VideoLLMs). While existing VideoLLMs excel at processing complete videos, they face significant limitations in streaming scenarios due to their inability to handle dense, redundant frames efficiently. We introduce TimeChat-Online, a novel online VideoLLM that revolutionizes real-time video interaction. At its core lies our innovative Differential Token Drop (DTD) module, which addresses the fundamental challenge of visual redundancy in streaming videos. Drawing inspiration from human visual perception's Change Blindness phenomenon, DTD preserves meaningful temporal changes while filtering out static, redundant content between frames. Remarkably, our experiments demonstrate that DTD achieves an 82.8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance. To enable seamless real-time interaction, we present TimeChat-Online-139K, a comprehensive streaming video dataset featuring diverse interaction patterns including backward-tracing, current-perception, and future-responding scenarios. TimeChat-Online's unique Proactive Response capability, naturally achieved through continuous monitoring of video scene transitions via DTD, sets it apart from conventional approaches. Our extensive evaluation demonstrates TimeChat-Online's superior performance on streaming benchmarks (StreamingBench and OvOBench) and maintaining competitive results on long-form video tasks such as Video-MME and MLVU.

arXiv:2504.06148공식 코드 · Papers with Code

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual-text processing. However, existing static image-text benchmarks are insufficient for evaluating their dynamic perception and interactive reasoning abilities. We introduce Vision-centric Multiple Abilities Game Evaluation(V-MAGE), a novel game-based evaluation framework designed to systematically assess MLLMs' visual reasoning in interactive, continuous-space environments. V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios. These scenarios are set in free-form, visually complex environments that require models to interpret dynamic game states and make decisions based solely on visual input, thereby closely reflecting the conditions encountered by human players. To ensure robust and interpretable comparisons across models, V-MAGE employs a dynamic Elo-based ranking system that accounts for varying difficulty levels and task diversity. Benchmarking state-of-the-art MLLMs against human baselines reveals that while leading models approach human-level performance in simple tasks, their performance drops significantly in complex scenarios requiring advanced reasoning and task orchestration. This persistent performance gap highlights fundamental limitations in current MLLMs' ability to perform real-time, vision-grounded interactions. Through extensive analyses, we demonstrate the utility of V-MAGE in uncovering these limitations and providing actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings. Code is publicly available at https://github.com/CSU-JPG/V-MAGE.

arXiv:2504.03748공식 코드 · Papers with Code

TDBench: Benchmarking Vision-Language Models in Understanding Top-Down Images

The rapid emergence of Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling applications in scene comprehension and visual reasoning. While these models have been primarily evaluated and developed for front-view image understanding, their capabilities in interpreting top-down images have received limited attention, partly due to the scarcity of diverse top-down datasets and the challenges in collecting such data. In contrast, top-down vision provides explicit spatial overviews and improved contextual understanding of scenes, making it particularly valuable for tasks like autonomous navigation, aerial imaging, and spatial planning. In this work, we address this gap by introducing TDBench, a comprehensive benchmark for VLMs in top-down image understanding. TDBench is constructed from public top-down view datasets and high-quality simulated images, including diverse real-world and synthetic scenarios. TDBench consists of visual question-answer pairs across ten evaluation dimensions of image understanding. Moreover, we conduct four case studies that commonly happen in real-world scenarios but are less explored. By revealing the strengths and limitations of existing VLM through evaluation results, we hope TDBench to provide insights for motivating future research. Project homepage: https://github.com/Columbia-ICSL/TDBench

arXiv:2504.00939공식 코드 · Papers with Code

WikiVideo: Article Generation from Multiple Videos

We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple diverse videos about real-world events, such as natural disasters or political elections. Videos are intuitive sources for retrieval-augmented generation (RAG), but most contemporary RAG workflows focus heavily on text and existing methods for video-based summarization focus on low-level scene understanding rather than high-level event semantics. To close this gap, we introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims, facilitating the integration of video into RAG pipelines and enabling the creation of in-depth content that is grounded in multimodal sources. We further propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos. CAG leverages an iterative interaction between an r1-style reasoning model and a VideoLLM to draw higher level inferences about the target event than is possible with VideoLLMs alone, which fixate on low-level visual features. We benchmark state-of-the-art VideoLLMs and CAG in both oracle retrieval and RAG settings and find that CAG consistently outperforms alternative methods, while suggesting intriguing avenues for future work.