{"list":"other","total":60,"rows":[{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2403.00231","title":"Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models","created":"2024-03-01","cited_by_count":139},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75},{"id":"2308.03349","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","created":"2023-08-07","cited_by_count":68},{"id":"2108.07344","title":"IsoScore: Measuring the Uniformity of Embedding Space Utilization","created":"2021-08-16","cited_by_count":53},{"id":"2405.08807","title":"SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation","created":"2024-05-14","cited_by_count":48},{"id":"2107.00152","title":"Controllable Open-ended Question Generation with A New Question Type Ontology","created":"2021-07-01","cited_by_count":36},{"id":"2010.01657","title":"Inquisitive Question Generation for High Level Text Comprehension","created":"2020-10-04","cited_by_count":32},{"id":"2306.00738","title":"ReFACT: Updating Text-to-Image Models by Editing the Text Encoder","created":"2023-06-01","cited_by_count":32},{"id":"2505.13444","title":"ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models","created":"2025-05-19","cited_by_count":32},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30},{"id":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30},{"id":"2301.08968","title":"The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation","created":"2023-01-21","cited_by_count":25},{"id":"2501.07391","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","created":"2025-01-13","cited_by_count":23},{"id":"2502.12317","title":"Can Language Models Learn Typologically Implausible Languages?","created":"2025-02-17","cited_by_count":23},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22},{"id":"2111.00701","title":"Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections","created":"2021-11-01","cited_by_count":19},{"id":"2310.14520","title":"QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing","created":"2023-10-23","cited_by_count":19},{"id":"2502.03201","title":"SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels","created":"2025-02-05","cited_by_count":17},{"id":"2502.15969","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","created":"2025-02-21","cited_by_count":16},{"id":"1605.04951","title":"Viziometrics: Analyzing Visual Information in the Scientific Literature","created":"2016-05-16","cited_by_count":15},{"id":"2210.01963","title":"COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models","created":"2022-10-05","cited_by_count":15},{"id":"2405.05506","title":"Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias","created":"2024-05-09","cited_by_count":15},{"id":"2305.10387","title":"Elaborative Simplification as Implicit Questions Under Discussion","created":"2023-05-17","cited_by_count":14},{"id":"2210.05905","title":"Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion","created":"2022-10-12","cited_by_count":13},{"id":"2504.09373","title":"QUDsim: Quantifying Discourse Similarities in LLM-Generated Text","created":"2025-04-12","cited_by_count":13},{"id":"2305.19358","title":"Stable Anisotropic Regularization","created":"2023-05-30","cited_by_count":12},{"id":"2311.18129","title":"Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices","created":"2023-11-29","cited_by_count":11},{"id":"2406.08398","title":"cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers","created":"2024-06-12","cited_by_count":11},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11},{"id":"2508.13650","title":"CRISP: Persistent Concept Unlearning via Sparse Autoencoders","created":"2025-08-19","cited_by_count":11},{"id":"1901.11429","title":"Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements","created":"2019-01-31","cited_by_count":10},{"id":"2507.10787","title":"Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers","created":"2025-07-14","cited_by_count":10},{"id":"2307.14991","title":"Multilingual Code Co-Evolution Using Large Language Models","created":"2023-07-27","cited_by_count":9},{"id":"2506.03902","title":"The Harmonic Structure of Information Contours","created":"2025-06-04","cited_by_count":9},{"id":"2511.08598","title":"OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking","created":"2025-10-31","cited_by_count":9},{"id":"2404.10917","title":"Which questions should I answer? Salience Prediction of Inquisitive Questions","created":"2024-04-16","cited_by_count":8},{"id":"2010.02494","title":"Help! Need Advice on Identifying Advice","created":"2020-10-06","cited_by_count":6},{"id":"2307.05435","title":"One-Versus-Others Attention: Scalable Multimodal Integration for Biomedical Data","created":"2023-07-11","cited_by_count":6},{"id":"2412.12072","title":"Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats","created":"2024-12-16","cited_by_count":6},{"id":"2507.13328","title":"Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It","created":"2025-07-17","cited_by_count":6},{"id":"2209.06687","title":"How people talk about each other: Modeling Generalized Intergroup Bias and Emotion","created":"2022-09-14","cited_by_count":5},{"id":"2405.00955","title":"Recovering Labels from Local Updates in Federated Learning","created":"2024-05-02","cited_by_count":5},{"id":"2405.14619","title":"exLong: Generating Exceptional Behavior Tests with Large Language Models","created":"2024-05-23","cited_by_count":4},{"id":"2410.07951","title":"Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions","created":"2024-10-10","cited_by_count":3},{"id":"2507.03165","title":"PiCME: Pipeline for Contrastive Modality Evaluation and Encoding in the MIMIC Dataset","created":"2025-07-03","cited_by_count":3},{"id":"2502.19395","title":"Fast and Accurate Antibody Sequence Design via Structure Retrieval","created":"2025-02-11","cited_by_count":2},{"id":"2602.19217","title":"Questions beyond Pixels: Integrating Commonsense Knowledge in Visual Question Generation for Remote Sensing","created":"2026-02-22","cited_by_count":2},{"id":"2209.06315","title":"Inline Tests","created":"2022-09-13","cited_by_count":1},{"id":"2305.13486","title":"pytest-inline: An Inline Testing Tool for Python","created":"2023-05-22","cited_by_count":1},{"id":"2502.19391","title":"Towards More Accurate Full-Atom Antibody Co-Design","created":"2025-02-11","cited_by_count":1},{"id":"2509.21606","title":"Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection","created":"2025-09-25","cited_by_count":1},{"id":"2510.24538","title":"Dark & Stormy: Modeling Humor in Sentences from the Bulwer-Lytton Fiction Contest","created":"2025-10-28","cited_by_count":1},{"id":"2602.19224","title":"Knowledge-aware Visual Question Generation for Remote Sensing Images","created":"2026-02-22","cited_by_count":1}],"next_cursor":null}