{"list":"other","total":80,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267},{"id":"2402.09181","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","created":"2024-02-14","cited_by_count":184},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123},{"id":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108},{"id":"2412.12507","title":"3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting","created":"2024-12-17","cited_by_count":88},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70},{"id":"2412.15867","title":"IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing","created":"2024-12-20","cited_by_count":54},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52},{"id":"2410.08017","title":"Fast Feedforward 3D Gaussian Splatting Compression","created":"2024-10-10","cited_by_count":52},{"id":"2401.16355","title":"PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology","created":"2024-01-29","cited_by_count":43},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43},{"id":"2412.19282","title":"Reflective Gaussian Splatting","created":"2024-12-26","cited_by_count":42},{"id":"2403.19615","title":"SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing","created":"2024-03-28","cited_by_count":41},{"id":"2503.18402","title":"DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds","created":"2025-03-24","cited_by_count":38},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37},{"id":"2405.05256","title":"THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models","created":"2024-05-08","cited_by_count":36},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36},{"id":"2503.12772","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","created":"2025-03-17","cited_by_count":30},{"id":"2411.16778","title":"GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis","created":"2024-11-25","cited_by_count":29},{"id":"2503.05082","title":"Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs","created":"2025-03-07","cited_by_count":29},{"id":"2504.20378","title":"Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views","created":"2025-04-29","cited_by_count":26},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25},{"id":"2412.06250","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","created":"2024-12-09","cited_by_count":24},{"id":"2412.12096","title":"PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting","created":"2024-12-16","cited_by_count":24},{"id":"2506.10857","title":"VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos","created":"2025-06-12","cited_by_count":24},{"id":"2405.02386","title":"Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids","created":"2024-05-03","cited_by_count":23},{"id":"2410.24204","title":"GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering","created":"2024-10-31","cited_by_count":22},{"id":"2405.20283","title":"TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes","created":"2024-05-30","cited_by_count":21},{"id":"2504.00219","title":"LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors","created":"2025-03-31","cited_by_count":21},{"id":"2410.08107","title":"IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera","created":"2024-10-10","cited_by_count":20},{"id":"2504.01957","title":"Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting","created":"2025-04-02","cited_by_count":20},{"id":"2507.20519","title":"AgroBench: Vision-Language Model Benchmark in Agriculture","created":"2025-07-28","cited_by_count":20},{"id":"2506.23479","title":"Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting","created":"2025-06-30","cited_by_count":18},{"id":"2503.13176","title":"DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction","created":"2025-03-17","cited_by_count":16},{"id":"2505.15185","title":"MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models","created":"2025-05-21","cited_by_count":16},{"id":"2312.10034","title":"SlimmeRF: Slimmable Radiance Fields","created":"2023-12-15","cited_by_count":15},{"id":"2410.11682","title":"SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars","created":"2024-10-15","cited_by_count":15},{"id":"2411.00144","title":"Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis","created":"2024-10-31","cited_by_count":14},{"id":"2506.23563","title":"MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI","created":"2025-06-30","cited_by_count":14},{"id":"2411.15582","title":"EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting","created":"2024-11-23","cited_by_count":13},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13},{"id":"2507.08136","title":"RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration","created":"2025-07-10","cited_by_count":13},{"id":"2507.15629","title":"Gaussian Splatting with Discretized SDF for Relightable Assets","created":"2025-07-21","cited_by_count":13},{"id":"2502.09563","title":"Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction","created":"2025-02-13","cited_by_count":11},{"id":"2412.16604","title":"OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities","created":"2024-12-21","cited_by_count":10},{"id":"2503.16710","title":"4D Gaussian Splatting SLAM","created":"2025-03-20","cited_by_count":10},{"id":"2503.18682","title":"Hardware-Rasterized Ray-Based Gaussian Splatting","created":"2025-03-24","cited_by_count":10},{"id":"2504.06606","title":"Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program","created":"2025-04-09","cited_by_count":10},{"id":"2506.21401","title":"Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction","created":"2025-06-26","cited_by_count":10},{"id":"2510.16641","title":"MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models","created":"2025-10-18","cited_by_count":10},{"id":"2503.10079","title":"Information Density Principle for MLLM Benchmarks","created":"2025-03-13","cited_by_count":9},{"id":"2405.17351","title":"DOF-GS:Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal","created":"2024-05-27","cited_by_count":8},{"id":"2406.04251","title":"Improving Gaussian Splatting with Localized Points Management","created":"2024-06-06","cited_by_count":8},{"id":"2502.01846","title":"UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping","created":"2025-02-03","cited_by_count":8},{"id":"2507.16403","title":"ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering","created":"2025-07-22","cited_by_count":8},{"id":"2509.17040","title":"From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning","created":"2025-09-21","cited_by_count":8},{"id":"2509.19726","title":"PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction","created":"2025-09-24","cited_by_count":8},{"id":"2406.09105","title":"INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance","created":"2024-06-13","cited_by_count":7},{"id":"2503.05332","title":"CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images","created":"2025-03-07","cited_by_count":7},{"id":"2410.01535","title":"GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians","created":"2024-10-02","cited_by_count":6},{"id":"2503.00746","title":"DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting","created":"2025-03-02","cited_by_count":6},{"id":"2503.06553","title":"ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges","created":"2025-03-09","cited_by_count":5},{"id":"2503.16856","title":"MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers","created":"2025-03-21","cited_by_count":5},{"id":"2503.19232","title":"HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting","created":"2025-03-25","cited_by_count":5},{"id":"2503.05182","title":"MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions","created":"2025-03-07","cited_by_count":4},{"id":"2503.17491","title":"Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping","created":"2025-03-21","cited_by_count":4},{"id":"2506.04174","title":"FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting","created":"2025-06-04","cited_by_count":3},{"id":"2507.07709","title":"One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models","created":"2025-07-10","cited_by_count":1}],"next_cursor":null}