{"list":"other","total":51,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2508.00083","title":"A Survey on Code Generation with LLM-based Agents","created":"2025-07-31","cited_by_count":106},{"id":"2501.06598","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","created":"2025-01-11","cited_by_count":92},{"id":"2504.06263","title":"OmniSVG: A Unified Scalable Vector Graphics Generation Model","created":"2025-04-08","cited_by_count":74},{"id":"2301.09043","title":"CodeScore: Evaluating Code Generation by Learning Code Execution","created":"2023-01-22","cited_by_count":67},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66},{"id":"2505.19713","title":"CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward","created":"2025-05-26","cited_by_count":56},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45},{"id":"2502.08636","title":"Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models","created":"2025-02-12","cited_by_count":38},{"id":"2504.15485","title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","created":"2025-04-21","cited_by_count":38},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35},{"id":"2411.11916","title":"From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing","created":"2024-11-18","cited_by_count":31},{"id":"2412.12693","title":"SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation","created":"2024-12-17","cited_by_count":31},{"id":"2509.01790","title":"Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs","created":"2025-09-01","cited_by_count":30},{"id":"2510.01174","title":"Code2Video: A Code-centric Paradigm for Educational Video Generation","created":"2025-10-01","cited_by_count":27},{"id":"2502.03214","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","created":"2025-02-05","cited_by_count":25},{"id":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24},{"id":"2503.11509","title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","created":"2025-03-14","cited_by_count":24},{"id":"2507.05269","title":"CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","created":"2025-07-03","cited_by_count":24},{"id":"2502.11859","title":"Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics","created":"2025-02-17","cited_by_count":23},{"id":"2505.22016","title":"PanoWan: Lifting Diffusion Video Generation Models to 360{\\deg} with Latitude/Longitude-aware Mechanisms","created":"2025-05-28","cited_by_count":23},{"id":"2509.04013","title":"On Robustness and Reliability of Benchmark-Based Evaluation of LLMs","created":"2025-09-04","cited_by_count":23},{"id":"2602.03828","title":"AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations","created":"2026-02-03","cited_by_count":23},{"id":"2504.20648","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","created":"2025-04-29","cited_by_count":21},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21},{"id":"2505.19015","title":"Can Multimodal Large Language Models Understand Spatial Relations?","created":"2025-05-25","cited_by_count":20},{"id":"2503.23573","title":"DASH: Detection and Assessment of Systematic Hallucinations of VLMs","created":"2025-03-30","cited_by_count":14},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14},{"id":"2503.19355","title":"ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models","created":"2025-03-25","cited_by_count":13},{"id":"2505.17653","title":"GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs","created":"2025-05-23","cited_by_count":13},{"id":"2507.19969","title":"Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text","created":"2025-07-26","cited_by_count":12},{"id":"2502.17775","title":"FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks","created":"2025-02-25","cited_by_count":9},{"id":"2409.09318","title":"ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models","created":"2024-09-14","cited_by_count":8},{"id":"2410.18652","title":"$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation","created":"2024-10-24","cited_by_count":6},{"id":"2505.11618","title":"Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges","created":"2025-05-16","cited_by_count":4},{"id":"2508.16644","title":"CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance","created":"2025-08-18","cited_by_count":4},{"id":"2511.22490","title":"SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts","created":"2025-11-27","cited_by_count":4},{"id":"2603.13251","title":"ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation","created":"2026-02-24","cited_by_count":2}],"next_cursor":null}