{"total":19,"rows":[{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68,"area":null},{"id":"2412.13810","title":"CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers","created":"2024-12-18","cited_by_count":40,"area":null},{"id":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32,"area":null},{"id":"2411.17673","title":"SketchAgent: Language-Driven Sequential Sketch Generation","created":"2024-11-26","cited_by_count":31,"area":null},{"id":"2503.11509","title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","created":"2025-03-14","cited_by_count":24,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2404.12500","title":"UIClip: A Data-driven Model for Assessing User Interface Design","created":"2024-04-18","cited_by_count":14,"area":null},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2410.00201","title":"DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2506.00003","title":"Probing Audio-Generation Capabilities of Text-Based Language Models","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2505.00975","title":"Generating Animated Layouts as Structured Text Representations","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2507.12808","title":"Large Language Models' Internal Perception of Symbolic Music","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.14149","title":"An Exploratory Study on Abstract Images and Visual Representations Learned from Them","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2603.19515","title":"ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}