{"total":29,"rows":[{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66,"area":null},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56,"area":null},{"id":"2412.14642","title":"Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation","created":"2024-12-19","cited_by_count":25,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2602.11144","title":"GENIUS: Generative Fluid Intelligence Evaluation Suite","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2510.15280","title":"Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2602.04849","title":"El Agente Estructural: An Artificially Intelligent Molecular Editor","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2506.13051","title":"Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2603.06700","title":"SIQA: Toward Reliable Scientific Image Quality Assessment","created":"2026-03-05","cited_by_count":4,"area":null},{"id":"2505.12650","title":"AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2510.20095","title":"BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2506.10912","title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2608.21504","title":"ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation","created":"2026-08-21","cited_by_count":2,"area":null},{"id":"2508.05427","title":"Large Language Models Transform Organic Synthesis From Reaction Prediction to Automation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2605.05832","title":"MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.03401","title":"Towards Characterizing Scientific Image Utility and Upgradability","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.03525","title":"MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.09100","title":"Real Data Closes Synthetic-to-Real Gap in Optical Chemical Structure Recognition","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2504.14633","title":"Harnessing Generative LLMs for Enhanced Financial Event Entity Extraction Performance","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2512.11901","title":"CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.21527","title":"Sustainable Materials Discovery in the Era of Artificial Intelligence","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.11924","title":"Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.12181","title":"MolDeTox: Evaluating Language Model's Stepwise Fragment Editing for Molecular Detoxification","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17214","title":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2608.22183","title":"VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSR","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.33608","title":"Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37568","title":"Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02242","title":"RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19780","title":"LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}