{"total":14,"rows":[{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2502.05863","title":"Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education","created":"2025-02-09","cited_by_count":13,"area":null},{"id":"2509.09666","title":"Unified Multimodal Models as Auto-Encoders","created":"2025-09-11","cited_by_count":13,"area":null},{"id":"2402.17532","title":"Retrieval is Accurate Generation","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2505.17050","title":"Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2508.09912","title":"E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2504.12314","title":"How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2505.15287","title":"GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2604.18326","title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2509.06566","title":"Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2601.01749","title":"MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2604.20851","title":"Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2605.10009","title":"Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":null}