{"total":14,"rows":[{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"id":"2406.09308","title":"Transformers meet Neural Algorithmic Reasoners","created":"2024-06-13","cited_by_count":13,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2410.09489","title":"Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks","created":"2024-10-12","cited_by_count":9,"area":"lr"},{"id":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2311.07311","title":"Do large language models and humans have similar behaviors in causal inference with script knowledge?","created":"2023-11-13","cited_by_count":3,"area":"lr"},{"id":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","cited_by_count":3,"area":"lr"},{"id":"2511.17171","title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2608.04132","title":"RUTA: Principled Visual Token Allocation via Rate-Utility Optimization","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.17993","title":"GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2602.16188","title":"Deep TPC: Temporal-Prior Conditioning for Time Series Forecasting","created":"2026-02-18","cited_by_count":0,"area":"lr"},{"id":"2608.28762","title":"Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering","created":"2026-08-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}