{"total":17,"rows":[{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2411.14794","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","created":"2024-11-22","cited_by_count":65,"area":"lr"},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59,"area":"lr"},{"id":"2410.02763","title":"Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos","created":"2024-10-03","cited_by_count":38,"area":"lr"},{"id":"2410.06166","title":"Temporal Reasoning Transfer from Text to Video","created":"2024-10-08","cited_by_count":38,"area":"lr"},{"id":"2210.12887","title":"Retrieval Augmentation for Commonsense Reasoning: A Unified Approach","created":"2022-10-23","cited_by_count":14,"area":"lr"},{"id":"2604.05546","title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","created":"2026-04-07","cited_by_count":9,"area":"lr"},{"id":"2210.11708","title":"Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2503.10691","title":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2307.06844","title":"Garbage in, garbage out: Zero-shot detection of crime using Large Language Models","created":"2023-07-04","cited_by_count":5,"area":"lr"},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2505.10292","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","created":"2025-05-15","cited_by_count":3,"area":"lr"},{"id":"2604.05887","title":"HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2606.14782","title":"Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2603.14426","title":"GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos","created":"2026-03-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}