{"total":17,"rows":[{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169,"area":null},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94,"area":null},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2208.08349","title":"Open Long-Tailed Recognition in a Dynamic World","created":"2022-08-17","cited_by_count":21,"area":null},{"id":"2507.21160","title":"Handling Out-of-Distribution Data: A Survey","created":"2025-07-25","cited_by_count":14,"area":null},{"id":"2303.04554","title":"RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps","created":"2023-03-08","cited_by_count":12,"area":null},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2406.11739","title":"V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2503.06368","title":"VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2503.18430","title":"CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2608.30247","title":"OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}