{"total":14,"rows":[{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346,"area":null},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40,"area":null},{"id":"2308.14436","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2306.10231","title":"GLIMMER: generalized late-interaction memory reranker","created":"2023-06-17","cited_by_count":7,"area":null},{"id":"2506.01673","title":"GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2309.13059","title":"Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2404.02581","title":"Multi-Granularity Guided Fusion-in-Decoder","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2408.06333","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2310.18077","title":"Detrimental Contexts in Open-Domain Question Answering","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2510.08774","title":"Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings","created":"2025-10-09","cited_by_count":0,"area":null}],"next_cursor":null}