{"total":23,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164,"area":null},{"id":"2406.15007","title":"RouteFinder: Towards Foundation Models for Vehicle Routing Problems","created":"2024-06-21","cited_by_count":55,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2404.03608","title":"Sailor: Open Language Models for South-East Asia","created":"2024-04-04","cited_by_count":19,"area":null},{"id":"2410.18565","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2405.16397","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","created":"2024-05-26","cited_by_count":14,"area":null},{"id":"2601.11579","title":"Bielik 11B v3: Multilingual Large Language Model for European Languages","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2308.16475","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","created":"2023-08-31","cited_by_count":5,"area":null},{"id":"2505.02550","title":"Bielik v3 Small: Technical Report","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2604.03582","title":"Simple yet Effective: Low-Rank Spatial Attention for Neural Operators","created":"2026-04-04","cited_by_count":4,"area":null},{"id":"2505.22758","title":"FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2605.06916","title":"Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2604.22260","title":"Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2512.10393","title":"Cross-modal Retrieval Models for Stripped Binary Analysis","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2507.18009","title":"GRR-CoCa: Leveraging LLM Mechanisms in Multimodal Model Architectures","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2510.21525","title":"A Unified Model for Multi-Task Drone Routing in Post-Disaster Road Assessment","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2603.03517","title":"MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.14521","title":"Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}