{"total":30,"rows":[{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2406.03751","title":"Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2504.10685","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results","created":"2025-04-14","cited_by_count":25,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11,"area":null},{"id":"2408.09856","title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2502.08020","title":"Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2601.21135","title":"TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2406.15570","title":"DEM: Distribution Edited Model for Training with Mixed Data Distributions","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2409.15764","title":"Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2502.15499","title":"Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2607.08077","title":"Modular Pretraining Enables Access Control","created":"2026-07-09","cited_by_count":3,"area":null},{"id":"2410.02744","title":"Neutral Residues: Revisiting Adapters for Model Extension","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2412.05644","title":"Mixture of Hidden-Dimensions Transformer","created":"2024-12-07","cited_by_count":2,"area":null},{"id":"2509.15651","title":"Toward Efficient Influence Function: Dropout as a Compression Tool","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2503.20939","title":"Hacia la interpretabilidad de la detecci\\'on anticipada de riesgos de depresi\\'on utilizando grandes modelos de lenguaje","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2505.23846","title":"Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.06807","title":"MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.05779","title":"Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecasting","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2602.22592","title":"pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2606.19195","title":"Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.05137","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}