{"total":23,"rows":[{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2602.03396","title":"Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.03168","title":"Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.03510","title":"Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2505.12566","title":"HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routing","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2605.11260","title":"Curriculum Learning-Guided Progressive Distillation in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.26676","title":"FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.37717","title":"Predictive Geometry of Hidden Trajectories in Transformers","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.10990","title":"Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.15322","title":"SuperAI: Merging Capabilities Across Heterogeneous Foundation Models","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}