{"total":18,"rows":[{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10,"area":null},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2512.17093","title":"A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving","created":"2025-12-18","cited_by_count":4,"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":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2601.22662","title":"Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2607.27578","title":"What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2510.18162","title":"Automatic Prompt Generation via Adaptive Selection of Prompting Techniques","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.10054","title":"Parallel Decoder Transformer: Planner-Conditioned Latent Coordination for Model-Intrinsic Parallel Generation","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2605.18697","title":"PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.33477","title":"Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.03296","title":"JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}