{"total":18,"rows":[{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2405.14696","title":"A Declarative System for Optimizing AI Workloads","created":"2024-05-23","cited_by_count":37,"area":null},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2401.12522","title":"BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models","created":"2024-01-23","cited_by_count":13,"area":null},{"id":"2410.05165","title":"Efficient Inference for Large Language Model-based Generative Recommendation","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2412.10418","title":"Constrained Decoding with Speculative Lookaheads","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2407.11055","title":"Knowledge boosting during low-latency inference","created":"2024-07-09","cited_by_count":4,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"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":"2511.15618","title":"FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2505.15252","title":"An Efficient Private GPT Never Autoregressively Decodes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2601.22132","title":"Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.23266","title":"Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2506.12204","title":"Semantic Scheduling for LLM Inference","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2603.25463","title":"CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}