{"total":24,"rows":[{"id":"2203.16487","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","created":"2022-03-30","cited_by_count":171,"area":"inference"},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124,"area":"inference"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2106.04970","title":"Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding","created":"2021-06-09","cited_by_count":53,"area":"inference"},{"id":"2410.20771","title":"MrT5: Dynamic Token Merging for Efficient Byte-level Language Models","created":"2024-10-28","cited_by_count":28,"area":"inference"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2502.05202","title":"Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies","created":"2025-01-31","cited_by_count":20,"area":"inference"},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"id":"2508.13666","title":"The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget","created":"2025-08-19","cited_by_count":12,"area":"inference"},{"id":"2502.16880","title":"CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter","created":"2025-02-24","cited_by_count":9,"area":"inference"},{"id":"2104.11897","title":"Modeling Coverage for Non-Autoregressive Neural Machine Translation","created":"2021-04-24","cited_by_count":4,"area":"inference"},{"id":"2309.09546","title":"Training dynamic models using early exits for automatic speech recognition on resource-constrained devices","created":"2023-09-18","cited_by_count":3,"area":"inference"},{"id":"2503.14153","title":"Speculative Decoding for Verilog: Speed and Quality, All in One","created":"2025-03-18","cited_by_count":2,"area":"inference"},{"id":"2505.22757","title":"Pre-Training Curriculum for Multi-Token Prediction in Language Models","created":"2025-05-28","cited_by_count":2,"area":"inference"},{"id":"2511.14806","title":"MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging","created":"2025-11-17","cited_by_count":2,"area":"inference"},{"id":"2605.11774","title":"From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction","created":"2026-05-12","cited_by_count":2,"area":"inference"},{"id":"2607.21179","title":"Out of Sight, Still in Mind: Token Compression for Omni-LLMs","created":"2026-07-23","cited_by_count":2,"area":"inference"},{"id":"2405.17376","title":"Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients","created":"2024-05-27","cited_by_count":1,"area":"inference"},{"id":"2506.18035","title":"Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices","created":"2025-06-22","cited_by_count":1,"area":"inference"},{"id":"2512.00719","title":"SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving","created":"2025-11-30","cited_by_count":1,"area":"inference"},{"id":"2605.09630","title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","created":"2026-05-10","cited_by_count":1,"area":"inference"},{"id":"2510.00982","title":"Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting","created":"2025-10-01","cited_by_count":0,"area":"inference"},{"id":"2510.15545","title":"TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs","created":"2025-10-17","cited_by_count":0,"area":"inference"},{"id":"2610.13605","title":"zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss","created":"2026-10-09","cited_by_count":0,"area":"inference"}],"next_cursor":null}