{"total":18,"rows":[{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2508.10395","title":"XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization","created":"2025-08-14","cited_by_count":4,"area":"inference"},{"id":"2505.22179","title":"Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design","created":"2025-05-28","cited_by_count":3,"area":"inference"},{"id":"2508.12590","title":"Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding","created":"2025-08-18","cited_by_count":1,"area":"inference"},{"id":"2509.19368","title":"Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding","created":"2025-09-19","cited_by_count":1,"area":"inference"},{"id":"2605.02888","title":"SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection","created":"2026-05-04","cited_by_count":0,"area":"inference"},{"id":"2605.26558","title":"Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2606.24957","title":"Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding","created":"2026-06-23","cited_by_count":0,"area":"inference"},{"id":"2607.16248","title":"High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration","created":"2026-06-27","cited_by_count":0,"area":"inference"},{"id":"2607.24260","title":"KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems","created":"2026-07-27","cited_by_count":0,"area":"inference"},{"id":"2608.05926","title":"BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network Edge","created":"2026-08-06","cited_by_count":0,"area":"inference"},{"id":"2608.30252","title":"Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.18005","title":"A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality","created":"2026-09-16","cited_by_count":0,"area":"inference"},{"id":"2610.02800","title":"BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.13202","title":"S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding","created":"2026-10-09","cited_by_count":0,"area":"inference"}],"next_cursor":null}