{"total":15,"rows":[{"id":"2409.17422","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","created":"2024-09-25","cited_by_count":39,"area":"inference"},{"id":"2504.06261","title":"Hogwild! Inference: Parallel LLM Generation via Concurrent Attention","created":"2025-04-08","cited_by_count":32,"area":"inference"},{"id":"2502.15470","title":"PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System","created":"2025-02-21","cited_by_count":20,"area":"inference"},{"id":"2503.00979","title":"Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs","created":"2025-03-02","cited_by_count":20,"area":"inference"},{"id":"2602.11812","title":"Predicting LLM Output Length via Entropy-Guided Representations","created":"2026-02-12","cited_by_count":9,"area":"inference"},{"id":"2511.00868","title":"FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management","created":"2025-11-02","cited_by_count":5,"area":"inference"},{"id":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2605.09329","title":"Test-Time Speculation","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2605.18165","title":"Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs","created":"2026-05-18","cited_by_count":1,"area":"inference"},{"id":"2505.04723","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","created":"2025-05-07","cited_by_count":0,"area":"inference"},{"id":"2510.07535","title":"OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs","created":"2025-10-08","cited_by_count":0,"area":"inference"},{"id":"2512.15550","title":"CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing","created":"2025-12-17","cited_by_count":0,"area":"inference"},{"id":"2608.19395","title":"HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads","created":"2026-08-19","cited_by_count":0,"area":"inference"},{"id":"2609.21172","title":"TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching","created":"2026-09-18","cited_by_count":0,"area":"inference"},{"id":"2610.05106","title":"SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling","created":"2026-10-04","cited_by_count":0,"area":"inference"}],"next_cursor":null}