{"total":26,"rows":[{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13,"area":"inference"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2503.18773","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache","created":"2025-03-24","cited_by_count":8,"area":"inference"},{"id":"2601.01204","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-01-03","cited_by_count":7,"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":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2510.06175","title":"VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization","created":"2025-10-07","cited_by_count":4,"area":"inference"},{"id":"2505.20839","title":"FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration","created":"2025-05-27","cited_by_count":2,"area":"inference"},{"id":"2605.21226","title":"OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization","created":"2026-05-20","cited_by_count":2,"area":"inference"},{"id":"2608.02691","title":"Output-Aware Rotation for INT2 KV-Cache Quantization","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2608.04074","title":"Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms","created":"2026-08-04","cited_by_count":2,"area":"inference"},{"id":"2606.24033","title":"RoPE-Aware Bit Allocation for KV-Cache Quantization","created":"2026-06-23","cited_by_count":1,"area":"inference"},{"id":"2608.14191","title":"KV Cache Compression Through the Lens of Transform Coding","created":"2026-08-14","cited_by_count":1,"area":"inference"},{"id":"2610.07643","title":"Monte Carlo Estimation for KV Cache Eviction","created":"2026-10-06","cited_by_count":1,"area":"inference"},{"id":"2602.05499","title":"SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration","created":"2026-02-05","cited_by_count":0,"area":"inference"},{"id":"2602.21780","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-02-25","cited_by_count":0,"area":"inference"},{"id":"2605.03562","title":"HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization","created":"2026-05-05","cited_by_count":0,"area":"inference"},{"id":"2607.01065","title":"GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache","created":"2026-07-01","cited_by_count":0,"area":"inference"},{"id":"2607.20538","title":"Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches","created":"2026-07-10","cited_by_count":0,"area":"inference"},{"id":"2608.28911","title":"SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"id":"2609.04263","title":"Quality Recovery for Quantized KV Caches via Low-Rank Attention Adaptation","created":"2026-09-02","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.13205","title":"Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2609.33536","title":"Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2610.14475","title":"EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.19605","title":"PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}