{"total":47,"rows":[{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"id":"2505.14969","title":"STree: Speculative Tree Decoding for Hybrid State-Space Models","created":"2025-05-20","cited_by_count":10,"area":"inference"},{"id":"2505.21487","title":"Hardware-Efficient Attention for Fast Decoding","created":"2025-05-27","cited_by_count":10,"area":"inference"},{"id":"2410.01485","title":"A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts","created":"2024-10-02","cited_by_count":9,"area":"inference"},{"id":"2505.22135","title":"RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding","created":"2025-05-28","cited_by_count":8,"area":"inference"},{"id":"2512.17910","title":"Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA","created":"2025-11-26","cited_by_count":8,"area":"inference"},{"id":"2503.11816","title":"Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques","created":"2025-03-14","cited_by_count":5,"area":"inference"},{"id":"2503.22196","title":"EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices","created":"2025-03-28","cited_by_count":5,"area":"inference"},{"id":"2509.19873","title":"SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding","created":"2025-09-24","cited_by_count":5,"area":"inference"},{"id":"2503.11132","title":"X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression","created":"2025-03-14","cited_by_count":4,"area":"inference"},{"id":"2605.05219","title":"Sparse Prefix Caching for Hybrid and Recurrent LLM Serving","created":"2026-04-17","cited_by_count":4,"area":"inference"},{"id":"2510.20787","title":"Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction","created":"2025-10-23","cited_by_count":3,"area":"inference"},{"id":"2603.05931","title":"A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA","created":"2026-03-06","cited_by_count":3,"area":"inference"},{"id":"2605.19049","title":"KVBuffer: IO-aware Serving for Linear Attention","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","cited_by_count":3,"area":"inference"},{"id":"2608.11231","title":"LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs","created":"2026-07-31","cited_by_count":3,"area":"inference"},{"id":"2602.18196","title":"RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference","created":"2026-02-20","cited_by_count":2,"area":"inference"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2605.06221","title":"UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification","created":"2026-05-07","cited_by_count":2,"area":"inference"},{"id":"2606.02775","title":"AURA: Action-Gated Memory for Robot Policies at Constant VRAM","created":"2026-06-01","cited_by_count":2,"area":"inference"},{"id":"2608.28444","title":"Sliding-window beats linear attention","created":"2026-08-28","cited_by_count":2,"area":"inference"},{"id":"2609.04434","title":"What Attention Recalls and Recurrence Controls in Hybrid Language Models","created":"2026-09-03","cited_by_count":2,"area":"inference"},{"id":"2610.13778","title":"ReplaySSM: Cache SSM Inputs, Not State","created":"2026-10-09","cited_by_count":2,"area":"inference"},{"id":"2508.00370","title":"EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices","created":"2025-08-01","cited_by_count":1,"area":"inference"},{"id":"2603.23701","title":"The Diminishing Returns of Early-Exit Decoding in Modern LLMs","created":"2026-03-24","cited_by_count":1,"area":"inference"},{"id":"2604.08426","title":"KV Cache Offloading for Context-Intensive Tasks","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2605.01106","title":"Component-Aware Self-Speculative Decoding in Hybrid Language Models","created":"2026-05-01","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":"2605.11999","title":"The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures","created":"2026-05-12","cited_by_count":1,"area":"inference"},{"id":"2606.09862","title":"Blurry Window Attention","created":"2026-05-31","cited_by_count":1,"area":"inference"},{"id":"2606.16429","title":"Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation","created":"2026-06-15","cited_by_count":1,"area":"inference"},{"id":"2608.15533","title":"DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding","created":"2026-08-16","cited_by_count":1,"area":"inference"},{"id":"2505.08600","title":"Automatic Task Detection and Heterogeneous LLM Speculative Decoding","created":"2025-05-13","cited_by_count":0,"area":"inference"},{"id":"2603.09968","title":"ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"id":"2604.05942","title":"BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs","created":"2026-04-07","cited_by_count":0,"area":"inference"},{"id":"2604.07716","title":"Breaking the KV Cache Bottleneck: Fan Duality Model Achieves O(1) Decode Memory with Superior Associative Recall","created":"2026-04-09","cited_by_count":0,"area":"inference"},{"id":"2607.02922","title":"STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation","created":"2026-07-03","cited_by_count":0,"area":"inference"},{"id":"2607.21535","title":"Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context","created":"2026-07-23","cited_by_count":0,"area":"inference"},{"id":"2608.23599","title":"Squeezing the Cache, Preserving the Truth: Monotonic Equipotential Allocation with Geodesia-KV","created":"2026-08-19","cited_by_count":0,"area":"inference"},{"id":"2609.38169","title":"STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.17355","title":"WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"},{"id":"2610.18143","title":"RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.18654","title":"Kwai Summary Attention V2 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19210","title":"Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}