{"total":50,"rows":[{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"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":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","cited_by_count":7,"area":"inference"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2606.06256","title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","created":"2026-06-04","cited_by_count":7,"area":"inference"},{"id":"2606.20537","title":"Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving","created":"2026-06-18","cited_by_count":7,"area":"inference"},{"id":"2604.20920","title":"Simplified Sparse Attention via Gist Tokens","created":"2026-04-22","cited_by_count":6,"area":"inference"},{"id":"2608.27513","title":"DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization","created":"2026-08-27","cited_by_count":6,"area":"inference"},{"id":"2607.16673","title":"SpecLA: Efficient Speculative Decoding for Linear-Attention Models","created":"2026-07-18","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":"2602.06932","title":"When RL Meets Adaptive Speculative Training: A Unified Training-Serving System","created":"2026-02-06","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":"2608.01651","title":"Bole: Efficient Tree Speculation for Hybrid-Attention Language Models","created":"2026-08-03","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":"2504.19191","title":"WuNeng: Hybrid State with Attention","created":"2025-04-27","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":"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":"2606.06467","title":"You Only Index Once: Cross-Layer Sparse Attention with Shared Routing","created":"2026-06-04","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":"2608.20961","title":"TreeWY: Speculative Verification for Gated DeltaNet Hybrids","created":"2026-08-21","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":"2604.08426","title":"KV Cache Offloading for Context-Intensive Tasks","created":"2026-04-09","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":"2608.30310","title":"Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2609.02737","title":"Language Models Can Control Their Own Attention","created":"2026-09-02","cited_by_count":1,"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":"2605.20936","title":"DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU","created":"2026-05-20","cited_by_count":0,"area":"inference"},{"id":"2607.11897","title":"Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels","created":"2026-06-12","cited_by_count":0,"area":"inference"},{"id":"2607.16473","title":"Enabling Spatially Fine-Grained DVFS in Neural Processing Units for Energy-Efficient LLM Serving","created":"2026-07-17","cited_by_count":0,"area":"inference"},{"id":"2609.19169","title":"SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops","created":"2026-09-12","cited_by_count":0,"area":"inference"},{"id":"2609.23314","title":"ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.23900","title":"LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.25053","title":"LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.27470","title":"DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video","created":"2026-09-23","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":"2609.39972","title":"UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding","created":"2026-09-30","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"},{"id":"2610.19792","title":"JetSpec++: Foresight Parallel Drafting with Self Refinements","created":"2026-10-14","cited_by_count":0,"area":"inference"},{"id":"2610.20503","title":"ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}