{"total":108,"rows":[{"id":"2507.05240","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","created":"2025-07-07","cited_by_count":118,"area":"inference"},{"id":"2506.00413","title":"Accelerating Diffusion LLMs via Adaptive Parallel Decoding","created":"2025-05-31","cited_by_count":112,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"id":"2510.04767","title":"ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs","created":"2025-10-06","cited_by_count":43,"area":"inference"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2503.23367","title":"FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning","created":"2025-03-30","cited_by_count":34,"area":"inference"},{"id":"2507.11097","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","created":"2025-07-15","cited_by_count":34,"area":"inference"},{"id":"2504.18583","title":"PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation","created":"2025-04-23","cited_by_count":29,"area":"inference"},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28,"area":"inference"},{"id":"2502.05202","title":"Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies","created":"2025-01-31","cited_by_count":20,"area":"inference"},{"id":"2603.04445","title":"Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey","created":"2026-02-23","cited_by_count":19,"area":"inference"},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2504.20068","title":"JITServe: SLO-aware LLM Serving with Imprecise Request Information","created":"2025-04-24","cited_by_count":17,"area":"inference"},{"id":"2509.09754","title":"LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation","created":"2025-09-11","cited_by_count":16,"area":"inference"},{"id":"2512.06866","title":"Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior","created":"2025-12-07","cited_by_count":15,"area":"inference"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2504.20039","title":"AutoJudge: Judge Decoding Without Manual Annotation","created":"2025-04-28","cited_by_count":13,"area":"inference"},{"id":"2502.20704","title":"Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff","created":"2025-02-28","cited_by_count":12,"area":"inference"},{"id":"2510.14557","title":"MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving","created":"2025-10-16","cited_by_count":11,"area":"inference"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2507.01957","title":"Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation","created":"2025-07-02","cited_by_count":10,"area":"inference"},{"id":"2510.02758","title":"TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling","created":"2025-10-03","cited_by_count":10,"area":"inference"},{"id":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10,"area":"inference"},{"id":"2508.02401","title":"CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation","created":"2025-08-04","cited_by_count":9,"area":"inference"},{"id":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2505.15774","title":"Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention","created":"2025-05-21","cited_by_count":7,"area":"inference"},{"id":"2505.15347","title":"FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management","created":"2025-05-21","cited_by_count":6,"area":"inference"},{"id":"2505.15380","title":"Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding","created":"2025-05-21","cited_by_count":6,"area":"inference"},{"id":"2503.10325","title":"Collaborative Speculative Inference for Efficient LLM Inference Serving","created":"2025-03-13","cited_by_count":5,"area":"inference"},{"id":"2505.20776","title":"SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences","created":"2025-05-27","cited_by_count":5,"area":"inference"},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2601.21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","created":"2026-01-29","cited_by_count":5,"area":"inference"},{"id":"2507.02659","title":"OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding","created":"2025-07-03","cited_by_count":4,"area":"inference"},{"id":"2511.00321","title":"Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits","created":"2025-10-31","cited_by_count":4,"area":"inference"},{"id":"2602.02108","title":"Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2604.04987","title":"Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling","created":"2026-04-05","cited_by_count":4,"area":"inference"},{"id":"2605.30571","title":"Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM Decode","created":"2026-05-28","cited_by_count":4,"area":"inference"},{"id":"2502.02493","title":"EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization","created":"2025-02-04","cited_by_count":3,"area":"inference"},{"id":"2504.18579","title":"Sparsity Forcing: Reinforcing Token Sparsity of MLLMs","created":"2025-04-23","cited_by_count":3,"area":"inference"},{"id":"2505.20316","title":"Reinforcement Speculative Decoding for Fast Ranking","created":"2025-05-23","cited_by_count":3,"area":"inference"},{"id":"2506.01215","title":"Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers","created":"2025-06-01","cited_by_count":3,"area":"inference"},{"id":"2508.15919","title":"HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling","created":"2025-08-21","cited_by_count":3,"area":"inference"},{"id":"2509.24328","title":"Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding","created":"2025-09-29","cited_by_count":3,"area":"inference"},{"id":"2511.20340","title":"Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios","created":"2025-11-25","cited_by_count":3,"area":"inference"},{"id":"2604.07931","title":"Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned Distributions","created":"2026-04-09","cited_by_count":3,"area":"inference"},{"id":"2605.07719","title":"An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2605.18053","title":"Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2607.28699","title":"WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization","created":"2026-07-30","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":"2505.16502","title":"Recursive Offloading for LLM Serving in Multi-tier Networks","created":"2025-05-22","cited_by_count":2,"area":"inference"},{"id":"2506.03206","title":"Out-of-Vocabulary Sampling Boosts Speculative Decoding","created":"2025-06-02","cited_by_count":2,"area":"inference"},{"id":"2508.19740","title":"Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval","created":"2025-08-27","cited_by_count":2,"area":"inference"},{"id":"2602.01274","title":"PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length","created":"2026-02-01","cited_by_count":2,"area":"inference"},{"id":"2603.28795","title":"StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving","created":"2026-03-24","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":"2607.23693","title":"Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2501.12162","title":"AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding","created":"2025-01-21","cited_by_count":1,"area":"inference"},{"id":"2510.18525","title":"From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing","created":"2025-10-21","cited_by_count":1,"area":"inference"},{"id":"2512.09238","title":"Training-free Context-adaptive Attention for Efficient Long Context Modeling","created":"2025-12-10","cited_by_count":1,"area":"inference"},{"id":"2601.13631","title":"ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management","created":"2026-01-20","cited_by_count":1,"area":"inference"},{"id":"2605.06763","title":"Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2605.15609","title":"PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding","created":"2026-05-15","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":"2607.17283","title":"Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware","created":"2026-07-19","cited_by_count":1,"area":"inference"},{"id":"2607.27600","title":"Back from the Future: Key-Value Cache Management by Counter-Causal Surprise","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2607.27692","title":"Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2607.28495","title":"Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation","created":"2026-07-30","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":"2502.13374","title":"Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor","created":"2025-02-19","cited_by_count":0,"area":"inference"},{"id":"2502.15294","title":"Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference","created":"2025-02-21","cited_by_count":0,"area":"inference"},{"id":"2503.17922","title":"WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference","created":"2025-03-23","cited_by_count":0,"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":"2604.26951","title":"Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models","created":"2026-04-29","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":"2605.06914","title":"Regulating Branch Parallelism in LLM Serving","created":"2026-05-07","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":"2605.27646","title":"Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2606.02680","title":"Post-Boundary Bridge: Must Local Attention Go Global Between Global Layers?","created":"2026-06-01","cited_by_count":0,"area":"inference"},{"id":"2606.20577","title":"Human-Less LLM Serving: Quantifying the Human Tax on Throughput","created":"2026-05-03","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":"2607.12550","title":"A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation","created":"2026-07-14","cited_by_count":0,"area":"inference"},{"id":"2608.10362","title":"MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.15592","title":"When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction","created":"2026-08-16","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":"2608.28846","title":"A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"id":"2609.00450","title":"HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.05764","title":"Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding","created":"2026-09-04","cited_by_count":0,"area":"inference"},{"id":"2609.13682","title":"LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inference","created":"2026-09-12","cited_by_count":0,"area":"inference"},{"id":"2609.22157","title":"PAGE: Partition-Aware Gated KV-Cache Eviction","created":"2026-08-26","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":"2609.24635","title":"Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache","created":"2026-09-21","cited_by_count":0,"area":"inference"},{"id":"2609.26763","title":"SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.29913","title":"MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression","created":"2026-09-24","cited_by_count":0,"area":"inference"},{"id":"2609.30884","title":"CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.32663","title":"Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference","created":"2026-09-26","cited_by_count":0,"area":"inference"},{"id":"2609.33334","title":"When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression","created":"2026-09-27","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}