{"total":166,"rows":[{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"area":null},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2403.01241","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","created":"2024-03-02","cited_by_count":52,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"area":null},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"area":null},{"id":"2411.01783","title":"Context Parallelism for Scalable Million-Token Inference","created":"2024-11-04","cited_by_count":26,"area":null},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2504.11320","title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints","created":"2025-04-15","cited_by_count":19,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2403.20041","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","created":"2024-03-29","cited_by_count":17,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2402.04902","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","created":"2024-02-07","cited_by_count":15,"area":null},{"id":"2406.19657","title":"LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM Inference","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2505.06901","title":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression","created":"2025-05-11","cited_by_count":14,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2510.04146","title":"Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models","created":"2025-10-05","cited_by_count":13,"area":null},{"id":"2505.01658","title":"A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency","created":"2025-05-03","cited_by_count":12,"area":null},{"id":"2409.12963","title":"Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner","created":"2024-09-19","cited_by_count":11,"area":null},{"id":"2409.13199","title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","created":"2024-09-20","cited_by_count":11,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2407.12866","title":"Beyond KV Caching: Shared Attention for Efficient LLMs","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2410.22217","title":"Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2410.01866","title":"House of Cards: Massive Weights in LLMs","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2505.00850","title":"ICQuant: Index Coding enables Low-bit LLM Quantization","created":"2025-05-01","cited_by_count":9,"area":null},{"id":"2510.10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2409.01366","title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification","created":"2024-09-02","cited_by_count":7,"area":null},{"id":"2410.03766","title":"FutureFill: Fast Generation from Convolutional Sequence Models","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2410.08661","title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2411.09510","title":"Communication Compression for Tensor Parallel LLM Inference","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2412.20677","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2507.10178","title":"Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2508.00904","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2603.14517","title":"Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models","created":"2026-03-15","cited_by_count":7,"area":null},{"id":"2607.15456","title":"Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers","created":"2026-07-16","cited_by_count":7,"area":null},{"id":"2410.12168","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2511.20426","title":"Block Cascading: Training Free Acceleration of Block-Causal Video Models","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2409.17836","title":"Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2501.06246","title":"A Partition Cover Approach to Tokenization","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2507.04610","title":"any4: Learned 4-bit Numeric Representation for LLMs","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2507.04723","title":"LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2508.16785","title":"Interpreting the Effects of Quantization on LLMs","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2510.18546","title":"EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2601.09527","title":"Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2606.07684","title":"Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2410.13166","title":"An Evolved Universal Transformer Memory","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.09579","title":"Cost-Optimal Grouped-Query Attention for Long-Context Modeling","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2505.19155","title":"Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2505.23520","title":"AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.07145","title":"CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs","created":"2025-07-09","cited_by_count":4,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2510.23649","title":"Efficient Low Rank Attention for Long-Context Inference in Large Language Models","created":"2025-10-25","cited_by_count":4,"area":null},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2512.21859","title":"TimeBill: Time-Budgeted Inference for Large Language Models","created":"2025-12-26","cited_by_count":4,"area":null},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2604.22782","title":"Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2609.00097","title":"Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding","created":"2026-08-31","cited_by_count":4,"area":null},{"id":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2502.12085","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.10656","title":"Token Sample Complexity of Attention","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2601.21927","title":"SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null}],"next_cursor":"100"}