{"list":"other","total":71,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2112.07916","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","created":"2021-12-15","cited_by_count":232},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116},{"id":"2403.07816","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","created":"2024-03-12","cited_by_count":109},{"id":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100},{"id":"2405.04437","title":"vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention","created":"2024-05-07","cited_by_count":98},{"id":"2407.08454","title":"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks","created":"2024-07-11","cited_by_count":96},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91},{"id":"2305.18466","title":"Test-Time Training on Nearest Neighbors for Large Language Models","created":"2023-05-29","cited_by_count":88},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86},{"id":"2402.15220","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","created":"2024-02-23","cited_by_count":82},{"id":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73},{"id":"2406.12335","title":"Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters","created":"2024-06-18","cited_by_count":73},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71},{"id":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67},{"id":"2311.08719","title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","created":"2023-11-15","cited_by_count":64},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62},{"id":"2402.17463","title":"Training-Free Long-Context Scaling of Large Language Models","created":"2024-02-27","cited_by_count":62},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2403.11421","title":"FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines","created":"2024-03-18","cited_by_count":49},{"id":"2403.17312","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","created":"2024-03-26","cited_by_count":48},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43},{"id":"2402.11975","title":"Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations","created":"2024-02-19","cited_by_count":36},{"id":"2406.07056","title":"Effectively Compress KV Heads for LLM","created":"2024-06-11","cited_by_count":30},{"id":"2306.01160","title":"Faster Causal Attention Over Large Sequences Through Sparse Flash Attention","created":"2023-06-01","cited_by_count":25},{"id":"2201.09680","title":"Relational Memory Augmented Language Models","created":"2022-01-24","cited_by_count":24},{"id":"2404.04793","title":"SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget","created":"2024-04-07","cited_by_count":23},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22},{"id":"2406.09297","title":"MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding","created":"2024-06-13","cited_by_count":21},{"id":"2409.04992","title":"InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference","created":"2024-09-08","cited_by_count":19},{"id":"2312.17259","title":"Empowering Working Memory for Large Language Model Agents","created":"2023-12-22","cited_by_count":18},{"id":"2402.10685","title":"LongHeads: Multi-Head Attention is Secretly a Long Context Processor","created":"2024-02-16","cited_by_count":16},{"id":"2405.12528","title":"SirLLM: Streaming Infinite Retentive LLM","created":"2024-05-21","cited_by_count":16},{"id":"2401.14215","title":"Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement","created":"2024-01-25","cited_by_count":14},{"id":"2407.12866","title":"Beyond KV Caching: Shared Attention for Efficient LLMs","created":"2024-07-13","cited_by_count":10},{"id":"2308.13191","title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","created":"2023-08-25","cited_by_count":9},{"id":"2406.00057","title":"Toward Conversational Agents with Context and Time Sensitive Long-term Memory","created":"2024-05-29","cited_by_count":8},{"id":"2407.20485","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","created":"2024-07-30","cited_by_count":8},{"id":"2312.08618","title":"Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention","created":"2023-12-14","cited_by_count":6},{"id":"2408.01890","title":"Cross-layer Attention Sharing for Pre-trained Large Language Models","created":"2024-08-04","cited_by_count":5},{"id":"2406.06124","title":"Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation","created":"2024-06-10","cited_by_count":4},{"id":"2406.12018","title":"CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling","created":"2024-06-17","cited_by_count":4},{"id":"2407.02328","title":"Efficient Sparse Attention needs Adaptive Token Release","created":"2024-07-02","cited_by_count":4},{"id":"2404.18057","title":"Efficient LLM Inference with Kcache","created":"2024-04-28","cited_by_count":2},{"id":"2406.10985","title":"Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens","created":"2024-06-16","cited_by_count":2}],"next_cursor":null}