{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"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":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"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":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","cited_by_count":204},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2501.08313","title":"MiniMax-01: Scaling Foundation Models with Lightning Attention","created":"2025-01-14","cited_by_count":166},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147},{"id":"2209.15189","title":"Learning by Distilling Context","created":"2022-09-30","cited_by_count":138},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125},{"id":"2401.06104","title":"Transformers are Multi-State RNNs","created":"2024-01-11","cited_by_count":120},{"id":"2312.04985","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","created":"2023-12-08","cited_by_count":119},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100},{"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":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75},{"id":"2402.05099","title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes","created":"2024-02-07","cited_by_count":73},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66},{"id":"2304.12102","title":"Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering","created":"2023-04-24","cited_by_count":65},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64},{"id":"2409.16167","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","created":"2024-09-24","cited_by_count":59},{"id":"2402.18700","title":"Learning to Compress Prompt in Natural Language Formats","created":"2024-02-28","cited_by_count":55},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51},{"id":"2408.12570","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","created":"2024-08-22","cited_by_count":50},{"id":"2501.15915","title":"Parametric Retrieval Augmented Generation","created":"2025-01-27","cited_by_count":38},{"id":"2505.03970","title":"A Reasoning-Focused Legal Retrieval Benchmark","created":"2025-05-06","cited_by_count":37},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34},{"id":"2401.14490","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","created":"2024-01-25","cited_by_count":33},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31},{"id":"2406.07056","title":"Effectively Compress KV Heads for LLM","created":"2024-06-11","cited_by_count":30},{"id":"2502.13063","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","created":"2025-02-18","cited_by_count":28},{"id":"2402.18334","title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation","created":"2024-02-28","cited_by_count":27},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24},{"id":"2310.02409","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","created":"2023-10-03","cited_by_count":23},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20},{"id":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17},{"id":"2504.12563","title":"MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation","created":"2025-04-17","cited_by_count":10},{"id":"2205.13722","title":"Can Foundation Models Help Us Achieve Perfect Secrecy?","created":"2022-05-27","cited_by_count":9},{"id":"2408.14906","title":"Writing in the Margins: Better Inference Pattern for Long Context Retrieval","created":"2024-08-27","cited_by_count":7},{"id":"2503.01586","title":"EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection","created":"2025-03-03","cited_by_count":7},{"id":"2503.22562","title":"Niyama : Breaking the Silos of LLM Inference Serving","created":"2025-03-28","cited_by_count":7},{"id":"2305.17660","title":"Plug-and-Play Document Modules for Pre-trained Models","created":"2023-05-28","cited_by_count":6},{"id":"2305.17691","title":"Plug-and-Play Knowledge Injection for Pre-trained Language Models","created":"2023-05-28","cited_by_count":6},{"id":"2502.14644","title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","created":"2025-02-20","cited_by_count":6},{"id":"2409.13697","title":"Prompt Baking","created":"2024-09-04","cited_by_count":5}],"next_cursor":null}