{"list":"other","total":123,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"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":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"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":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453},{"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":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","created":"2025-01-20","cited_by_count":400},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258},{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246},{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238},{"id":"2508.19828","title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","created":"2025-08-27","cited_by_count":237},{"id":"2307.06945","title":"In-context Autoencoder for Context Compression in a Large Language Model","created":"2023-07-13","cited_by_count":199},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191},{"id":"2402.05120","title":"More Agents Is All You Need","created":"2024-02-03","cited_by_count":180},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125},{"id":"2506.07398","title":"G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems","created":"2025-06-09","cited_by_count":122},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109},{"id":"2405.04437","title":"vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention","created":"2024-05-07","cited_by_count":98},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95},{"id":"2402.04624","title":"MEMORYLLM: Towards Self-Updatable Large Language Models","created":"2024-02-07","cited_by_count":93},{"id":"2408.12757","title":"NanoFlow: Towards Optimal Large Language Model Serving Throughput","created":"2024-08-22","cited_by_count":90},{"id":"2605.26494","title":"The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence","created":"2026-05-26","cited_by_count":61},{"id":"2502.00592","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","created":"2025-02-01","cited_by_count":54},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46}],"next_cursor":"100"}