{"list":"other","total":48,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"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":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2412.21187","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","created":"2024-12-30","cited_by_count":570},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"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":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"2403.14123","title":"AI and Memory Wall","created":"2024-03-21","cited_by_count":92},{"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":"2410.06916","title":"SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration","created":"2024-10-09","cited_by_count":72},{"id":"2006.16362","title":"Multi-Head Attention: Collaborate Instead of Concatenate","created":"2020-06-29","cited_by_count":60},{"id":"2408.11743","title":"MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models","created":"2024-08-21","cited_by_count":52},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26},{"id":"2404.08698","title":"Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding","created":"2024-04-10","cited_by_count":23},{"id":"2511.19269","title":"CDLM: Consistency Diffusion Language Models For Faster Sampling","created":"2025-11-24","cited_by_count":21},{"id":"2601.11580","title":"Speculative Decoding: Performance or Illusion?","created":"2025-12-31","cited_by_count":15},{"id":"2411.03786","title":"The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation","created":"2024-11-06","cited_by_count":14},{"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},{"id":"2505.16162","title":"KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization","created":"2025-05-22","cited_by_count":11},{"id":"2505.24196","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding","created":"2025-05-30","cited_by_count":11},{"id":"2511.13841","title":"Beat the long tail: Distribution-Aware Speculative Decoding for RL Training","created":"2025-11-17","cited_by_count":10},{"id":"2604.26779","title":"Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding","created":"2026-04-29","cited_by_count":9},{"id":"2410.10141","title":"Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation","created":"2024-10-14","cited_by_count":7}],"next_cursor":null}