{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"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":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148},{"id":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104},{"id":"2406.06282","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","created":"2024-06-10","cited_by_count":103},{"id":"2410.11845","title":"A Review on Edge Large Language Models: Design, Execution, and Applications","created":"2024-09-29","cited_by_count":100},{"id":"2311.13230","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","created":"2023-11-22","cited_by_count":99},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72},{"id":"2402.18041","title":"Datasets for Large Language Models: A Comprehensive Survey","created":"2024-02-28","cited_by_count":71},{"id":"2306.05064","title":"K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization","created":"2023-06-08","cited_by_count":69},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57},{"id":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38},{"id":"2402.16819","title":"Nemotron-4 15B Technical Report","created":"2024-02-26","cited_by_count":36},{"id":"2401.00434","title":"GeoGalactica: A Scientific Large Language Model in Geoscience","created":"2023-12-31","cited_by_count":33},{"id":"2406.15758","title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","created":"2024-06-22","cited_by_count":27},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19},{"id":"2502.05605","title":"Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization","created":"2025-02-08","cited_by_count":16},{"id":"2405.03594","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","created":"2024-05-06","cited_by_count":15},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7},{"id":"2503.00392","title":"Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving","created":"2025-03-01","cited_by_count":7},{"id":"2502.15975","title":"Sparsity May Be All You Need: Sparse Random Parameter Adaptation","created":"2025-02-21","cited_by_count":5},{"id":"2502.15349","title":"AttentionEngine: A Versatile Framework for Efficient Attention Mechanisms on Diverse Hardware Platforms","created":"2025-02-21","cited_by_count":4},{"id":"2408.08909","title":"An Adaptive Differential Privacy Method Based on Federated Learning","created":"2024-08-13","cited_by_count":3},{"id":"2411.05281","title":"Fox-1: Open Small Language Model for Cloud and Edge","created":"2024-11-08","cited_by_count":3},{"id":"2409.18164","title":"Data-Prep-Kit: getting your data ready for LLM application development","created":"2024-09-26","cited_by_count":2},{"id":"2502.13542","title":"Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference","created":"2025-02-19","cited_by_count":2},{"id":"2502.18773","title":"Research on Edge Computing and Cloud Collaborative Resource Scheduling Optimization Based on Deep Reinforcement Learning","created":"2025-02-26","cited_by_count":2}],"next_cursor":null}