{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"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":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"1805.11973","title":"MolGAN: An implicit generative model for small molecular graphs","created":"2018-05-30","cited_by_count":393},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"2102.09548","title":"Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development","created":"2021-02-18","cited_by_count":264},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"1810.08678","title":"Optimization of Molecules via Deep Reinforcement Learning","created":"2018-10-19","cited_by_count":200},{"id":"1803.09518","title":"Fr\\'echet ChemNet Distance: A metric for generative models for molecules in drug discovery","created":"2018-03-26","cited_by_count":194},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"id":"1711.10907","title":"Deep Reinforcement Learning for De-Novo Drug Design","created":"2017-11-29","cited_by_count":161},{"id":"2206.12411","title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","created":"2022-06-22","cited_by_count":155},{"id":"2402.09391","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","created":"2024-02-14","cited_by_count":128},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"id":"2308.01320","title":"DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales","created":"2023-08-02","cited_by_count":108},{"id":"2310.07276","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","created":"2023-10-11","cited_by_count":100},{"id":"2010.13369","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","created":"2020-10-26","cited_by_count":93},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72},{"id":"2112.03041","title":"Keeping it Simple: Language Models can learn Complex Molecular Distributions","created":"2021-12-06","cited_by_count":68},{"id":"2406.16976","title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","created":"2024-06-23","cited_by_count":61},{"id":"2306.10209","title":"ZeRO++: Extremely Efficient Collective Communication for Giant Model Training","created":"2023-06-16","cited_by_count":52},{"id":"2303.06318","title":"A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training","created":"2023-03-11","cited_by_count":47},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44},{"id":"2108.06084","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","created":"2021-08-13","cited_by_count":36},{"id":"2404.00459","title":"NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning","created":"2024-03-30","cited_by_count":31},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","cited_by_count":15},{"id":"2310.04610","title":"DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies","created":"2023-10-06","cited_by_count":15},{"id":"2405.06690","title":"DrugLLM: Open Large Language Model for Few-shot Molecule Generation","created":"2024-05-07","cited_by_count":15},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13},{"id":"2401.14112","title":"FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design","created":"2024-01-25","cited_by_count":12},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11},{"id":"2407.18897","title":"Small Molecule Optimization with Large Language Models","created":"2024-07-26","cited_by_count":6},{"id":"2305.09847","title":"Selective Guidance: Are All the Denoising Steps of Guided Diffusion Important?","created":"2023-05-16","cited_by_count":5},{"id":"2303.08374","title":"MCR-DL: Mix-and-Match Communication Runtime for Deep Learning","created":"2023-03-15","cited_by_count":4},{"id":"2405.06836","title":"Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning","created":"2024-05-10","cited_by_count":1}],"next_cursor":null}