{"list":"other","total":116,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"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":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"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":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"1809.02627","title":"Unity: A General Platform for Intelligent Agents","created":"2018-09-07","cited_by_count":236},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223},{"id":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122},{"id":"2401.11181","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","created":"2024-01-20","cited_by_count":121},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"2010.02519","title":"Improved Analysis of Clipping Algorithms for Non-convex Optimization","created":"2020-10-05","cited_by_count":89},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70},{"id":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69},{"id":"2401.03868","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","created":"2024-01-08","cited_by_count":64},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63},{"id":"2403.20306","title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference","created":"2024-03-29","cited_by_count":61},{"id":"2308.02019","title":"Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty","created":"2023-08-03","cited_by_count":57},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55},{"id":"2402.16840","title":"MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT","created":"2024-02-26","cited_by_count":34},{"id":"2312.05693","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","created":"2023-12-09","cited_by_count":33},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30}],"next_cursor":"100"}