{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"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":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"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":"1906.01749","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","created":"2019-06-04","cited_by_count":431},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256},{"id":"1904.08375","title":"Document Expansion by Query Prediction","created":"2019-04-17","cited_by_count":231},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225},{"id":"2108.05540","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","created":"2021-08-12","cited_by_count":203},{"id":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"1611.00179","title":"Dual Learning for Machine Translation","created":"2016-11-01","cited_by_count":148},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119},{"id":"2401.12954","title":"Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding","created":"2024-01-23","cited_by_count":117},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116},{"id":"1907.01470","title":"Augmenting Self-attention with Persistent Memory","created":"2019-07-02","cited_by_count":93},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39},{"id":"2410.18963","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","created":"2024-10-24","cited_by_count":38},{"id":"2206.11349","title":"Prompt Injection: Parameterization of Fixed Inputs","created":"2022-05-31","cited_by_count":36},{"id":"2403.04317","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","created":"2024-03-07","cited_by_count":35},{"id":"2404.09982","title":"INMS: Memory Sharing for Large Language Model based Agents","created":"2024-04-15","cited_by_count":31},{"id":"2306.00477","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","created":"2023-06-01","cited_by_count":26},{"id":"2407.06324","title":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","created":"2024-07-08","cited_by_count":26},{"id":"2402.13449","title":"CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory","created":"2024-02-21","cited_by_count":24},{"id":"2402.11078","title":"Model Editing by Standard Fine-Tuning","created":"2024-02-16","cited_by_count":23},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13},{"id":"2410.03156","title":"MELODI: Exploring Memory Compression for Long Contexts","created":"2024-10-04","cited_by_count":11},{"id":"2410.05162","title":"Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models","created":"2024-10-07","cited_by_count":10},{"id":"2105.03458","title":"Duplex Sequence-to-Sequence Learning for Reversible Machine Translation","created":"2021-05-07","cited_by_count":9},{"id":"2212.09598","title":"Query-as-context Pre-training for Dense Passage Retrieval","created":"2022-12-19","cited_by_count":9},{"id":"2407.17695","title":"Enhancing Agent Learning through World Dynamics Modeling","created":"2024-07-25","cited_by_count":9},{"id":"2305.12628","title":"Duplex Diffusion Models Improve Speech-to-Speech Translation","created":"2023-05-22","cited_by_count":5},{"id":"2412.11814","title":"EventSum: A Large-Scale Event-Centric Summarization Dataset for Chinese Multi-News Documents","created":"2024-12-16","cited_by_count":3}],"next_cursor":null}