{"list":"other","total":56,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"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":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","created":"2025-04-28","cited_by_count":779},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60},{"id":"2506.06105","title":"Text-to-LoRA: Instant Transformer Adaption","created":"2025-06-06","cited_by_count":58},{"id":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38},{"id":"2501.15915","title":"Parametric Retrieval Augmented Generation","created":"2025-01-27","cited_by_count":38},{"id":"2407.03471","title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","created":"2024-07-03","cited_by_count":32},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25},{"id":"2602.06358","title":"SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass","created":"2026-02-06","cited_by_count":25},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24},{"id":"2410.08258","title":"In Search of Forgotten Domain Generalization","created":"2024-10-10","cited_by_count":21},{"id":"2406.18400","title":"Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers","created":"2024-06-26","cited_by_count":15},{"id":"2402.00793","title":"Human Expertise in Algorithmic Prediction","created":"2024-02-01","cited_by_count":13},{"id":"2502.04375","title":"An Analysis for Reasoning Bias of Language Models with Small Initialization","created":"2025-02-05","cited_by_count":13},{"id":"2502.14502","title":"How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?","created":"2025-02-20","cited_by_count":13},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13},{"id":"2409.14057","title":"Co-occurrence is not Factual Association in Language Models","created":"2024-09-21","cited_by_count":12},{"id":"2408.11869","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","created":"2024-08-19","cited_by_count":8},{"id":"2507.05346","title":"LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks","created":"2025-07-07","cited_by_count":8},{"id":"2504.03454","title":"SpectR: Dynamically Composing LM Experts with Spectral Routing","created":"2025-04-04","cited_by_count":6},{"id":"2409.05798","title":"Enhancing Preference-based Linear Bandits via Human Response Time","created":"2024-09-09","cited_by_count":3}],"next_cursor":null}