{"list":"other","total":69,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"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":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"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":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"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":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99},{"id":"2304.13343","title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","created":"2023-04-26","cited_by_count":98},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74},{"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":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60},{"id":"2402.18700","title":"Learning to Compress Prompt in Natural Language Formats","created":"2024-02-28","cited_by_count":55},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53},{"id":"2401.14490","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","created":"2024-01-25","cited_by_count":33},{"id":"2602.16284","title":"Fast KV Compaction via Attention Matching","created":"2026-02-18","cited_by_count":31},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25},{"id":"2601.17668","title":"Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction","created":"2026-01-25","cited_by_count":16},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2503.07259","title":"COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition","created":"2025-03-10","cited_by_count":9},{"id":"2509.01092","title":"REFRAG: Rethinking RAG based Decoding","created":"2025-09-01","cited_by_count":9},{"id":"2502.06766","title":"Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs","created":"2025-02-10","cited_by_count":5},{"id":"2504.12637","title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation","created":"2025-04-17","cited_by_count":4},{"id":"2510.20535","title":"ARC-Encoder: learning compressed text representations for large language models","created":"2025-10-23","cited_by_count":3},{"id":"2604.27398","title":"Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings","created":"2026-04-30","cited_by_count":2},{"id":"2505.05777","title":"PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection","created":"2025-05-09","cited_by_count":1}],"next_cursor":null}