{"list":"other","total":105,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"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":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"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":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"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":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2410.07985","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","created":"2024-10-10","cited_by_count":284},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250},{"id":"1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","created":"2016-10-27","cited_by_count":216},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154},{"id":"2509.13313","title":"ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization","created":"2025-09-16","cited_by_count":141},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2308.13149","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","created":"2023-08-25","cited_by_count":115},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86},{"id":"2305.15074","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","created":"2023-05-24","cited_by_count":77},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70},{"id":"2007.08124","title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","created":"2020-07-16","cited_by_count":69},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62},{"id":"2401.13660","title":"MambaByte: Token-free Selective State Space Model","created":"2024-01-24","cited_by_count":59},{"id":"2501.14723","title":"CodeMonkeys: Scaling Test-Time Compute for Software Engineering","created":"2025-01-24","cited_by_count":51},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43},{"id":"2408.03675","title":"NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time","created":"2024-08-07","cited_by_count":43},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43},{"id":"2006.03274","title":"GMAT: Global Memory Augmentation for Transformers","created":"2020-06-05","cited_by_count":36},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36},{"id":"2004.08483","title":"ETC: Encoding Long and Structured Inputs in Transformers","created":"2020-04-17","cited_by_count":34},{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32},{"id":"2602.16284","title":"Fast KV Compaction via Attention Matching","created":"2026-02-18","cited_by_count":31},{"id":"2512.12167","title":"Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings","created":"2025-12-13","cited_by_count":26},{"id":"2502.18845","title":"Sliding Window Attention Training for Efficient Large Language Models","created":"2025-02-26","cited_by_count":24},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22},{"id":"2405.06067","title":"HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing","created":"2024-05-09","cited_by_count":21},{"id":"2503.15952","title":"Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning","created":"2025-03-20","cited_by_count":21},{"id":"2503.08879","title":"LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference","created":"2025-03-11","cited_by_count":20},{"id":"2408.04093","title":"Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters","created":"2024-08-07","cited_by_count":13},{"id":"2503.07518","title":"TokenButler: Token Importance is Predictable","created":"2025-03-10","cited_by_count":12},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11},{"id":"2606.23525","title":"Self-Compacting Language Model Agents","created":"2026-06-22","cited_by_count":11}],"next_cursor":"100"}