{"list":"other","total":62,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"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":"2506.13131","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","created":"2025-06-16","cited_by_count":867},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2504.08066","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","created":"2025-04-10","cited_by_count":422},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321},{"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":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2410.10989","title":"Liger Kernel: Efficient Triton Kernels for LLM Training","created":"2024-10-14","cited_by_count":130},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99},{"id":"2510.02387","title":"CWM: An Open-Weights LLM for Research on Code Generation with World Models","created":"2025-09-30","cited_by_count":93},{"id":"2507.02554","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","created":"2025-07-03","cited_by_count":71},{"id":"2410.20424","title":"AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions","created":"2024-10-27","cited_by_count":70},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43},{"id":"2405.20233","title":"Grokfast: Accelerated Grokking by Amplifying Slow Gradients","created":"2024-05-30","cited_by_count":41},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38},{"id":"2503.04715","title":"Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining","created":"2025-03-06","cited_by_count":34},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33},{"id":"2304.14802","title":"ResiDual: Transformer with Dual Residual Connections","created":"2023-04-28","cited_by_count":31},{"id":"2408.11029","title":"Scaling Law with Learning Rate Annealing","created":"2024-08-20","cited_by_count":29},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22},{"id":"2411.12364","title":"Ultra-Sparse Memory Network","created":"2024-11-19","cited_by_count":19},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14},{"id":"2410.17980","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","created":"2024-10-23","cited_by_count":13},{"id":"2603.26499","title":"AIRA_2: Overcoming Bottlenecks in AI Research Agents","created":"2026-03-27","cited_by_count":12},{"id":"2411.19574","title":"KV Shifting Attention Enhances Language Modeling","created":"2024-11-29","cited_by_count":8},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7},{"id":"2512.10977","title":"Agentic Operator Generation for ML ASICs","created":"2025-12-03","cited_by_count":7},{"id":"2603.21191","title":"On the Role of Batch Size in Stochastic Conditional Gradient Methods","created":"2026-03-22","cited_by_count":7},{"id":"2502.05967","title":"$\\mu$nit Scaling: Simple and Scalable FP8 LLM Training","created":"2025-02-09","cited_by_count":5},{"id":"2512.23236","title":"KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta","created":"2025-12-29","cited_by_count":5},{"id":"2603.22473","title":"Component Ablation for Efficient Hybrid Language Model Architectures: Performance, Resilience, and Compression Implications","created":"2026-03-23","cited_by_count":4},{"id":"2412.05644","title":"Mixture of Hidden-Dimensions Transformer","created":"2024-12-07","cited_by_count":2},{"id":"2603.07300","title":"AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery","created":"2026-03-07","cited_by_count":1}],"next_cursor":null}