{"list":"other","total":59,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2406.06592","title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","created":"2024-06-05","cited_by_count":441},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182},{"id":"2403.02884","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","created":"2024-03-05","cited_by_count":144},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118},{"id":"2406.18139","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","created":"2024-06-26","cited_by_count":95},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2210.16257","title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","created":"2022-10-28","cited_by_count":77},{"id":"2406.10858","title":"Step-level Value Preference Optimization for Mathematical Reasoning","created":"2024-06-16","cited_by_count":72},{"id":"2403.06659","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","created":"2024-03-11","cited_by_count":67},{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","cited_by_count":67},{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","cited_by_count":54},{"id":"2310.09044","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","created":"2023-10-13","cited_by_count":45},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38},{"id":"2505.15929","title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","created":"2025-05-21","cited_by_count":38},{"id":"2505.17952","title":"Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL","created":"2025-05-23","cited_by_count":36},{"id":"2502.06805","title":"Efficient Diffusion Models: A Survey","created":"2025-02-03","cited_by_count":35},{"id":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31},{"id":"2407.00320","title":"LiteSearch: Efficacious Tree Search for LLM","created":"2024-06-29","cited_by_count":31},{"id":"2502.17599","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","created":"2025-02-24","cited_by_count":31},{"id":"2501.03226","title":"BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning","created":"2025-01-06","cited_by_count":21},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14},{"id":"2210.15373","title":"Self-consistent Reasoning For Solving Math Word Problems","created":"2022-10-27","cited_by_count":10},{"id":"2212.03613","title":"G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks","created":"2022-12-07","cited_by_count":9},{"id":"2407.21004","title":"Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection","created":"2024-07-30","cited_by_count":9},{"id":"2406.03403","title":"Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?","created":"2024-06-04","cited_by_count":7},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7},{"id":"2410.13523","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","created":"2024-10-17","cited_by_count":7},{"id":"2505.19261","title":"Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning","created":"2025-05-25","cited_by_count":7},{"id":"2003.07013","title":"Large Scale Many-Objective Optimization Driven by Distributional Adversarial Networks","created":"2020-03-16","cited_by_count":6},{"id":"2003.08295","title":"Many-Objective Estimation of Distribution Optimization Algorithm Based on WGAN-GP","created":"2020-03-16","cited_by_count":6},{"id":"2409.01341","title":"Enhancing Test Time Adaptation with Few-shot Guidance","created":"2024-09-02","cited_by_count":5},{"id":"2502.17900","title":"Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs","created":"2025-02-25","cited_by_count":5},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5}],"next_cursor":null}