{"list":"other","total":76,"rows":[{"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"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":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171},{"id":"2503.05132","title":"R1-Zero's \"Aha Moment\" in Visual Reasoning on a 2B Non-SFT Model","created":"2025-03-07","cited_by_count":165},{"id":"2411.00836","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","created":"2024-10-29","cited_by_count":146},{"id":"2007.13156","title":"Benchmarking Multivariate Time Series Classification Algorithms","created":"2020-07-26","cited_by_count":145},{"id":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118},{"id":"2305.11860","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","created":"2023-05-19","cited_by_count":115},{"id":"2506.03569","title":"MiMo-VL Technical Report","created":"2025-06-04","cited_by_count":115},{"id":"2406.05756","title":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models","created":"2024-06-09","cited_by_count":107},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106},{"id":"2308.04371","title":"Cumulative Reasoning with Large Language Models","created":"2023-08-08","cited_by_count":94},{"id":"2405.16433","title":"CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling","created":"2024-05-26","cited_by_count":89},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89},{"id":"2410.18959","title":"Context is Key: A Benchmark for Forecasting with Essential Textual Information","created":"2024-10-24","cited_by_count":87},{"id":"2404.17140","title":"Small Language Models Need Strong Verifiers to Self-Correct Reasoning","created":"2024-04-26","cited_by_count":86},{"id":"2503.01875","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","created":"2025-02-26","cited_by_count":82},{"id":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72},{"id":"2410.14752","title":"TimeSeriesExam: A time series understanding exam","created":"2024-10-18","cited_by_count":49},{"id":"2502.00334","title":"UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models","created":"2025-02-01","cited_by_count":48},{"id":"2410.05440","title":"Can LLMs Understand Time Series Anomalies?","created":"2024-10-07","cited_by_count":41},{"id":"2404.03647","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","created":"2024-04-04","cited_by_count":37},{"id":"2506.20093","title":"ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset","created":"2025-06-25","cited_by_count":37},{"id":"2406.12747","title":"TSI-Bench: Benchmarking Time Series Imputation","created":"2024-06-18","cited_by_count":33},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30},{"id":"2510.12712","title":"Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning","created":"2025-10-14","cited_by_count":29},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27},{"id":"2503.17452","title":"CausalRivers -- Scaling up benchmarking of causal discovery for real-world time-series","created":"2025-03-21","cited_by_count":26},{"id":"2502.18834","title":"FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting","created":"2025-02-26","cited_by_count":24},{"id":"2509.04439","title":"ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory","created":"2025-09-04","cited_by_count":24},{"id":"2505.07671","title":"Benchmarking Retrieval-Augmented Generation for Chemistry","created":"2025-05-12","cited_by_count":20},{"id":"2509.16204","title":"Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs","created":"2025-07-01","cited_by_count":20},{"id":"2506.10412","title":"Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series","created":"2025-06-12","cited_by_count":19},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17},{"id":"2506.17667","title":"PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level","created":"2025-06-21","cited_by_count":16},{"id":"2511.14159","title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","created":"2025-11-18","cited_by_count":15},{"id":"2408.08302","title":"Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors","created":"2024-08-15","cited_by_count":13},{"id":"2501.13766","title":"UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models","created":"2025-01-23","cited_by_count":13},{"id":"2511.01163","title":"ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation","created":"2025-11-03","cited_by_count":13},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10},{"id":"2408.13960","title":"Time Series Analysis for Education: Methods, Applications, and Future Directions","created":"2024-08-25","cited_by_count":5},{"id":"2510.03185","title":"PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning","created":"2025-10-03","cited_by_count":4},{"id":"2601.06559","title":"ArrowGEV: Grounding Events in Video via Learning the Arrow of Time","created":"2026-01-10","cited_by_count":4},{"id":"2508.17905","title":"Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning","created":"2025-08-25","cited_by_count":1}],"next_cursor":null}