{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2503.07365","title":"MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning","created":"2025-03-10","cited_by_count":303},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292},{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234},{"id":"2505.20275","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","created":"2025-05-26","cited_by_count":231},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"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":"2003.08039","title":"ROMA: Multi-Agent Reinforcement Learning with Emergent Roles","created":"2020-03-18","cited_by_count":137},{"id":"1802.05642","title":"The Mechanics of n-Player Differentiable Games","created":"2018-02-15","cited_by_count":118},{"id":"1804.03984","title":"Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input","created":"2018-04-11","cited_by_count":102},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100},{"id":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"id":"2502.02723","title":"Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives","created":"2025-02-04","cited_by_count":48},{"id":"2410.18798","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","created":"2024-10-24","cited_by_count":31},{"id":"2506.10128","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs","created":"2025-06-11","cited_by_count":25},{"id":"2508.06492","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding","created":"2025-08-08","cited_by_count":20},{"id":"2111.14210","title":"Emergent Graphical Conventions in a Visual Communication Game","created":"2021-11-28","cited_by_count":16},{"id":"2306.16884","title":"Policy Space Diversity for Non-Transitive Games","created":"2023-06-29","cited_by_count":15},{"id":"2410.07553","title":"COMMA: A Communicative Multimodal Multi-Agent Benchmark","created":"2024-10-10","cited_by_count":14},{"id":"2410.18311","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","created":"2024-10-23","cited_by_count":14},{"id":"2509.09119","title":"Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models","created":"2025-09-11","cited_by_count":14},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13},{"id":"2506.22434","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning","created":"2025-06-27","cited_by_count":9},{"id":"2310.20499","title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models","created":"2023-10-31","cited_by_count":8},{"id":"2505.19235","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","created":"2025-05-25","cited_by_count":8},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","cited_by_count":7},{"id":"2507.06466","title":"Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models","created":"2025-07-09","cited_by_count":6},{"id":"2304.14511","title":"Visual Referential Games Further the Emergence of Disentangled Representations","created":"2023-04-27","cited_by_count":5},{"id":"2012.07966","title":"Odd-One-Out Representation Learning","created":"2020-12-14","cited_by_count":4},{"id":"2408.09946","title":"Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game","created":"2024-08-19","cited_by_count":4},{"id":"2410.15311","title":"Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game","created":"2024-10-20","cited_by_count":3},{"id":"2509.04326","title":"Efficient Odd-One-Out Anomaly Detection","created":"2025-09-04","cited_by_count":1}],"next_cursor":null}