{"list":"other","total":65,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275},{"id":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207},{"id":"2408.08152","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","created":"2024-08-15","cited_by_count":197},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2503.13939","title":"Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models","created":"2025-03-18","cited_by_count":144},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2504.05812","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","created":"2025-04-08","cited_by_count":128},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100},{"id":"2411.07279","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","created":"2024-11-11","cited_by_count":96},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85},{"id":"2008.00305","title":"Self-supervised Learning of Point Clouds via Orientation Estimation","created":"2020-08-01","cited_by_count":72},{"id":"1802.01880","title":"Learning Image Representations by Completing Damaged Jigsaw Puzzles","created":"2018-02-06","cited_by_count":66},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64},{"id":"2505.19914","title":"Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles","created":"2025-05-26","cited_by_count":56},{"id":"2504.00883","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training","created":"2025-04-01","cited_by_count":51},{"id":"2505.19641","title":"SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond","created":"2025-05-26","cited_by_count":50},{"id":"1808.07507","title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","created":"2018-08-22","cited_by_count":40},{"id":"2505.22453","title":"First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training","created":"2025-05-28","cited_by_count":34},{"id":"2505.20282","title":"One-shot Entropy Minimization","created":"2025-05-26","cited_by_count":32},{"id":"2207.11971","title":"Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer","created":"2022-07-25","cited_by_count":21},{"id":"2505.10554","title":"Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models","created":"2025-05-15","cited_by_count":18},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14},{"id":"2405.07414","title":"Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains","created":"2024-05-13","cited_by_count":12},{"id":"2505.19439","title":"Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers","created":"2025-05-26","cited_by_count":11},{"id":"2505.10185","title":"The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think","created":"2025-05-15","cited_by_count":9},{"id":"2406.16069","title":"FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models","created":"2024-06-23","cited_by_count":7}],"next_cursor":null}