{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"2504.02495","title":"Inference-Time Scaling for Generalist Reward Modeling","created":"2025-04-03","cited_by_count":239},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136},{"id":"2511.08667","title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","created":"2025-11-11","cited_by_count":132},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117},{"id":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89},{"id":"2509.03505","title":"LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence","created":"2025-09-03","cited_by_count":79},{"id":"2510.21204","title":"Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models","created":"2025-10-24","cited_by_count":77},{"id":"2305.17535","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","created":"2023-05-27","cited_by_count":73},{"id":"2411.16646","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","created":"2024-11-25","cited_by_count":71},{"id":"1806.04613","title":"Improving Regression Performance with Distributional Losses","created":"2018-06-12","cited_by_count":67},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63},{"id":"2404.07544","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","created":"2024-04-11","cited_by_count":57},{"id":"2511.08567","title":"The Path Not Taken: RLVR Provably Learns Off the Principals","created":"2025-11-11","cited_by_count":56},{"id":"2407.04057","title":"TALENT: A Tabular Analytics and Learning Toolbox","created":"2024-07-04","cited_by_count":52},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49},{"id":"1702.08835","title":"Deep Forest","created":"2017-02-28","cited_by_count":46},{"id":"2211.16887","title":"T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction","created":"2022-11-30","cited_by_count":41},{"id":"2407.00956","title":"A Closer Look at Deep Learning Methods on Tabular Datasets","created":"2024-07-01","cited_by_count":41},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36},{"id":"2301.02819","title":"ExcelFormer: A neural network surpassing GBDTs on tabular data","created":"2023-01-07","cited_by_count":34},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28},{"id":"2504.10337","title":"Heimdall: test-time scaling on the generative verification","created":"2025-04-14","cited_by_count":26},{"id":"2506.17774","title":"PhysiX: A Foundation Model for Physics Simulations","created":"2025-06-21","cited_by_count":22},{"id":"2508.11800","title":"Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes","created":"2025-08-15","cited_by_count":22},{"id":"2503.04381","title":"TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge","created":"2025-03-06","cited_by_count":17},{"id":"2403.04182","title":"Regression-aware Inference with LLMs","created":"2024-03-07","cited_by_count":14},{"id":"2506.21718","title":"Performance Prediction for Large Systems via Text-to-Text Regression","created":"2025-06-26","cited_by_count":14},{"id":"2411.02083","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","created":"2024-11-04","cited_by_count":13},{"id":"2501.19383","title":"Decoding-based Regression","created":"2025-01-31","cited_by_count":12},{"id":"2511.16231","title":"Pass@k Metric for RLVR: A Diagnostic Tool of Exploration, But Not an Objective","created":"2025-11-20","cited_by_count":12},{"id":"2402.13425","title":"Investigating the Histogram Loss in Regression","created":"2024-02-20","cited_by_count":11},{"id":"2509.26476","title":"Regression Language Models for Code","created":"2025-09-30","cited_by_count":11},{"id":"2511.13027","title":"Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection","created":"2025-11-17","cited_by_count":9},{"id":"2410.10190","title":"Language Model Embeddings Can Be Sufficient for Bayesian Optimization","created":"2024-10-14","cited_by_count":8},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8},{"id":"2506.07109","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","created":"2025-06-08","cited_by_count":7},{"id":"2505.20993","title":"Who Reasons in the Large Language Models?","created":"2025-05-27","cited_by_count":5},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4},{"id":"2509.06806","title":"MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining","created":"2025-09-08","cited_by_count":3},{"id":"2508.21762","title":"Reasoning-Intensive Regression","created":"2025-08-29","cited_by_count":2}],"next_cursor":null}