{"total":47,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2602.11451","title":"LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation","created":"2026-02-11","cited_by_count":61,"area":"lr"},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23,"area":"lr"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2605.11011","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","created":"2026-05-10","cited_by_count":15,"area":"lr"},{"id":"2605.12466","title":"Solve the Loop: Attractor Models for Language and Reasoning","created":"2026-05-12","cited_by_count":13,"area":"lr"},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2503.10061","title":"Compute Optimal Scaling of Skills: Knowledge vs Reasoning","created":"2025-03-13","cited_by_count":11,"area":"lr"},{"id":"2603.08391","title":"Adaptive Loops and Memory in Transformers: Think Harder or Know More?","created":"2026-03-09","cited_by_count":11,"area":"lr"},{"id":"2602.01395","title":"Rethinking Selective Knowledge Distillation","created":"2026-02-01","cited_by_count":9,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2410.06735","title":"Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?","created":"2024-10-09","cited_by_count":5,"area":"lr"},{"id":"2412.06845","title":"7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement","created":"2024-12-08","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2506.07463","title":"CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2512.21231","title":"MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models","created":"2025-12-24","cited_by_count":3,"area":"lr"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2509.16551","title":"Rethinking the Role of Text Complexity in Language Model Pretraining","created":"2025-09-20","cited_by_count":2,"area":"lr"},{"id":"2602.04556","title":"Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and Updates","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2602.20528","title":"Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2409.09613","title":"Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora","created":"2024-09-15","cited_by_count":1,"area":"lr"},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2503.18908","title":"FFN Fusion: Rethinking Sequential Computation in Large Language Models","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2505.22202","title":"Latent Reasoning via Sentence Embedding Prediction","created":"2025-05-28","cited_by_count":1,"area":"lr"},{"id":"2510.18909","title":"Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2602.11081","title":"SteuerLLM: Local specialized large language model for German tax law analysis","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2605.06997","title":"Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2606.16517","title":"How Post-Training Shapes Biological Reasoning Models","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2608.21308","title":"Rethinking Expressivity and Efficiency in Test-Time Training","created":"2026-08-21","cited_by_count":1,"area":"lr"},{"id":"2412.19638","title":"Xmodel-2 Technical Report","created":"2024-12-27","cited_by_count":0,"area":"lr"},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2602.13940","title":"You Can Learn Tokenization End-to-End with Reinforcement Learning","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.24809","title":"Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2609.29845","title":"Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32791","title":"$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.19100","title":"GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}