{"total":28,"rows":[{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2503.19755","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","created":"2025-03-25","cited_by_count":178,"area":"lr"},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"area":"lr"},{"id":"2310.16069","title":"CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting","created":"2023-10-24","cited_by_count":28,"area":"lr"},{"id":"2407.05013","title":"Progress or Regress? Self-Improvement Reversal in Post-training","created":"2024-07-06","cited_by_count":23,"area":"lr"},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2205.08794","title":"LogiGAN: Learning Logical Reasoning via Adversarial Pre-training","created":"2022-05-18","cited_by_count":11,"area":"lr"},{"id":"2508.04524","title":"RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection","created":"2025-08-06","cited_by_count":8,"area":"lr"},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2210.14914","title":"Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability","created":"2022-10-26","cited_by_count":7,"area":"lr"},{"id":"2511.21667","title":"Escaping the Verifier: Learning to Reason via Demonstrations","created":"2025-11-26","cited_by_count":7,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2509.07820","title":"Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach","created":"2025-09-09","cited_by_count":3,"area":"lr"},{"id":"2403.03190","title":"Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability","created":"2024-03-05","cited_by_count":2,"area":"lr"},{"id":"2604.13660","title":"VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection","created":"2026-04-15","cited_by_count":2,"area":"lr"},{"id":"2405.09521","title":"Declarative Design of Neural Predicates in Neuro-Symbolic Systems","created":"2024-05-15","cited_by_count":1,"area":"lr"},{"id":"2407.02688","title":"Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability","created":"2024-07-02","cited_by_count":1,"area":"lr"},{"id":"2506.22036","title":"Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion","created":"2025-06-27","cited_by_count":1,"area":"lr"},{"id":"2509.25736","title":"Think Less, Label Better: Multi-Stage Domain-Grounded Synthetic Data Generation for Fine-Tuning Large Language Models in Telecommunications","created":"2025-09-30","cited_by_count":1,"area":"lr"},{"id":"2403.03452","title":"D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability","created":"2024-03-06","cited_by_count":0,"area":"lr"},{"id":"2505.18485","title":"The Prompt is Mightier than the Example","created":"2025-05-24","cited_by_count":0,"area":"lr"},{"id":"2508.15387","title":"DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Ability","created":"2025-08-21","cited_by_count":0,"area":"lr"},{"id":"2601.19122","title":"Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2605.05438","title":"On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2609.16255","title":"Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}