{"total":13,"rows":[{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2506.09958","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","created":"2025-06-11","cited_by_count":11,"area":"lr"},{"id":"2410.06524","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","created":"2024-10-09","cited_by_count":6,"area":"lr"},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2407.11780","title":"SwitchCIT: Switching for Continual Instruction Tuning","created":"2024-07-16","cited_by_count":1,"area":"lr"},{"id":"2602.11516","title":"Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2512.21280","title":"SMART SLM: Structured Memory and Reasoning Transformer, A Small Language Model for Accurate Document Assistance","created":"2025-12-24","cited_by_count":0,"area":"lr"},{"id":"2604.19488","title":"CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.06165","title":"Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2606.19944","title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"}],"next_cursor":null}