{"total":19,"rows":[{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16,"area":"lr"},{"id":"2402.02791","title":"PanGu-$\\pi$ Pro:Rethinking Optimization and Architecture for Tiny Language Models","created":"2024-02-05","cited_by_count":14,"area":"lr"},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2604.10506","title":"A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations","created":"2026-04-12","cited_by_count":4,"area":"lr"},{"id":"2312.16012","title":"Detection-based Intermediate Supervision for Visual Question Answering","created":"2023-12-26","cited_by_count":3,"area":"lr"},{"id":"2412.08347","title":"SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs","created":"2024-12-11","cited_by_count":3,"area":"lr"},{"id":"2505.20753","title":"Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2605.11491","title":"Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2302.14431","title":"Efficient Masked Autoencoders with Self-Consistency","created":"2023-02-28","cited_by_count":2,"area":"lr"},{"id":"2511.08364","title":"DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering","created":"2025-11-11","cited_by_count":2,"area":"lr"},{"id":"2507.00754","title":"Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs","created":"2025-07-01","cited_by_count":1,"area":"lr"},{"id":"2604.08140","title":"Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2609.03151","title":"BASP: Communication-Efficient Batch-Aware Sequence Parallelism for LLM Training","created":"2026-09-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}