{"total":20,"rows":[{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92,"area":"lr"},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2507.07562","title":"The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs","created":"2025-07-10","cited_by_count":12,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2502.09056","title":"Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe","created":"2025-02-13","cited_by_count":9,"area":"lr"},{"id":"2507.01887","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","created":"2025-07-02","cited_by_count":9,"area":"lr"},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2505.17592","title":"AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model","created":"2025-05-23","cited_by_count":7,"area":"lr"},{"id":"2412.03467","title":"Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning","created":"2024-12-04","cited_by_count":6,"area":"lr"},{"id":"2511.07581","title":"Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models","created":"2025-11-10","cited_by_count":5,"area":"lr"},{"id":"2509.01363","title":"Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic","created":"2025-09-01","cited_by_count":4,"area":"lr"},{"id":"2509.22034","title":"The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging","created":"2025-09-26","cited_by_count":4,"area":"lr"},{"id":"2604.11399","title":"Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2508.08665","title":"Aryabhata: An exam-focused language model for JEE Math","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2509.00309","title":"Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2601.14053","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2607.14895","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","created":"2026-07-16","cited_by_count":0,"area":"lr"}],"next_cursor":null}