{"total":39,"rows":[{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"id":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","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":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","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":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2502.04030","title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","created":"2025-02-06","cited_by_count":4,"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":"2602.05805","title":"NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2505.16151","title":"Training-Free Reasoning and Reflection in MLLMs","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2505.22635","title":"Learning Composable Chains-of-Thought","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2511.02451","title":"Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2605.12419","title":"ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2607.18026","title":"Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2609.00746","title":"Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis","created":"2026-09-01","cited_by_count":1,"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":"2603.21705","title":"Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2605.14386","title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","created":"2026-05-14","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"},{"id":"2608.06699","title":"AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models","created":"2026-08-07","cited_by_count":0,"area":"lr"},{"id":"2608.10447","title":"Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.28859","title":"The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2610.08659","title":"Selective Transfer of RL Updates for Visual Reasoning","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}