Imagen de Portada

RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Zhehao, Liu, Yuhang, Lin, Baijiong, Lou, Yixin, He, Zhengbao, Tian, Hanling, Li, Tao, Huang, Xiaolin
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training
por: Huang, Zhehao, et al.
Publicado: (2025)

Towards Natural Machine Unlearning
por: He, Zhengbao, et al.
Publicado: (2024)

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
por: Huang, Zhehao, et al.
Publicado: (2024)

A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
por: Huang, Zhehao, et al.
Publicado: (2025)

VL-RouterBench: A Benchmark for Vision-Language Model Routing
por: Huang, Zhehao, et al.
Publicado: (2025)

Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
por: Liu, Yuhang, et al.
Publicado: (2025)

Trainable Weight Averaging: Accelerating Training and Improving Generalization
por: Li, Tao, et al.
Publicado: (2022)

Remaining-data-free Machine Unlearning by Suppressing Sample Contribution
por: Cheng, Xinwen, et al.
Publicado: (2024)

Friendly Sharpness-Aware Minimization
por: Li, Tao, et al.
Publicado: (2024)

Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression
por: Huang, Jiameng, et al.
Publicado: (2025)

MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes
por: Yang, Ruikai, et al.
Publicado: (2024)

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
por: Li, Tao, et al.
Publicado: (2024)

Inverse-Free Fast Natural Gradient Descent Method for Deep Learning
por: Ou, Xinwei, et al.
Publicado: (2024)

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
por: Wu, Yingwen, et al.
Publicado: (2024)

Online Continual Learning via Logit Adjusted Softmax
por: Huang, Zhehao, et al.
Publicado: (2023)

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
por: He, Tao, et al.
Publicado: (2025)

EMR-Merging: Tuning-Free High-Performance Model Merging
por: Huang, Chenyu, et al.
Publicado: (2024)

When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
por: Li, Xiaomin, et al.
Publicado: (2025)

Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information
por: Cheng, Xinwen, et al.
Publicado: (2026)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
por: Lou, Xinyue, et al.
Publicado: (2025)

Large Language Model Instruction Following: A Survey of Progresses and Challenges
por: Lou, Renze, et al.
Publicado: (2023)

Toward Zero-Shot Instruction Following
por: Lou, Renze, et al.
Publicado: (2023)

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
por: Kwon, Yongchan, et al.
Publicado: (2025)

A Riemannian Accelerated Proximal Gradient Method
por: Feng, Shuailing, et al.
Publicado: (2025)

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
por: Zou, Tao, et al.
Publicado: (2025)

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
por: Sun, Yuchong, et al.
Publicado: (2023)

RAIN: Secure and Robust Aggregation under Shuffle Model of Differential Privacy
por: Li, Yuhang, et al.
Publicado: (2026)

Crashworthiness Analysis of the Gradient Fractal Double Square Tube
por: Jinjin Huang, et al.
Publicado: (2025)

Efficient Reasoning with Balanced Thinking
por: Li, Yulin, et al.
Publicado: (2026)

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
por: Sun, Wangtao, et al.
Publicado: (2024)

Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
por: Kang, Myeongkyun, et al.
Publicado: (2026)

Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
por: Karov, Bar, et al.
Publicado: (2025)

THE RAIN'S ETERNAL ECHO
por: ANTIQUANDO, ADVEN SHELLA E.
Publicado: (2025)

ASSESSING THE RAIN EROSIVITY AND RAIN DISTRIBUTION IN DIFFERENT AGRO-CLIMATOLOGICAL ZONES IN VENEZUELA
por: Deyanira Lobo Lujan
Publicado: (2005)

A Comprehensive Study on Quantization Techniques for Large Language Models
por: Lang, Jiedong, et al.
Publicado: (2024)

Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
por: Xia, Tian
Publicado: (2026)

Thinking LLMs: General Instruction Following with Thought Generation
por: Wu, Tianhao, et al.
Publicado: (2024)

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
por: Qin, Yulei, et al.
Publicado: (2025)

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
por: Fu, Tingchen, et al.
Publicado: (2025)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
por: Tang, Yao, et al.
Publicado: (2026)