Cover Image

SABER: Switchable and Balanced Training for Efficient LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Kai, Zhao, Yanjun, Song, Jiaming, He, Shien, Zhang, Lusheng, Zhang, Qiang, Li, Tianjiao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
by: Zhao, Weilin, et al.
Published: (2025)

Efficient Reasoning with Balanced Thinking
by: Li, Yulin, et al.
Published: (2026)

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
by: Chen, Zhipeng, et al.
Published: (2025)

Memory-Efficient LLM Training with Online Subspace Descent
by: Liang, Kaizhao, et al.
Published: (2024)

Switchable Decision: Dynamic Neural Generation Networks
by: Zhang, Shujian, et al.
Published: (2024)

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
by: Zeng, Weihao, et al.
Published: (2024)

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
by: Duo, Jiangshan, et al.
Published: (2026)

Training Tensor Attention Efficiently: From Cubic to Almost Linear Time
by: Cao, Yang, et al.
Published: (2024)

Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge
by: Zhang, Wenbo, et al.
Published: (2026)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
by: Li, Changming, et al.
Published: (2026)

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

Scaling with Collapse: Efficient and Predictable Training of LLM Families
by: Bergsma, Shane, et al.
Published: (2025)

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
by: He, Haoyang, et al.
Published: (2026)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
by: Liu, Yixin, et al.
Published: (2026)

Sliding Window Attention Training for Efficient Large Language Models
by: Fu, Zichuan, et al.
Published: (2025)

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
by: Zhao, Shiwan, et al.
Published: (2026)

AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance
by: He, Lixuan, et al.
Published: (2025)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
by: Xi, Zhiheng, et al.
Published: (2024)

RelayLLM: Efficient Reasoning via Collaborative Decoding
by: Huang, Chengsong, et al.
Published: (2026)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
by: Rai, Arushi, et al.
Published: (2026)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
by: Xiao, Chaojun, et al.
Published: (2024)

LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning
by: Fang, Tao, et al.
Published: (2024)

Learning to Reason Efficiently with A* Post-Training
by: Opedal, Andreas, et al.
Published: (2026)

Token-Budget-Aware LLM Reasoning
by: Han, Tingxu, et al.
Published: (2024)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
by: Ju, Yiming, et al.
Published: (2024)

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
by: Shi, Jiajun, et al.
Published: (2025)

Better LLM Reasoning via Dual-Play
by: Zhang, Zhengxin, et al.
Published: (2025)

Contextual Drag: How Errors in the Context Affect LLM Reasoning
by: Cheng, Yun, et al.
Published: (2026)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
by: Zhou, Zhi, et al.
Published: (2025)

Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
by: Zhao, Zirui, et al.
Published: (2024)

Efficient Reasoning with Hidden Thinking
by: Shen, Xuan, et al.
Published: (2025)

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
by: Xu, Fangzhi, et al.
Published: (2025)

Muon is Scalable for LLM Training
by: Liu, Jingyuan, et al.
Published: (2025)

GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
by: Zhang, Yunan, et al.
Published: (2025)

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
by: Ling Team, et al.
Published: (2025)

Regurgitative Training: The Value of Real Data in Training Large Language Models
by: Zhang, Jinghui, et al.
Published: (2024)

DataSciBench: An LLM Agent Benchmark for Data Science
by: Zhang, Dan, et al.
Published: (2025)

R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training
by: Ge, Albert, et al.
Published: (2025)

EfficientLLM: Efficiency in Large Language Models
by: Yuan, Zhengqing, et al.
Published: (2025)

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
by: Wang, Shenzhi, et al.
Published: (2025)