Cover Image

Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Liangyu, Xie, Huanyi, Wang, Xinhai, Huang, Tianjin, Li, Mengdi, Wang, Di
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
by: Wang, Liangyu, et al.
Published: (2025)

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
by: Wang, Xinhai, et al.
Published: (2025)

ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
by: Wang, Liangyu, et al.
Published: (2025)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
by: Wang, Liangyu, et al.
Published: (2025)

The Compositional Architecture of Regret in Large Language Models
by: Cui, Xiangxiang, et al.
Published: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
by: Wang, Chen, et al.
Published: (2025)

LOST: Low-rank and Sparse Pre-training for Large Language Models
by: Li, Jiaxi, et al.
Published: (2025)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
by: Zhang, Jiaming, et al.
Published: (2026)

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
by: Huang, Tianjin, et al.
Published: (2025)

DiRL: An Efficient Post-Training Framework for Diffusion Language Models
by: Zhu, Ying, et al.
Published: (2025)

Attributing Data for Sharpness-Aware Minimization
by: Ren, Chenyang, et al.
Published: (2025)

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
by: Wu, Jiahao, et al.
Published: (2026)

OpenClaw-RL: Train Any Agent Simply by Talking
by: Wang, Yinjie, et al.
Published: (2026)

Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
by: Xie, Huanyi, et al.
Published: (2025)

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
by: Wang, Yinjie, et al.
Published: (2026)

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
by: Gu, Hao, et al.
Published: (2026)

Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
by: Li, Yangyi, et al.
Published: (2025)

Group Causal Policy Optimization for Post-Training Large Language Models
by: Gu, Ziyin, et al.
Published: (2025)

Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
by: Sun, Xinhai
Published: (2026)

JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
by: Hu, Zhengding, et al.
Published: (2026)

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
by: Zhang, Jun, et al.
Published: (2025)

Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training
by: Wu, Yanru, et al.
Published: (2026)

SAIL: Self-Improving Efficient Online Alignment of Large Language Models
by: Ding, Mucong, et al.
Published: (2024)

Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
by: Zhang, Zizhuo, et al.
Published: (2025)

Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling
by: Huang, Yongqi, et al.
Published: (2025)

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
by: Mao, Yixiu, et al.
Published: (2026)

DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
by: Gai, Jiading, et al.
Published: (2026)

An Empirical Study of Sample Selection Strategies for Large Language Model Repair
by: Li, Xuran, et al.
Published: (2025)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
by: Yu, Peiqi, et al.
Published: (2026)

Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks
by: Li, Zihao, et al.
Published: (2023)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
by: Qu, Yun, et al.
Published: (2026)

FlashSampling: Fast and Memory-Efficient Exact Sampling
by: Ruiz, Tomas, et al.
Published: (2026)

Differentially Private Non-convex Distributionally Robust Optimization
by: Xu, Difei, et al.
Published: (2026)

Uncertainty-aware Language Guidance for Concept Bottleneck Models
by: Li, Yangyi, et al.
Published: (2026)

Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models
by: Ji, Xiang, et al.
Published: (2024)

Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
by: Guo, Yingqing, et al.
Published: (2025)

Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics
by: Li, Liangyu, et al.
Published: (2026)

Learning Dynamics in RL Post-Training for Language Models
by: Tomihari, Akiyoshi
Published: (2026)

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
by: Han, Zhenyu, et al.
Published: (2025)

RL-PINNs: Reinforcement Learning-Driven Adaptive Sampling for Efficient Training of PINNs
by: Song, Zhenao
Published: (2025)