Image de couverture de livre

Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shi, Hengyu, Han, Tianyang, Wang, Peizhe, Wang, Zhiling, Yang, Xu, Su, Junhao
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
par: Han, Tianyang, et autres
Publié: (2026)

Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
par: Dönder, Yusuf Denizay, et autres
Publié: (2025)

Prompt Curriculum Learning for Efficient LLM Post-Training
par: Gao, Zhaolin, et autres
Publié: (2025)

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
par: Xu, Ran, et autres
Publié: (2026)

Faster MoE LLM Inference for Extremely Large Models
par: Yang, Haoqi, et autres
Publié: (2025)

Consolidating Rewarded Perturbations for LLM Post-Training
par: Zhang, Zheyu, et autres
Publié: (2026)

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
par: Ding, Bowen, et autres
Publié: (2025)

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
par: Pouransari, Hadi, et autres
Publié: (2024)

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
par: Li, Yaxuan, et autres
Publié: (2026)

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
par: Xu, Yang, et autres
Publié: (2024)

Replacement Learning: Training Neural Networks with Fewer Parameters
par: Zhang, Yuming, et autres
Publié: (2026)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
par: Liu, Yixin, et autres
Publié: (2026)

Cascade Speculative Drafting for Even Faster LLM Inference
par: Chen, Ziyi, et autres
Publié: (2023)

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
par: Zhao, Ji, et autres
Publié: (2026)

Rethinking LLM Ensembling from the Perspective of Mixture Models
par: Fu, Jiale, et autres
Publié: (2026)

Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning
par: Walton, Steven
Publié: (2025)

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
par: Zhu, Dingwei, et autres
Publié: (2026)

Scaling Laws for Post Training Quantized Large Language Models
par: Xu, Zifei, et autres
Publié: (2024)

Faster LLM Inference via Sequential Monte Carlo
par: Emara, Yahya, et autres
Publié: (2026)

Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning
par: Song, Dezhao, et autres
Publié: (2026)

LLM Router: Rethinking Routing with Prefill Activations
par: Varshney, Tanay, et autres
Publié: (2026)

Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?
par: Wang, Shaobo, et autres
Publié: (2025)

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
par: Du, He, et autres
Publié: (2026)

CLUE: Conflict-guided Localization for LLM Unlearning Framework
par: Chen, Hang, et autres
Publié: (2025)

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training
par: Pan, Chengjun, et autres
Publié: (2026)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
par: Zhou, Jin Peng, et autres
Publié: (2025)

DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
par: Wang, Zhenting, et autres
Publié: (2025)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
par: Yu, Peiqi, et autres
Publié: (2026)

Value Drifts: Tracing Value Alignment During LLM Post-Training
par: Bhatia, Mehar, et autres
Publié: (2025)

Muon is Scalable for LLM Training
par: Liu, Jingyuan, et autres
Publié: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
par: Xu, Hongling, et autres
Publié: (2025)

Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems
par: Barker, Matthew, et autres
Publié: (2025)

Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
par: Liu, Haoxin, et autres
Publié: (2026)

RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
par: Jiang, Haoxiang, et autres
Publié: (2026)

Towards Lifelong Learning of Large Language Models: A Survey
par: Zheng, Junhao, et autres
Publié: (2024)

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
par: Wu, Xixi, et autres
Publié: (2026)

Can Language Models Learn Typologically Implausible Languages?
par: Xu, Tianyang, et autres
Publié: (2025)

FlashDecoding++: Faster Large Language Model Inference on GPUs
par: Hong, Ke, et autres
Publié: (2023)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
par: Huang, Wei, et autres
Publié: (2024)

Post-training an LLM for RAG? Train on Self-Generated Demonstrations
par: Finlayson, Matthew, et autres
Publié: (2025)