Imagen de Portada

Param$Δ$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Sheng, Wu, Mingrui, Prasad, Karthik, Tian, Yuandong, Liu, Zechun
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
por: Zhao, Changsheng, et al.
Publicado: (2025)

AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
por: Nauman, Mohd, et al.
Publicado: (2025)

Training Large Language Models To Reason In Parallel With Global Forking Tokens
por: Jia, Sheng, et al.
Publicado: (2025)

APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models
por: Guan, Ziyi, et al.
Publicado: (2024)

Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
por: Jiang, Minhao, et al.
Publicado: (2026)

Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
por: Wang, Xinyuan, et al.
Publicado: (2025)

Large Language Models for Causal Discovery: Current Landscape and Future Directions
por: Wan, Guangya, et al.
Publicado: (2024)

Efficient Streaming Language Models with Attention Sinks
por: Xiao, Guangxuan, et al.
Publicado: (2023)

Aggressive Post-Training Compression on Extremely Large Language Models
por: Zhang, Zining, et al.
Publicado: (2024)

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
por: Huang, Pengcheng, et al.
Publicado: (2025)

Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models
por: Jiang, Haitao, et al.
Publicado: (2026)

Offline Training of Language Model Agents with Functions as Learnable Weights
por: Zhang, Shaokun, et al.
Publicado: (2024)

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
por: Zhou, Chenxi, et al.
Publicado: (2025)

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
por: Liu, Zechun, et al.
Publicado: (2024)

LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding
por: Wu, Mingrui, et al.
Publicado: (2024)

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
por: Yang, Kevin, et al.
Publicado: (2023)

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

Post-Training Language Models for Crosslingual Consistency
por: Liu, Tianyu, et al.
Publicado: (2026)

Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
por: Pipatanakul, Kunat, et al.
Publicado: (2026)

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
por: Zhang, Chuang, et al.
Publicado: (2026)

Towards a More Inclusive AI: Progress and Perspectives in Large Language Model Training for the Sámi Language
por: Paul, Ronny, et al.
Publicado: (2024)

Evaluating the Retrieval Robustness of Large Language Models
por: Cao, Shuyang, et al.
Publicado: (2025)

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
por: Huang, Xijie, et al.
Publicado: (2024)

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
por: Xiao, Guangxuan, et al.
Publicado: (2022)

Positional Encoding via Token-Aware Phase Attention
por: Wang, Yu, et al.
Publicado: (2025)

AutoMix: Automatically Mixing Language Models
por: Aggarwal, Pranjal, et al.
Publicado: (2023)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
por: Su, DiJia, et al.
Publicado: (2025)

Towards a Unified View of Large Language Model Post-Training
por: Lv, Xingtai, et al.
Publicado: (2025)

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
por: van Niekerk, Carel, et al.
Publicado: (2025)

The Super Weight in Large Language Models
por: Yu, Mengxia, et al.
Publicado: (2024)

Weights-Rotated Preference Optimization for Large Language Models
por: Yang, Chenxu, et al.
Publicado: (2025)

Token-Level Uncertainty-Aware Objective for Language Model Post-Training
por: Liu, Tingkai, et al.
Publicado: (2025)

Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
por: Tian, Yuandong
Publicado: (2024)

A Survey on Post-training of Large Language Models
por: Tie, Guiyao, et al.
Publicado: (2025)

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
por: Wu, Tianhao, et al.
Publicado: (2024)

ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
por: Han, Feijiang, et al.
Publicado: (2025)

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats
por: Zhang, Manyi, et al.
Publicado: (2026)

Language Self-Play For Data-Free Training
por: Kuba, Jakub Grudzien, et al.
Publicado: (2025)

Interactions Across Blocks in Post-Training Quantization of Large Language Models
por: Shabanovi, Khasmamad, et al.
Publicado: (2024)

Evolving Subnetwork Training for Large Language Models
por: Li, Hanqi, et al.
Publicado: (2024)