Imagen de Portada

Reinforcement Mid-Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tian, Yijun, Chen, Shaoyu, Xu, Zhichao, Wang, Yawei, Bi, Jinhe, Han, Peng, Wang, Wei
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
por: Xu, Zhichao, et al.
Publicado: (2025)

Reinforcement Learning for LLM Post-Training: A Survey
por: Wang, Zhichao, et al.
Publicado: (2024)

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
por: Wang, Yujun, et al.
Publicado: (2025)

Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning
por: Tian, Yunshuo, et al.
Publicado: (2026)

A Survey on LLM Mid-Training
por: Tu, Chengying, et al.
Publicado: (2025)

HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench
por: Wang, Yueyang, et al.
Publicado: (2026)

LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
por: Xu, Zhichao, et al.
Publicado: (2026)

Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation
por: Feng, Weiqi, et al.
Publicado: (2024)

CSPLADE: Learned Sparse Retrieval with Causal Language Models
por: Xu, Zhichao, et al.
Publicado: (2025)

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
por: Bi, Jinhe, et al.
Publicado: (2024)

Large-Scale Diverse Synthesis for Mid-Training
por: Zhang, Xuemiao, et al.
Publicado: (2025)

RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following
por: Wang, Zhichao, et al.
Publicado: (2025)

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
por: Tian, Yijun, et al.
Publicado: (2024)

PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning
por: Pentyala, Shiva Kumar, et al.
Publicado: (2024)

Rethinking On-policy Optimization for Query Augmentation
por: Xu, Zhichao, et al.
Publicado: (2025)

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
por: Zhang, Charlie, et al.
Publicado: (2025)

Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
por: Lyu, Mengxian, et al.
Publicado: (2026)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
por: Yang, Wang, et al.
Publicado: (2026)

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
por: Wang, Zhichao
Publicado: (2025)

Thoth: Mid-Training Bridges LLMs to Time Series Understanding
por: Lin, Jiafeng, et al.
Publicado: (2026)

1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training
por: Zhao, Han, et al.
Publicado: (2025)

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
por: Tian, Xiaoyu, et al.
Publicado: (2025)

Mid-Training of Large Language Models: A Survey
por: Mo, Kaixiang, et al.
Publicado: (2025)

Reinforcement Pre-Training
por: Dong, Qingxiu, et al.
Publicado: (2025)

How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
por: Ji, Yunjie, et al.
Publicado: (2025)

Learning to Reason as Action Abstractions with Scalable Mid-Training RL
por: Zhang, Shenao, et al.
Publicado: (2025)

SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media
por: Xu, Xilai, et al.
Publicado: (2025)

Re-ReST: Reflection-Reinforced Self-Training for Language Agents
por: Dou, Zi-Yi, et al.
Publicado: (2024)

Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting
por: Xu, Bowen, et al.
Publicado: (2024)

From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
por: Liu, Tianqiao, et al.
Publicado: (2025)

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
por: Wang, Zengzhi, et al.
Publicado: (2025)

Context-aware Decoding Reduces Hallucination in Query-focused Summarization
por: Xu, Zhichao
Publicado: (2023)

RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers
por: Xu, Zhichao
Publicado: (2024)

Distillation versus Contrastive Learning: How to Train Your Rerankers
por: Xu, Zhichao, et al.
Publicado: (2025)

JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
por: Wang, Junda, et al.
Publicado: (2024)

AlignSAE: Concept-Aligned Sparse Autoencoders
por: Yang, Minglai, et al.
Publicado: (2025)

Off-Policy Value-Based Reinforcement Learning for Large Language Models
por: Wang, Peng-Yuan, et al.
Publicado: (2026)

DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition
por: Wang, Yi-Cheng, et al.
Publicado: (2024)

Diversity Enhances an LLM's Performance in RAG and Long-context Task
por: Wang, Zhichao, et al.
Publicado: (2025)

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
por: Bi, Jinhe, et al.
Publicado: (2025)