Cover Image

PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Ruishuo, Chen, Yu, Li, Zhuoran, Huang, Longbo
Format:	Preprint
Published:	2026
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

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
by: Chen, Ruishuo, et al.
Published: (2025)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
by: Li, Ziniu, et al.
Published: (2025)

Offline Critic-Guided Diffusion Policy for Multi-User Delay-Constrained Scheduling
by: Li, Zhuoran, et al.
Published: (2025)

Reparameterization Flow Policy Optimization
by: Zhong, Hai, et al.
Published: (2026)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

FlowRL: Matching Reward Distributions for LLM Reasoning
by: Zhu, Xuekai, et al.
Published: (2025)

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
by: Hu, Rui, et al.
Published: (2024)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
by: Li, Yawei, et al.
Published: (2026)

Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
by: Peng, Dan, et al.
Published: (2025)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
by: Liu, Mingjie, et al.
Published: (2025)

A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis
by: Gao, Xin, et al.
Published: (2025)

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
by: Li, Ming, et al.
Published: (2024)

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs
by: Ren, Yanwei, et al.
Published: (2025)

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs
by: Yang, Hongming, et al.
Published: (2025)

Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling
by: Bratulić, Jelena, et al.
Published: (2025)

PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
by: Wang, Xinyu, et al.
Published: (2025)

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
by: Wang, Zihan, et al.
Published: (2026)

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
by: Wu, Yutong, et al.
Published: (2025)

DB-LLM: Accurate Dual-Binarization for Efficient LLMs
by: Chen, Hong, et al.
Published: (2024)

Reparameterization Proximal Policy Optimization
by: Zhong, Hai, et al.
Published: (2025)

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs
by: Xu, Yongqin, et al.
Published: (2024)

OM2P: Offline Multi-Agent Mean-Flow Policy
by: Li, Zhuoran, et al.
Published: (2025)

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
by: Monsefi, Amin Karimi, et al.
Published: (2026)

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
by: He, Jianliang, et al.
Published: (2024)

TruthFlow: Truthful LLM Generation via Representation Flow Correction
by: Wang, Hanyu, et al.
Published: (2025)

Beyond Shallow Behavior: Task-Efficient Value-Based Multi-Task Offline MARL via Skill Discovery
by: Wang, Xun, et al.
Published: (2025)

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

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
by: Dang, John, et al.
Published: (2024)

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
by: Ou, Jingyang, et al.
Published: (2025)

Mode-Conditioning Unlocks Superior Test-Time Scaling
by: Wu, Chen Henry, et al.
Published: (2025)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
by: Luo, Ruilin, et al.
Published: (2025)

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
by: Altabaa, Awni, et al.
Published: (2025)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
by: Chen, Yanda, et al.
Published: (2024)

MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
by: Chen, Guoxin, et al.
Published: (2025)

Unlocking Public Catalogues: Instruction-Tuning LLMs for ICD Coding of German Tumor Diagnoses
by: Lenz, Stefan, et al.
Published: (2025)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
by: Tan, Zhen, et al.
Published: (2026)

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment
by: Zhang, Jinghao, et al.
Published: (2025)

Tree Matching Networks for Natural Language Inference: Parameter-Efficient Semantic Understanding via Dependency Parse Trees
by: Lunder, Jason
Published: (2025)

Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization
by: Xiong, Boya, et al.
Published: (2025)