Cover Image

Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Chen, Ma, Yiyuan, Yang, Yuan, Liu, Deyi, Liu, Jing, Song, Zuquan, Song, Yuxin, Ren, Cheng, Zhu, Hang, Liu, Xin, Qiao, Siyuan, Zhou, Xun, Xiang, Liang, Wu, Yonghui
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
by: Zheng, Chen, et al.
Published: (2025)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
by: Lv, Ang, et al.
Published: (2025)

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
by: Yu, Qifan, et al.
Published: (2026)

LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
by: Ouyang, Xu, et al.
Published: (2026)

FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models
by: Li, Yiyuan, et al.
Published: (2024)

Regulating Cocatalyst Spin‐Electronic Structures for Achieving Solar‐To‐H 2 of 7.32% in Photothermal‐Catalytic H 2 O Overall Splitting
by: Yiyuan Liu, et al.
Published: (2025)

Reinforcement Learning Method for Zero-Sum Linear-Quadratic Stochastic Differential Games in Infinite Horizons
by: Wang, Yiyuan
Published: (2026)

A New Algorithm for Computing the Stabilizing Solution of General Periodic Time-Varying Stochastic Game-Theoretic Riccati Differential Equations
by: Wang, Yiyuan
Published: (2025)

A Unified Computational Approach for Zero-Sum Linear-Quadratic Stochastic Differential Games in Infinite Horizons
by: Wang, Yiyuan
Published: (2025)

A Convergent Algorithm Based on Deterministic Approximation for a Large Class of Regime-Switching Generalized Stochastic Game-Theoretic Riccati Differential Equations
by: Wang, Yiyuan
Published: (2025)

Mistral-C2F: Coarse to Fine Actor for Analytical and Reasoning Enhancement in RLHF and Effective-Merged LLMs
by: Zheng, Chen, et al.
Published: (2024)

Model Merging in Pre-training of Large Language Models
by: Li, Yunshui, et al.
Published: (2025)

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
by: Lai, Xunhao, et al.
Published: (2025)

Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF
by: Liu, Jing
Published: (2025)

Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF
by: Zheng, Chen, et al.
Published: (2024)

Explore the Limits of Omni-modal Pretraining at Scale
by: Zhang, Yiyuan, et al.
Published: (2024)

Subgroup learning in functional regression models under the RKHS framework
by: Guan, Xin, et al.
Published: (2025)

Change-plane analysis in functional response quantile regression
by: Guan, Xin, et al.
Published: (2025)

Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
by: Pan, Yiyuan, et al.
Published: (2025)

Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation
by: Xu, Yunzhe, et al.
Published: (2025)

BootSeer: Analyzing and Mitigating Initialization Bottlenecks in Large-Scale LLM Training
by: Li, Rui, et al.
Published: (2025)

A Novel Framework for Modeling Quarantinable Disease Transmission
by: Liu, Wenchen, et al.
Published: (2025)

Segment-Level Attribution for Selective Learning of Long Reasoning Traces
by: Wang, Siyuan, et al.
Published: (2026)

Mechanisms promoting biodiversity in ecosystems
by: Kang, Ju, et al.
Published: (2024)

BEMEval-Doc2Schema: Benchmarking Large Language Models for Structured Data Extraction in Building Energy Modeling
by: Jia, Yiyuan, et al.
Published: (2026)

Breaking the Encoder Barrier for Seamless Video-Language Understanding
by: Li, Handong, et al.
Published: (2025)

Co-Scheduling of Energy and Production in Discrete Manufacturing Considering Decision-Dependent Uncertainties
by: Pan, Yiyuan, et al.
Published: (2024)

Improving log-based anomaly detection through learned adaptive filter
by: Xiong, Yiyuan, et al.
Published: (2025)

Deep Reinforcement Learning for Artificial Upwelling Energy Management
by: Zhang, Yiyuan, et al.
Published: (2023)

MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs
by: Chen, Zhihao, et al.
Published: (2024)

Part-Attention Based Model Make Occluded Person Re-Identification Stronger
by: Chen, Zhihao, et al.
Published: (2024)

Mind the Jumps: A Scalable Robust Local Gaussian Process for Multidimensional Response Surfaces with Discontinuities
by: Adjetey, Isaac, et al.
Published: (2025)

Trajectories of temperamental shyness and attention shifting in Chinese children and their relations to psychosocial adjustment at entry to elementary school
by: Yiyuan Xu, et al.
Published: (2024)

Efficient Federated RLHF via Zeroth-Order Policy Optimization
by: Wang, Deyi, et al.
Published: (2026)

FLAME: Learning to Navigate with Multimodal LLM in Urban Environments
by: Xu, Yunzhe, et al.
Published: (2024)

Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation
by: Pan, Yiyuan, et al.
Published: (2024)

Diversified Scaling Inference in Time Series Foundation Models
by: Hua, Ruijin, et al.
Published: (2026)

Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
by: Pan, Yiyuan, et al.
Published: (2025)

Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
by: Yang, Yiyuan, et al.
Published: (2025)

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
by: Liang, Jiawei, et al.
Published: (2022)