Image de couverture de livre

Trust Region On-Policy Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xing, Xingrun, Wang, Haoqing, Gao, Boyan, Li, Ziheng, Tang, Yehui
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
par: Xia, Wei, et autres
Publié: (2026)

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
par: Long, Xiang, et autres
Publié: (2026)

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
par: Xing, Xingrun, et autres
Publié: (2024)

TRE: Encouraging Exploration in the Trust Region
par: Huang, Chao, et autres
Publié: (2026)

MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models
par: Zhang, Ying, et autres
Publié: (2024)

PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
par: Tian, Ye, et autres
Publié: (2025)

Mixture of Lookup Experts
par: Jie, Shibo, et autres
Publié: (2025)

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
par: Li, Xin, et autres
Publié: (2026)

Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
par: Yang, Xuewei, et autres
Publié: (2026)

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing
par: Rang, Miao, et autres
Publié: (2026)

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
par: Liu, Fangcheng, et autres
Publié: (2024)

PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization
par: Rahman, Ben
Publié: (2025)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
par: Zhao, Siyan, et autres
Publié: (2026)

Sinkhorn Distance Minimization for Knowledge Distillation
par: Cui, Xiao, et autres
Publié: (2024)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
par: Sherborne, Tom, et autres
Publié: (2023)

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
par: He, Wei, et autres
Publié: (2024)

SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
par: Xing, Xingrun, et autres
Publié: (2024)

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
par: Chen, Xiwen, et autres
Publié: (2026)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
par: Ju, Yiming, et autres
Publié: (2024)

A Survey of On-Policy Distillation for Large Language Models
par: Song, Mingyang, et autres
Publié: (2026)

Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
par: Ko, Jongwoo, et autres
Publié: (2026)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
par: Zhou, Yuhang, et autres
Publié: (2026)

Efficient Second-Order Neural Network Optimization via Adaptive Trust Region Methods
par: Vo, James
Publié: (2024)

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

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
par: Zheng, Binbin, et autres
Publié: (2026)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
par: Xu, Xin, et autres
Publié: (2025)

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
par: Zhao, Ziqi, et autres
Publié: (2026)

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
par: Zhang, Songming, et autres
Publié: (2025)

ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation
par: Singh, Aasheesh, et autres
Publié: (2025)

BitNet Distillation
par: Wu, Xun, et autres
Publié: (2025)

CBQ: Cross-Block Quantization for Large Language Models
par: Ding, Xin, et autres
Publié: (2023)

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
par: Jie, Shibo, et autres
Publié: (2024)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
par: Wang, Jian, et autres
Publié: (2025)

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
par: Wang, Jianze, et autres
Publié: (2026)

Self-Distilled RLVR
par: Yang, Chenxu, et autres
Publié: (2026)

A Survey on Transformer Compression
par: Tang, Yehui, et autres
Publié: (2024)

BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation
par: Jia, Chengxing, et autres
Publié: (2024)

Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
par: Li, Ziheng, et autres
Publié: (2026)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
par: Fu, Yuqian, et autres
Publié: (2026)

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
par: Yang, Wenkai, et autres
Publié: (2026)