Image de couverture de livre

Reasoning Compression with Mixed-Policy Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Han, Wu, Mingyan, He, Bailan, Cao, Zeyu, Yan, Sikuan, Lin, Kevin Qinghong, Ding, Zifeng
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TCP: a Benchmark for Temporal Constraint-Based Planning
par: Ding, Zifeng, et autres
Publié: (2025)

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
par: Liu, Yilun, et autres
Publié: (2024)

EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
par: Zhang, Boer, et autres
Publié: (2026)

Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention
par: Lin, Wenye, et autres
Publié: (2026)

Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
par: Ding, Zifeng, et autres
Publié: (2023)

Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation
par: Prasad, Aaditya, et autres
Publié: (2024)

Paper2Video: Automatic Video Generation from Scientific Papers
par: Zhu, Zeyu, et autres
Publié: (2025)

Structural Rationale Distillation via Reasoning Space Compression
par: Yang, Jialin, et autres
Publié: (2026)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
par: Wu, Yecheng, et autres
Publié: (2026)

Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
par: Ke, Junlong, et autres
Publié: (2026)

Routing-Free Mixture-of-Experts
par: Liu, Yilun, et autres
Publié: (2026)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
par: Wang, Jiaqi, et autres
Publié: (2025)

HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
par: Ding, Ken
Publié: (2026)

Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?
par: Jin, Jiahe, et autres
Publié: (2025)

VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
par: Liu, Ye, et autres
Publié: (2025)

Mixed Distillation Helps Smaller Language Model Better Reasoning
par: Li, Chenglin, et autres
Publié: (2023)

Extreme Region Policy Distillation
par: Chen, Changyu, et autres
Publié: (2026)

OPD+: Rethinking the Advantage Design for On-Policy Distillation
par: Zhao, Hanyang, et autres
Publié: (2026)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
par: Yang, Zhicheng, et autres
Publié: (2026)

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

DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
par: Li, Gang, et autres
Publié: (2025)

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
par: Yang, Yuxiao, et autres
Publié: (2026)

Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering
par: Sui, Yuan, et autres
Publié: (2024)

Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization
par: Gu, Boyang, et autres
Publié: (2025)

PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
par: Xu, Yuanda, et autres
Publié: (2026)

MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models
par: Liao, Zhaokang, et autres
Publié: (2026)

Data-Efficient On-Policy Distillation for Automatic Speech Recognition
par: Lin, Yu, et autres
Publié: (2026)

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
par: Wang, Puyi, et autres
Publié: (2026)

OPSDL: On-Policy Self-Distillation for Long-Context Language Models
par: Zhang, Xinsen, et autres
Publié: (2026)

LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms
par: Zhang, Haoting, et autres
Publié: (2026)

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
par: Jiang, Yuxuan, et autres
Publié: (2026)

TIP: Token Importance in On-Policy Distillation
par: Xu, Yuanda, et autres
Publié: (2026)

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
par: Liang, Kun, et autres
Publié: (2026)

KDMOS:Knowledge Distillation for Motion Segmentation
par: Cao, Chunyu, et autres
Publié: (2025)

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
par: Xu, Huimin, et autres
Publié: (2025)

LRAS: Advanced Legal Reasoning with Agentic Search
par: Zhou, Yujin, et autres
Publié: (2026)

MAPO: Mixed Advantage Policy Optimization
par: Huang, Wenke, et autres
Publié: (2025)

ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
par: Lu, Guanxing, et autres
Publié: (2024)

Flow-OPD: On-Policy Distillation for Flow Matching Models
par: Fang, Zhen, et autres
Publié: (2026)

Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
par: Kim, Dohyun, et autres
Publié: (2025)