Imagen de Portada

Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jia, Nan, Yang, Haojin, Ma, Xing, Lian, Jiesong, Zhang, Shuailiang, Zhang, Weipeng, Zeng, Ke, Cai, Xunliang, Sun, Zequn
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
por: Jian, Ai, et al.
Publicado: (2025)

Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents
por: Yang, Haojin, et al.
Publicado: (2026)

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
por: Zheng, Binbin, et al.
Publicado: (2026)

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
por: Zhang, Songming, et al.
Publicado: (2025)

On uniformly quasiconformal Anosov diffeomorphisms with two dimensional distributions
por: Zhang, Jiesong
Publicado: (2023)

WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
por: Yang, Haojin, et al.
Publicado: (2025)

Conflux-PSRO: Effectively Leveraging Collective Advantages in Policy Space Response Oracles
por: Huang, Yucong, et al.
Publicado: (2024)

TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
por: Jian, Ai, et al.
Publicado: (2026)

Stochastic gravitational wave background: birth from string-wall death
por: Ge, Shuailiang
Publicado: (2023)

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
por: Wei, Zhenlin, et al.
Publicado: (2026)

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
por: Zhang, Xiaoyun, et al.
Publicado: (2025)

Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oracles
por: Lian, Jiesong, et al.
Publicado: (2024)

Invariant distributions of partially hyperbolic systems: fractal graphs, excessive regularity, and rigidity
por: Xu, Disheng, et al.
Publicado: (2024)

On holomorphic partially hyperbolic systems
por: Xu, Disheng, et al.
Publicado: (2024)

New mechanism for primordial black hole formation from the QCD axion
por: Ge, Shuailiang, et al.
Publicado: (2023)

DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
por: Chen, Qingfeng, et al.
Publicado: (2025)

Clustering-Based User Selection in Federated Learning: Metadata Exploitation for 3GPP Networks
por: Zheng, Ce, et al.
Publicado: (2026)

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
por: Yao, Xincheng, et al.
Publicado: (2026)

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
por: Zhang, Xiaohui, et al.
Publicado: (2026)

When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
por: Liu, Xiaogeng, et al.
Publicado: (2026)

Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
por: Bai, Yimeng, et al.
Publicado: (2025)

Background-Enhanced Axion Force by Axion Dark Matter
por: Cheng, Yu, et al.
Publicado: (2025)

Sommerfeld Enhancement from Background Force and the Galactic Center GeV Excess
por: Cheng, Yu, et al.
Publicado: (2025)

AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction
por: Yang, Jiashu, et al.
Publicado: (2026)

Direct Detection of Dark Photon Dark Matter with the James Webb Space Telescope
por: An, Haipeng, et al.
Publicado: (2024)

In Situ Measurements of Dark Photon Dark Matter Using Parker Solar Probe: Going beyond the Radio Window
por: An, Haipeng, et al.
Publicado: (2024)

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
por: Chen, Hansheng, et al.
Publicado: (2025)

Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
por: Wei, Jingxuan, et al.
Publicado: (2024)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
por: Zhang, Xiaoyun, et al.
Publicado: (2025)

EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer
por: Zhang, Hao, et al.
Publicado: (2026)

TIP: Token Importance in On-Policy Distillation
por: Xu, Yuanda, et al.
Publicado: (2026)

Extremal distributions of partially hyperbolic systems: the Lipschitz threshold
por: Leguil, Martin, et al.
Publicado: (2026)

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
por: Wang, Haojin, et al.
Publicado: (2025)

Efficient Quantification of Multimodal Interaction at Sample Level
por: Yang, Zequn, et al.
Publicado: (2025)

T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
por: Zhang, Hongquan, et al.
Publicado: (2025)

Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency
por: Wei, Riling, et al.
Publicado: (2025)

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
por: Jiang, Yuxuan, et al.
Publicado: (2026)

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
por: Chen, Sichen, et al.
Publicado: (2024)

Data-Efficient On-Policy Distillation for Automatic Speech Recognition
por: Lin, Yu, et al.
Publicado: (2026)

Searching for Ultralight Dark Matter Conversion in Solar Corona using Low Frequency Array Data
por: An, Haipeng, et al.
Publicado: (2023)