Cover Image

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Binbin, Ma, Xing, Liang, Yiheng, Ruan, Jingqing, Fu, Xiaoliang, Lin, Kepeng, Zhu, Benchang, Zeng, Ke, Cai, Xunliang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
by: Fu, Xiaoliang, et al.
Published: (2026)

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

Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
by: Jia, Nan, et al.
Published: (2026)

How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
by: Fang, Yangyi, et al.
Published: (2026)

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
by: Liu, Qi, et al.
Published: (2025)

Explainable Reinforcement Learning via a Causal World Model
by: Yu, Zhongwei, et al.
Published: (2023)

Learning Causal Dynamics Models in Object-Oriented Environments
by: Yu, Zhongwei, et al.
Published: (2024)

From $\log π$ to $π$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
by: Fu, Xiaoliang, et al.
Published: (2026)

DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion Enhancement
by: Xie, Xinyu, et al.
Published: (2025)

Is Market a Hero or Villain? A Narrative Policy Framework Analysis of China's Patient‐Centred Healthcare Policy
by: Jingqing Yang
Published: (2026)

Multitask Vehicle Signal Recognition With Dual‐Speed Adaptive Weighting
by: Dianjing Cheng, et al.
Published: (2025)

Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification
by: Park, Youngjoon
Published: (2026)

Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making
by: Ruan, Jingqing, et al.
Published: (2023)

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
by: Hou, Wenjin, et al.
Published: (2026)

SCOPE in Cataloguing.
by: Tom, Ellen, et al.
Published: (1970)

Stability Evaluation of the Goaf Based on Combination Weighting and Cloud Model
by: Linning Guo, et al.
Published: (2024)

Leveraging Local and Global Knowledge Integration with Time-Frequency Calibrated Distillation for Speech Enhancement
by: Cheng, Jiaming, et al.
Published: (2025)

Knowledge Distillation for Variational Quantum Convolutional Neural Networks on Heterogeneous Data
by: Yu, Kai, et al.
Published: (2025)

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

Generative AI Driven Task-Oriented Adaptive Semantic Communications
by: Fu, Yuzhou, et al.
Published: (2024)

Dual-Path Enhancements in Event-Based Eye Tracking: Augmented Robustness and Adaptive Temporal Modeling
by: Truong, Hoang M., et al.
Published: (2025)

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
by: Liang, Kun, et al.
Published: (2026)

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

The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation
by: Zhang, Jiaxin, et al.
Published: (2026)

A Center‐Border Dual‐Branch Network With Dynamic Weighted Fusion for Breast Cancer Histopathology Image Classification
by: Liang Zeng, et al.
Published: (2026)

CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
by: Dong, Benchang, et al.
Published: (2024)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
by: Wang, Chen, et al.
Published: (2025)

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
by: Kwan, Wai-Chung, et al.
Published: (2026)

Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement
by: Yuan, Xihao, et al.
Published: (2025)

CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
by: Ruan, Jingqing, et al.
Published: (2024)

Distilling Reasoning Ability from Large Language Models with Adaptive Thinking
by: Chen, Xiaoshu, et al.
Published: (2024)

Two-layer consensus based on master-slave consortium chain data sharing for Internet of Vehicles
by: Zhao, Feng, et al.
Published: (2024)

SCOPE-DTI: Semi-Inductive Dataset Construction and Framework Optimization for Practical Usability Enhancement in Deep Learning-Based Drug Target Interaction Prediction
by: Chen, Yigang, et al.
Published: (2025)

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
by: Ren, Tianfei, et al.
Published: (2026)

HackaLOD: HAICu - SCOPE
by: Romein, C. A. (Annemieke)
Published: (2025)

SCOPE for Hexapod Gait Generation
by: O'Connor, Jim, et al.
Published: (2025)