Image de couverture de livre

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lazaridis, Aristotelis, Bates, Dylan, Sharma, Aman, King, Brian, Lu, Vincent, FitzGerald, Jack
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

Measuring and Eliminating Refusals in Military Large Language Models
par: FitzGerald, Jack, et autres
Publié: (2026)

EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge
par: FitzGerald, Jack, et autres
Publié: (2025)

PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint
par: Vasani, Bhoomit, et autres
Publié: (2025)

The Twin Purposes of Guided Inquiry: Guiding Student Inquiry and Evidence-Based Practice
par: FitzGerald, Lee
Publié: (2010)

MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources
par: Lee, Dongkyu, et autres
Publié: (2024)

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

Impossible Things in the Age of Reformations
par: Brian FitzGerald
Publié: (2025)

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

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

DP-OPD: Differentially Private On-Policy Distillation for Language Models
par: Khadem, Fatemeh, et autres
Publié: (2026)

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

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
par: Chen, Xianwei, 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)

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

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
par: Cao, Di, et autres
Publié: (2026)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
par: Yuan, Qianhao, et autres
Publié: (2026)

Privileged Information Distillation for Language Models
par: Penaloza, Emiliano, et autres
Publié: (2026)

QSTToolkit: A Python Library for Deep Learning Powered Quantum State Tomography
par: FitzGerald, George, et autres
Publié: (2025)

Catherine Vézina, Diplomacia migratoria: una historia transnacional del Programa Bracero, 1947-1952, México, Centro de Investigación y Docencia Económicas, 2017, 404 pp. ISBN 978-607-446-102-2
par: David Scott FitzGerald
Publié: (2020)

Erika Pani, Para pertenecer a la gran familia mexicana: procesos de naturalización en el siglo xix, México, El Colegio de México, 2015, 204 pp. ISBN 978-607-462-713-8
par: David Scott FitzGerald
Publié: (2016)

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
par: Zhang, Xingjian, et autres
Publié: (2025)

Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods
par: Shin, Min Kyu, et autres
Publié: (2024)

Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
par: Lin, Zizhuo, et autres
Publié: (2026)

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback
par: Chen, Bin, et autres
Publié: (2026)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
par: Zhao, Anhao, et autres
Publié: (2026)

OISD: On-Policy Internal Self-Distillation of Language Models
par: Liu, Xinyu, et autres
Publié: (2026)

Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport
par: Aslam, Muhammad Haseeb, et autres
Publié: (2024)

"Just Let Me Go at It": Exploring Students' Use and Perceptions of Guided Inquiry
par: Garrison, Kasey L., et autres
Publié: (2018)

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

Depth-Guided Self-Supervised Human Keypoint Detection via Cross-Modal Distillation
par: Anand, Aman, et autres
Publié: (2024)

Random walks in Weyl chambers
par: Denisov, Denis, et autres
Publié: (2025)

Critique de la méthode de distinction entre poissons anadromes et dulcicoles de la même espèce par la teneur en strontium de leurs écailles
par: Castonguay, M., FitzGerald, G. J
Publié: (1982)

Ordered random walks and the Airy line ensemble
par: Denisov, Denis, et autres
Publié: (2024)

Library Signage: Applications for the Apple Macintosh and MacPaint.
par: Diskin, Jill A., et autres
Publié: (1984)

EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data
par: Chen, Xuetian, et autres
Publié: (2024)

Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
par: Singhal, Ronit, et autres
Publié: (2024)

ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
par: Zhang, Yulin, et autres
Publié: (2026)

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
par: Zhu, Siqi, et autres
Publié: (2026)

AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
par: Nguyen, Duy, et autres
Publié: (2026)

EDGE: A Theoretical Framework for Misconception-Aware Adaptive Learning
par: Verma, Ananda Prakash
Publié: (2025)