Imagen de Portada

Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zeng, Fanqin, Hong, Feng, Yu, Geng, Zheng, Huangjie, Cao, Xiaofeng, Zhang, Ya, Han, Bo, Wang, Yanfeng, Yao, Jiangchao
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
por: Hong, Feng, et al.
Publicado: (2025)

Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference
por: Ye, Yushi, et al.
Publicado: (2026)

Learning to Instruct for Visual Instruction Tuning
por: Zhou, Zhihan, et al.
Publicado: (2025)

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context
por: Mi, Maggie, et al.
Publicado: (2024)

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
por: Yu, Geng, et al.
Publicado: (2024)

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
por: Han, Wei, et al.
Publicado: (2025)

Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
por: Li, Haolin, et al.
Publicado: (2026)

TAIA: Large Language Models are Out-of-Distribution Data Learners
por: Jiang, Shuyang, et al.
Publicado: (2024)

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
por: Sun, Jingwei, et al.
Publicado: (2026)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
por: Zhou, Zhanke, et al.
Publicado: (2025)

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
por: Wang, Weixun, et al.
Publicado: (2025)

How Good Are LLMs at Out-of-Distribution Detection?
por: Liu, Bo, et al.
Publicado: (2023)

Can LLMs Detect Their Own Hallucinations?
por: Kadotani, Sora, et al.
Publicado: (2025)

G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models
por: Zhang, Tianjiao, et al.
Publicado: (2025)

Rolling Diffusion Models
por: Ruhe, David, et al.
Publicado: (2024)

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
por: Gong, Shansan, et al.
Publicado: (2025)

When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs
por: Kamoi, Ryo, et al.
Publicado: (2024)

BYOL: Bring Your Own Language Into LLMs
por: Zamir, Syed Waqas, et al.
Publicado: (2026)

LLMs Can Generate a Better Answer by Aggregating Their Own Responses
por: Li, Zichong, et al.
Publicado: (2025)

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
por: Fan, Ziqing, et al.
Publicado: (2024)

UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification
por: Dai, Tianjie, et al.
Publicado: (2023)

Investigation of the Efficiency of Roll Profiles and Technological Schemes of Deformation of Asymmetric Rolling in Relief Rolls of C11000 Copper Alloy by FEM Simulation
por: Evgeniy Panin, et al.
Publicado: (2024)

Do LLMs Benefit From Their Own Words?
por: Huang, Jenny Y., et al.
Publicado: (2026)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
por: Fan, Siqi, et al.
Publicado: (2025)

Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models
por: Li, Hao, et al.
Publicado: (2024)

Diversified Batch Selection for Training Acceleration
por: Hong, Feng, et al.
Publicado: (2024)

Single Image Rolling Shutter Removal with Diffusion Models
por: Yang, Zhanglei, et al.
Publicado: (2024)

Roll‐To‐Roll Production of Smart Dressings for Wound Monitoring
por: Ziheng Wang, et al.
Publicado: (2025)

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
por: Feng, Xiao, et al.
Publicado: (2026)

Large Language Models are In-context Teachers for Knowledge Reasoning
por: Zhao, Jiachen, et al.
Publicado: (2023)

Long-tailed Recognition with Model Rebalancing
por: Luo, Jiaan, et al.
Publicado: (2025)

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
por: Nagarajan, Vaishnavh, et al.
Publicado: (2025)

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
por: Wang, Xiyao, et al.
Publicado: (2023)

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
por: Zhou, Mingyuan, et al.
Publicado: (2024)

TreeDiff: AST-Guided Code Generation with Diffusion LLMs
por: Zeng, Yiming, et al.
Publicado: (2025)

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
por: Ghasemabadi, Amirhosein, et al.
Publicado: (2025)

Rolling Shutter Correction with Intermediate Distortion Flow Estimation
por: Cao, Mingdeng, et al.
Publicado: (2024)

Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
por: Tran, Hieu, et al.
Publicado: (2025)

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
por: Murgul, Sebastian, et al.
Publicado: (2025)

Evaluating LLMs on Chinese Idiom Translation
por: Yang, Cai, et al.
Publicado: (2025)