Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct
Fuente:
arXiv
Saved in:
| Main Authors: | Zheng, Haoyang, Liu, Xinyang, Kong, Cindy Xiangrui, Jiang, Nan, Hu, Zheyuan, Luo, Weijian, Deng, Wei, Lin, Guang |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
by: Kong, Cindy Xiangrui, et al.
Published: (2026)
by: Kong, Cindy Xiangrui, et al.
Published: (2026)
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
by: Wu, Junyi, et al.
Published: (2026)
by: Wu, Junyi, et al.
Published: (2026)
BLADE: Bayesian Langevin Active Discovery with Replica Exchange for Identification of Complex Systems
by: Kong, Cindy Xiangrui, et al.
Published: (2025)
by: Kong, Cindy Xiangrui, et al.
Published: (2025)
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
by: Wang, Yifei, et al.
Published: (2025)
by: Wang, Yifei, et al.
Published: (2025)
Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
by: Luo, Yihong, et al.
Published: (2025)
by: Luo, Yihong, et al.
Published: (2025)
Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
by: Luo, Weijian
Published: (2024)
by: Luo, Weijian
Published: (2024)
Generalized Discrete Diffusion with Self-Correction
by: Wang, Linxuan, et al.
Published: (2026)
by: Wang, Linxuan, et al.
Published: (2026)
Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
by: Luo, Weijian, et al.
Published: (2023)
by: Luo, Weijian, et al.
Published: (2023)
InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
by: Wei, Zhepei, et al.
Published: (2024)
by: Wei, Zhepei, et al.
Published: (2024)
Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
by: Zheng, Haoyang, et al.
Published: (2024)
by: Zheng, Haoyang, et al.
Published: (2024)
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
by: Zheng, Haoyang, et al.
Published: (2024)
by: Zheng, Haoyang, et al.
Published: (2024)
A Reparameterized Discrete Diffusion Model for Text Generation
by: Zheng, Lin, et al.
Published: (2023)
by: Zheng, Lin, et al.
Published: (2023)
Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange
by: Zheng, Haoyang, et al.
Published: (2025)
by: Zheng, Haoyang, et al.
Published: (2025)
Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
by: Zheng, Bowen, et al.
Published: (2026)
by: Zheng, Bowen, et al.
Published: (2026)
Denoising Fisher Training For Neural Implicit Samplers
by: Luo, Weijian, et al.
Published: (2024)
by: Luo, Weijian, et al.
Published: (2024)
Muti-Fidelity Prediction and Uncertainty Quantification with Laplace Neural Operators for Parametric Partial Differential Equations
by: Zheng, Haoyang, et al.
Published: (2025)
by: Zheng, Haoyang, et al.
Published: (2025)
LES-SINDy: Laplace-Enhanced Sparse Identification of Nonlinear Dynamical Systems
by: Zheng, Haoyang, et al.
Published: (2024)
by: Zheng, Haoyang, et al.
Published: (2024)
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
by: Dong, ZiYi, et al.
Published: (2026)
by: Dong, ZiYi, et al.
Published: (2026)
Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
by: Lin, Guang, et al.
Published: (2026)
by: Lin, Guang, et al.
Published: (2026)
Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
by: Wang, Weixin, et al.
Published: (2025)
by: Wang, Weixin, et al.
Published: (2025)
InstructSing: High-Fidelity Singing Voice Generation via Instructing Yourself
by: Zeng, Chang, et al.
Published: (2024)
by: Zeng, Chang, et al.
Published: (2024)
Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization
by: Chang, Yuanyuan, et al.
Published: (2025)
by: Chang, Yuanyuan, et al.
Published: (2025)
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
by: Luo, Wenyang, et al.
Published: (2025)
by: Luo, Wenyang, et al.
Published: (2025)
Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
by: Luo, Xianzhen, et al.
Published: (2024)
by: Luo, Xianzhen, et al.
Published: (2024)
Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
by: Ye, Jiacheng, et al.
Published: (2024)
by: Ye, Jiacheng, et al.
Published: (2024)
Instruct Large Language Models to Generate Scientific Literature Survey Step by Step
by: Lai, Yuxuan, et al.
Published: (2024)
by: Lai, Yuxuan, et al.
Published: (2024)
dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning
by: Chen, Shirui, et al.
Published: (2025)
by: Chen, Shirui, et al.
Published: (2025)
Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
by: Zheng, Haonan, et al.
Published: (2024)
by: Zheng, Haonan, et al.
Published: (2024)
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
by: Luo, Ziyang, et al.
Published: (2023)
by: Luo, Ziyang, et al.
Published: (2023)
A Matrix Rank Formula for Vector Bundles of Vertex Operator Algebra Coinvariants and Conformal Blocks
by: Luo, Xiangrui
Published: (2026)
by: Luo, Xiangrui
Published: (2026)
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
by: Wei, Cong, et al.
Published: (2024)
by: Wei, Cong, et al.
Published: (2024)
Mercury: Ultra-Fast Language Models Based on Diffusion
by: Labs, Inception, et al.
Published: (2025)
by: Labs, Inception, et al.
Published: (2025)
A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
by: Zheng, Haonan, et al.
Published: (2024)
by: Zheng, Haonan, et al.
Published: (2024)
LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating
by: Chen, Junting, et al.
Published: (2025)
by: Chen, Junting, et al.
Published: (2025)
TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
by: Luo, Yihong, et al.
Published: (2026)
by: Luo, Yihong, et al.
Published: (2026)
TIDE: Achieving Balanced Subject-Driven Image Generation via Target-Instructed Diffusion Enhancement
by: Lin, Jibai, et al.
Published: (2025)
by: Lin, Jibai, et al.
Published: (2025)
Fast Graph Generation via Spectral Diffusion
by: Luo, Tianze, et al.
Published: (2022)
by: Luo, Tianze, et al.
Published: (2022)
InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification
by: Hu, Yujia, et al.
Published: (2024)
by: Hu, Yujia, et al.
Published: (2024)
EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion
by: Zhang, Jian, et al.
Published: (2024)
by: Zhang, Jian, et al.
Published: (2024)
Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models
by: Li, Jijie, et al.
Published: (2025)
by: Li, Jijie, et al.
Published: (2025)
Similar Items
-
Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
by: Kong, Cindy Xiangrui, et al.
Published: (2026) -
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
by: Wu, Junyi, et al.
Published: (2026) -
BLADE: Bayesian Langevin Active Discovery with Replica Exchange for Identification of Complex Systems
by: Kong, Cindy Xiangrui, et al.
Published: (2025) -
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
by: Wang, Yifei, et al.
Published: (2025) -
Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
by: Luo, Yihong, et al.
Published: (2025)