PaperHub
影响力指数
92.97/100
前 0.4%
全站排名 #249
发表论文35 篇
平均评分5.6
年均产出11.7 篇/年

Mingyuan Zhou

Researcher@Microsoft·美国·OpenReview
研究方向

generative AI · reinforcement learning · deep generative models · deep learning · discrete data analysis · latent variable models · Bayesian analysis

6.5
15

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

ICLR 2026Poster
6.0
19

Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data

ICLR 2026Poster
5.5
17

Distilled Protein Backbone Generation

ICLR 2026Rejected
通讯
5.5
25

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

ICLR 2026Poster
通讯
4.5
17

Score Distillation of Flow Matching Models

ICLR 2026Rejected
一作
4.5
16

DLM-One: Diffusion Language Models for One-Step Sequence Generation

ICLR 2026Rejected
三作
4.0
28

Turning Uncertainty into Control: Bi-level Training with Editable Bayesian Layers

ICLR 2026Withdrawn
通讯
3.5
18

Controllable diffusion-based generation for multi-channel biological data

ICLR 2026Poster
二作
2.5
12

A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation

ICLR 2026Rejected
三作
7.8
19

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

NeurIPS 2025Spotlight
7.8
26

Generative Model Inversion Through the Lens of the Manifold Hypothesis

NeurIPS 2025Poster
通讯
7.3
19

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

NeurIPS 2025Poster
通讯
6.6
11

OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation

ICML 2025Poster
通讯
6.5
19

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

ICLR 2025Poster
一作
6.5
29

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

ICLR 2025Poster
三作
6.4
20

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

NeurIPS 2025Poster
6.3
18

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

ICLR 2025Poster
一作
6.3
23

Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer

ICLR 2025Poster
通讯
6.0
25

Advancing Graph Generation through Beta Diffusion

ICLR 2025Poster
通讯
5.8
32

DRL: Decomposed Representation Learning for Tabular Anomaly Detection

ICLR 2025Poster
5.8
31

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

ICLR 2025Rejected
5.3
23

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

ICLR 2025Rejected
通讯
5.3
23

Segmenting Text and Learning Their Rewards for Improved RLHF in Language Models

ICLR 2025Rejected
通讯
4.8
9

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

ICML 2025Poster
4.7
13

Diffusion Preference Alignment via Relative Text-Image Contrast

ICLR 2025Rejected
通讯
4.4
19

Single-Step Diffusion Model-Based Generative Model Inversion Attacks

ICLR 2025Rejected
通讯
4.0
6

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment

ICLR 2025Rejected
通讯
合作者 (20)