paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

MT

Molei Tao

ICML 2026×7推理效率与系统强化学习与后训练多模态长上下文与架构

新星分贡献者

64

一作贡献0

核心/参与34

方向广度10

合作网络12

0 一作 · 7 篇 · ICML 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

7

作者位次 #6/9ICML 2026Poster

Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

Shufan Li · Yuchen Zhu · Kangning Liu · Zhe Lin · Yongxin Chen · Molei Tao · Aditya Grover · Jiuxiang Gu · Jason Kuen

推理多模态长上下文与架构OpenReview

作者位次 #9/10ICML 2026Poster· Applications / Chemistry, Physics, and Earth Sciences

MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Metadynamics

Xiaochen Du · Juno Nam · Jaemoo Choi · Wei Guo · Sathya Edamadaka · Junyi Sha · Elton Pan · Yongxin Chen · Molei Tao · Rafael Gomez-Bombarelli

作者位次 #8/9ICML 2026Poster· Probabilistic Methods / Monte Carlo and Sampling Methods

Discrete Adjoint Schrödinger Bridge Sampler

Wei Guo · Yuchen Zhu · Xiaochen Du · Juno Nam · Yongxin Chen · Rafael Gomez-Bombarelli · Guan-Horng Liu · Molei Tao · Jaemoo Choi

作者位次 #3/3ICML 2026Spotlight· Deep Learning / Generative Models and Autoencoders

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

Kijung Jeon · Michael Muehlebach · Molei Tao

效率与系统OpenReview

作者位次 #8/11ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

Jinbin Bai · Yixuan Li · Yuchen Zhu · Yi Xin · Qingyu Shi · Aosong Feng · Xiaohong Liu · Molei Tao · Jianru Xue · Xiangtai Li · Ming-Hsuan Yang

推理效率与系统检索与知识OpenReview

作者位次 #6/7ICML 2026Spotlight· Deep Learning / Generative Models and Autoencoders

Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization

Yuchen Zhu · Wei Guo · Jaemoo Choi · Petr Molodyk · Bo Yuan · Molei Tao · Yongxin Chen

推理强化学习与后训练OpenReview

作者位次 #8/9ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

Jaemoo Choi · Yuchen Zhu · Wei Guo · Petr Molodyk · Bo Yuan · Jinbin Bai · Yi Xin · Molei Tao · Yongxin Chen

强化学习与后训练OpenReview

常见合作者

YZYuchen Zhu×5 YCYongxin Chen×5 JCJaemoo Choi×4 WGWei Guo×4 XDXiaochen Du×2 JNJuno Nam×2 RGRafael Gomez-Bombarelli×2 JBJinbin Bai×2 YXYi Xin×2 PMPetr Molodyk×2 BYBo Yuan×2 SLShufan Li