paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

DB

David Brandfonbrener

ICLR 2026×3强化学习与后训练长上下文与架构理论与学习动力学

新星分贡献者

55

一作贡献0

核心/参与26

方向广度6

合作网络12

0 一作 · 3 篇 · ICLR 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

3

作者位次 #8/9ICLR 2026Oral· Reinforcement Learning / Deep RL

The Art of Scaling Reinforcement Learning Compute for LLMs

Devvrit Khatri · Lovish Madaan · Rishabh Tiwari · Rachit Bansal · Venkata Sai Surya Subramanyam Duvvuri · Manzil Zaheer · Inderjit Dhillon · David Brandfonbrener · Rishabh Agarwal

强化学习与后训练OpenReview

作者位次 #7/11ICLR 2026Poster· Deep Learning / Algorithms

Let's (not) just put things in Context: Test-time Training for Long-context LLMs

Rachit Bansal · Aston Zhang · Rishabh Tiwari · Lovish Madaan · Venkata Sai Surya Subramanyam Duvvuri · Devvrit Khatri · David Brandfonbrener · David Alvarez-Melis · Prajjwal Bhargava · Mihir Kale · Samy Jelassi

长上下文与架构OpenReview

作者位次 #2/8ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Generalized Parallel Scaling with Interdependent Generations

Harry Dong · David Brandfonbrener · Eryk Helenowski · Yun He · Mrinal Kumar · Han Fang · Yuejie Chi · Karthik Abinav Sankararaman

理论与学习动力学OpenReview

常见合作者

DKDevvrit Khatri×2 LMLovish Madaan×2 RTRishabh Tiwari×2 RBRachit Bansal×2 VDVenkata Sai Surya Subramanyam Duvvuri×2 MZManzil Zaheer IDInderjit Dhillon RARishabh Agarwal AZAston Zhang DADavid Alvarez-Melis PBPrajjwal Bhargava MKMihir Kale