Ahmad Beirami

~Ahmad_Beirami1

10

论文总数

5.0

年均投稿

6.6

平均评分

接收情况8/10

会议分布

ICLR

5

ICML

3

COLM

1

NeurIPS

1

发表论文 (10 篇)

20257 篇

Theoretical guarantees on the best-of-n alignment policy

ICML 2025Poster

Controlled Denoising For Diffusion Models

ICLR 2025withdrawn

Generalization and Robustness of the Tilted Empirical Risk

ICML 2025Poster

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

ICLR 2025Poster

Block Verification Accelerates Speculative Decoding

ICLR 2025Poster

Safety Alignment Should be Made More Than Just a Few Tokens Deep

InfAlign: Inference-aware language model alignment

ICML 2025Poster

20243 篇

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

ICLR 2024Spotlight

Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

COLM 2024Poster

Robust Preference Optimization through Reward Model Distillation

NeurIPS 2024Rejected

合作者 (20)

Chirag Nagpal4 篇

Jacob Eisenstein4 篇

Jonathan Berant4 篇

Alekh Agarwal3 篇

Ananda Theertha Suresh3 篇

Adam Fisch2 篇

Alexander Nicholas D'Amour2 篇

Peter Shaw2 篇