影响力指数

63.78/100

前 3.8%

全站排名 #2,452

发表论文16 篇

平均评分5.1

年均产出5.3 篇/年

Ehsan Abbasnejad

Associate Professor@Monash University·澳大利亚·OpenReview

研究方向

Out-of-distribution Generalisation · Reasoning · Vision and Language Tasks · Generative Models · Bayesian Methods

4.7

Identifying Unperturbed Cellular Programs Enables Accurate Single-Cell Perturbation Prediction

ICLR 2026Rejected

7.5

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection

NeurIPS 2025Poster

通讯

6.8

Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency

NeurIPS 2025Poster

6.3

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

ICLR 2025Poster

二作

6.0

Do Deep Neural Network Solutions Form a Star Domain?

ICLR 2025Poster

三作

6.0

RandLoRA: Full rank parameter-efficient fine-tuning of large models

ICLR 2025Poster

通讯

5.7

Can Model Randomization Offer Robustness Against Query-Based Black-Box Attacks?

ICLR 2025Withdrawn

三作

5.2

The Quest for Winning Tickets in Low-Rank Adapters

合作者 (20)

Cristian Rodriguez-Opazo

Ehsan Abbasnejad

BEYOND IMITATION: RECOVERING DENSE REWARDS FROM DEMONSTRATIONS

Black-box Attack Robustness with Model Diversity and Randomization

DefNTaxS: The Inevitable Need for Context in Classification

Identifying Unperturbed Cellular Programs Enables Accurate Single-Cell Perturbation Prediction

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection

Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Do Deep Neural Network Solutions Form a Star Domain?

RandLoRA: Full rank parameter-efficient fine-tuning of large models

Can Model Randomization Offer Robustness Against Query-Based Black-Box Attacks?

The Quest for Winning Tickets in Low-Rank Adapters