Ismail Elezi

9 papers at tracked venues · 9 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

CVPR ×3 AAAI ×2 ICCV ×2 ICLR ×1 NeurIPS ×1

Frequent coauthors

Jiankang Deng

×9

Roy Miles

×4

Yin Xie

×2

Kaicheng Yang

×2

Xiang An

×2

Yongle Zhao

×2

Yumeng Wang

×2

Ziyong Feng

×2

Chengcheng Ma

×2

Pradyumna Reddy

×2

Peirou Liang

×1

Xin Wen

×1

Papers

ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
AAAI 2026 ·
Yin Xie
,
Kaicheng Yang
,
Peirou Liang
,
Xiang An
,
Yongle Zhao
,
Yumeng Wang
,
Ziyong Feng
,
Roy Miles
, Ismail Elezi,
Jiankang Deng
"Principal Components" Enable a New Language of Images
ICCV 2025 ·
Xin Wen
,
Bingchen Zhao
, Ismail Elezi,
Jiankang Deng
,
Xiaojuan Qi
Fractal Calibration for Long-tailed Object Detection
CVPR 2025 ·
Konstantinos Panagiotis Alexandridis
, Ismail Elezi,
Jiankang Deng
,
Anh Nguyen
,
Shan Luo
From Attention to Activation: Unraveling the Enigmas of Large Language Models
ICLR 2025 ·
Prannay Kaul
,
Chengcheng Ma
, Ismail Elezi,
Jiankang Deng
Region-based Cluster Discrimination for Visual Representation Learning
ICCV 2025 ·
Yin Xie
,
Kaicheng Yang
,
Xiang An
,
Kun Wu
,
Yongle Zhao
,
Weimo Deng
,
Zimin Ran
,
Yumeng Wang
,
Ziyong Feng
,
Roy Miles
, Ismail Elezi,
Jiankang Deng
$V_{k}D$: Improving Knowledge Distillation Using Orthogonal Projections
CVPR 2024 ·
Roy Miles
, Ismail Elezi,
Jiankang Deng
G3DR: Generative 3D Reconstruction in ImageNet
CVPR 2024 ·
Pradyumna Reddy
, Ismail Elezi,
Jiankang Deng
Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning
AAAI 2024 ·
Chengcheng Ma
, Ismail Elezi,
Jiankang Deng
,
Weiming Dong
,
Changsheng Xu
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
NeurIPS 2024 ·
Roy Miles
,
Pradyumna Reddy
, Ismail Elezi,
Jiankang Deng