Fatih Porikli

Vice President@QualComm·美国·OpenReview

研究方向

Generative AI · Computer Vision and Perception · Deep Learning · Manifold Learning · Image and Video Processing · Efficient AI · Model Adaptation

5.0

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding

ICLR 2026Poster

5.0

COREDIT: SPATIAL COHERENCE-GUIDED TOKEN PRUNING AND RECONSTRUCTION FOR EFFICIENT DIF- FUSION TRANSFORMERS

ICLR 2026Withdrawn

通讯

6.4

ODG: Occupancy Prediction Using Dual Gaussians

NeurIPS 2025Poster

通讯

6.1

Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models

ICML 2025Poster

通讯

6.0

Generalized Contrastive Learning for Universal Multimodal Retrieval

合作者 (20)

Fatih Porikli

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

DisCo: Reinforcement with Diversity Constraints for Multi-Human Generation

MoViE: Mobile Diffusion for Video Editing

Attention Guided Alignment in Efficient Vision-Language Models

DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks

COREDIT: SPATIAL COHERENCE-GUIDED TOKEN PRUNING AND RECONSTRUCTION FOR EFFICIENT DIF- FUSION TRANSFORMERS

ODG: Occupancy Prediction Using Dual Gaussians

Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models

Generalized Contrastive Learning for Universal Multimodal Retrieval