Mohammad Mahdi Derakhshani — accepted AI-conference papers

2026

Purrception: Variational Flow Matching for Vector-Quantized Image Generation

Răzvan-Andrei Matișan, Vincent Tao Hu, Grigory Bartosh, Björn Ommer, Cees G. M. Snoek, Max Welling +3

ICLR 2026poster

We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous transport dynamics. Our method adapts Variational Flow Matching to vector-quantized latents by learning categorical posteri…

Cited by 0 Source ↗Scholar ↗

2025

TULIP: Token-length Upgraded CLIP

Ivona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki M Asano, Nanne Van Noord, Marcel Worring, Cees G. M. Snoek

ICLR 2025poster

We address the challenge of representing long captions in vision-language models, such as CLIP. By design these models are limited by fixed, absolute positional encodings, restricting inputs to a maximum of 77 tokens and hindering performance on tasks requiring longer descriptions. Although recent w…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2025

TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning

Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma, Yuki M. Asano, Martin R. Oswald, Cees G. M. Snoek

ICCV 2025poster

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding abil…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Any-Shift Prompting for Generalization over Distributions

Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani, Shengcai Liao, Cees G. M. Snoek

CVPR 2024poster

Image-language models with prompt learning have shown remarkable advances in numerous downstream vision tasks. Nevertheless conventional prompt learning methods overfit the training distribution and lose the generalization ability on the test distributions. To improve the generalization across vario…

Cited by 17 Source ↗PDF ↗Scholar ↗

2023

Bayesian Prompt Learning for Image-Language Model Generalization

Mohammad Mahdi Derakhshani, Enrique Sanchez, Adrian Bulat, Victor G. Turrisi da Costa, Cees G.M. Snoek, Georgios Tzimiropoulos +1

ICCV 2023poster

Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes an Empirical Risk Minimization objective. Howe…

Cited by 42 PDF ↗code ↗Scholar ↗

2021

Kernel Continual Learning

Mohammad Mahdi Derakhshani, Xiantong Zhen, Ling Shao, Cees Snoek

ICML 2021spotlight

This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific c…

Cited by 47 Source ↗PDF ↗code ↗Scholar ↗

2019

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

Mohammad Mahdi Derakhshani, Saeed Masoudnia, Amir Hossein Shaker, Omid Mersa, Mohammad Amin Sadeghi, Mohammad Rastegari +1

CVPR 2019poster

We present a simple yet effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize…

Cited by 39 PDF ↗Scholar ↗