23 citations · 42 across the 18 of their papers we have counts for
22 papers
Aligning Policy Encoders with a Shape Teacher
Madelon Bernardy, Mohammad Mahdi Derakhshani, David M Knigge +2
3D-aware representations can improve robotic manipulation by providing geometric information that is robust to changes in viewpoint, object position, and occlusion. However, using…
Semantically Steerable Image Tokenization
Danilo de Goede, Mohammad Mahdi Derakhshani, Yuki M. Asano +1
Adaptive image tokenizers compress an image into a variable number of tokens matched to its complexity, and recent work makes this allocation controllable: conditioned on a target…
PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence
Dheeraj Varghese, Anna Vettoruzzo, Walter Simoncini +5
Recent advances in multimodal foundation models yield strong performance on static perception and reasoning benchmarks, yet such evaluations largely overlook a central aspect of in…
LiFT: Loop Flow Transformers
Mohammad Mahdi Derakhshani, Pedro M. P. Curvo, Gertjan J. Burghouts +2
We introduce Loop Flow Transformers (LiFT), a family of looped generative models that scales computation by repeatedly applying a shared Diffusion Transformer (DiT) core, with only…
FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection
Francesco Tonini, Lorenzo Vaquero, Mohammad Mahdi Derakhshani +3
Human-Object Interaction (HOI) detection aims to localize humans and objects in images and classify their interactions. Zero-shot HOI focuses on recognizing interactions that are n…
GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
Polytimi Anna Gkotsi, Andrii Zadaianchuk, Mohammad Mahdi Derakhshani
Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to…
Private PoEtry: Private In-Context Learning via Product of Experts
Rob Romijnders, Mohammad Mahdi Derakhshani, Jonathan Petit +3
In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks with only a small set of examples at inference time, thereby avoiding task-specific fine-tuning…
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
Răzvan-Andrei Matişan, Vincent Tao Hu, Grigory Bartosh +6
We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous tra…
NeoBabel: A Multilingual Open Tower for Visual Generation
Mohammad Mahdi Derakhshani, Dheeraj Varghese, Marzieh Fadaee +1
Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing system…
Continual Hyperbolic Learning of Instances and Classes
Melika Ayoughi, Mina Ghadimi Atigh, Mohammad Mahdi Derakhshani +3
Continual learning has traditionally focused on classifying either instances or classes, but real-world applications, such as robotics and self-driving cars, require models to hand…
TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning
Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma +3
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 th…
TULIP: Token-length Upgraded CLIP
Ivona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki M. Asano +3
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, restrict…
Any-Shift Prompting for Generalization over Distributions
Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani +2
Image-language models with prompt learning have shown remarkable advances in numerous downstream vision tasks. Nevertheless, conventional prompt learning methods overfit their trai…
Unlocking Spatial Comprehension in Text-to-Image Diffusion Models
Mohammad Mahdi Derakhshani, Menglin Xia, Harkirat Behl +2
We propose CompFuser, an image generation pipeline that enhances spatial comprehension and attribute assignment in text-to-image generative models. Our pipeline enables the interpr…
Self-Supervised Open-Ended Classification with Small Visual Language Models
Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Cees G. M. Snoek +2
We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks few-shot abilities for open-ended classification with small visual language models. Our approach…
Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
Tom van Sonsbeek, Mohammad Mahdi Derakhshani, Ivona Najdenkoska +2
Medical Visual Question Answering (VQA) is an important challenge, as it would lead to faster and more accurate diagnoses and treatment decisions. Most existing methods approach it…
Bayesian Prompt Learning for Image-Language Model Generalization
Mohammad Mahdi Derakhshani, Enrique Sanchez, Adrian Bulat +4
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…
LifeLonger: A Benchmark for Continual Disease Classification
Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Tom van Sonsbeek +4
Deep learning models have shown a great effectiveness in recognition of findings in medical images. However, they cannot handle the ever-changing clinical environment, bringing new…
Generative Kernel Continual learning
Mohammad Mahdi Derakhshani, Xiantong Zhen, Ling Shao +1
Kernel continual learning by \citet{derakhshani2021kernel} has recently emerged as a strong continual learner due to its non-parametric ability to tackle task interference and cata…
Kernel Continual Learning
Mohammad Mahdi Derakhshani, Xiantong Zhen, Ling Shao +1
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 catastrop…
Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors
Mohammad Mahdi Derakhshani, Saeed Masoudnia, Amir Hossein Shaker +4
We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefull…
BlockCNN: A Deep Network for Artifact Removal and Image Compression
Danial Maleki, Soheila Nadalian, Mohammad Mahdi Derakhshani +1
We present a general technique that performs both artifact removal and image compression. For artifact removal, we input a JPEG image and try to remove its compression artifacts. F…