Kirolos Ataallah, Eslam Mohamed Bakr, Mahmoud Ahmed, Chenhui Gou, Khushbu Pahwa, Jian Ding, Mohamed Elhoseiny. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propose a novel approach that extends the diffusion framework into modality space, decomposing the complex task of RGB image generation into simpler, interpretable stages. Our method, termed {\papernameAbbrev}, cascades modality-specific models, each responsible for generating an intermediate representation, such as contours, palettes, and detailed textures, ultimately culminating in a high-quality RGB image. Instead of relying on the naive LDM concatenation conditioning mechanism to connect the different stages together, we employ Schr\"odinger Bridge to determine the optimal transport between different modalities. Although employing a cascaded pipeline introduces more stages, which could lead to a more complex architecture, each stage is meticulously formulated for efficiency and accuracy, surpassing Stable-Diffusion (LDM) performance. Modality composition not only enhances overall performance but enables emerging proprieties such as consistent editing, interaction capabilities, high-level interpretability, and faster convergence and sampling rate. Extensive experiments on diverse datasets, including LSUN-Churches, ImageNet, CelebHQ, and LAION-Art, demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods. For instance, {\papernameAbbrev} achieves notable efficiency, matching LDM performance on LSUN-Churches while operating 2$\times$ faster with a 3$\times$ smaller architecture. The project website is available at: \href{https://toddlerdiffusion.github.io/website/}{$https://toddlerdiffusion.github.io/website/$}

3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it does not illustrate how and why the network reaches the final decision. In this paper, we address this question “Can we design an interpretable 3D visual grounding framework that has the potential to mimic the human perception system?”. To this end, we formulate the 3D visual grounding problem as a sequence-to-sequence (Seq2Seq) task by first predicting a chain of anchors and then the final target. Interpretability not only improves the overall performance but also helps us identify failure cases. Following the chain of thoughts approach enables us to decompose the referring task into interpretable intermediate steps, boosting the performance and making our framework extremely data-efficient. Moreover, our proposed framework can be easily integrated into any existing architecture. We validate our approach through comprehensive experiments on the Nr3D, Sr3D, and Scanrefer benchmarks and show consistent performance gains compared to existing methods without requiring manually annotated data. Furthermore, our proposed framework, dubbed CoT3DRef, is significantly data-efficient, whereas on the Sr3D dataset, when trained only on 10% of the data, we match the SOTA performance that trained on the entire data. The code is available at github.com/eslambakr/CoT 3DV G.

In recent years, Text-to-Image (T2I) models have been extensively studied, especially with the emergence of diffusion models that achieve state-of-the-art results on T2I synthesis tasks. However, existing benchmarks heavily rely on subjective human evaluation, limiting their ability to holistically assess the model’s capabilities. Furthermore, there is a significant gap between efforts in developing new T2I architectures and those in evaluation. To address this, we introduce HRS-Bench, a concrete evaluation benchmark for T2I models that is Holistic, Reliable, and Scalable. Unlike existing benchmarks that focus on limited aspects, HRS-Bench measures 13 skills that can be categorized into five major categories: accuracy, robustness, generalization, fairness, and bias. In addition, HRS-Bench covers 50 scenarios, including fashion, animals, transportation, food, and clothes. We evaluate nine recent large-scale T2I models using metrics that cover a wide range of skills. A human evaluation aligned with 95% of our evaluations on average was conducted to probe the effectiveness of HRS-Bench. Our experiments demonstrate that existing models often struggle to generate images with the desired count of objects, visual text, or grounded emotions. We hope that our benchmark help ease future text-to-image generation research. The code and data are available at https://eslambakr.github.io/hrsbench.github.io/.

Proactive content caching has been proposed as a promising solution to cope with the challenges caused by the rapid surge in content access using wireless and mobile devices and to prevent significant revenue loss for content providers. In this paper, we propose an end-to-end Deep Learning framework for proactive content caching that models the dynamic interaction between users and content items, particularly their features. The proposed model performs the caching task by building a probability distribution across different content items, per user, via a Deep Neural Network model and supports, both, centralized and distributed caching schemes. In addition, the paper addresses the key question: Do we need an explicit user-item pairs-based recommendation system in content caching? i.e., do we need to develop a recommendation system while tackling the content caching problem? To this end, an end-to-end Deep Learning framework is introduced. Finally, we validate our approach through extensive experiments on a real-world, public data set, coined MovieLens. Our experiments show consistent performance gains against its counterparts, where our proposed Deep Learning Caching module, dubbed as DLC, significantly outperforms state-of-the-art content caching schemes, serving as a baseline. Our code is available here: https://github.com/heshameraqi/Proactive-Content-Caching-with-Deep-Learning.

3D visual grounding task has been explored with visual and language streams to comprehend referential language for identifying targeted objects in 3D scenes.However, most existing methods devote the visual stream to capture the 3D visual clues using off-the-shelf point clouds encoders. The main question we address is “can we consolidate the 3D visual stream by 2D clues and efficiently utilize them in both training and testing phases?”. The main idea is to assist the 3D encoder by incorporating rich 2D object representations without requiring extra 2D inputs. To this end, we leverage 2D clues, synthetically generated from 3D point clouds, that empirically show their aptitude to boost the quality of the learned visual representations. We validate our approach through comprehensive experiments on Nr3D, Sr3D, and ScanRefer datasets. Our experiments show consistent performance gains against counterparts, where our proposed module, dubbed as LAR, significantly outperforms state-of-the-art 3D visual grounding techniques on three benchmarks.Our code will be made publicly available.