More Like this

1. The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers

   Qi, Daiqing; Zhao, Handong; Shi, Jing; Jenni, Simon; Fan, Yifei; Dernoncourt, Franck; Cohen, Scott; Li, Sheng (June 2025, The IEEE/CVF Conference on Computer Vision and Pattern Recognition)

   Photographer, curator, and former director of photography at the Museum of Modern Art (MoMA), John Szarkowski remarked in *William Eggleston's Guide*, "While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky." Szarkowski insightfully revealed a notable gap between general and aesthetic visual understanding: while the former emphasizes identifying factual elements in an image (the sky), the latter transcends mere object identification, viewing it instead as an aesthetic component--a pure expanse of blue, valued purely as a color block in visual aesthetics. Such distinctions between general visual understanding (detection, localization, etc.) and aesthetic perception (color, lighting, composition, etc.) pose a significant challenge for existing Multimodal Large Language Models (MLLMs) in comprehending image aesthetics, which is increasingly needed in real-world applications, from image recommendation and enhancement to generation. To fundamentally advance the aesthetic understanding of MLLMs, we introduce a novel dataset, PhotoCritique, derived from extensive discussions among professional photographers and enthusiasts, distinguished by its large scale, expertise, and diversity. Additionally, we propose a new model, PhotoEye, an MLLM featuring a language-guided multi-view vision fusion mechanism for understanding image aesthetics from multiple perspectives. Finally, we introduce PhotoBench, a comprehensive and professional benchmark for aesthetic visual understanding. Our model demonstrates significant advantages over both open-source and commercial models on existing benchmarks and PhotoBench. 

   more » « less
2. Flatter Is Better: Percentile Transformations for Recommender Systems

   https://doi.org/10.1145/3437910  

   Mansoury, Masoud; Burke, Robin; Mobasher, Bamshad (March 2021, ACM Transactions on Intelligent Systems and Technology)

   null (Ed.)

   It is well known that explicit user ratings in recommender systems are biased toward high ratings and that users differ significantly in their usage of the rating scale. Implementers usually compensate for these issues through rating normalization or the inclusion of a user bias term in factorization models. However, these methods adjust only for the central tendency of users’ distributions. In this work, we demonstrate that a lack of flatness in rating distributions is negatively correlated with recommendation performance. We propose a rating transformation model that compensates for skew in the rating distribution as well as its central tendency by converting ratings into percentile values as a pre-processing step before recommendation generation. This transformation flattens the rating distribution, better compensates for differences in rating distributions, and improves recommendation performance. We also show that a smoothed version of this transformation can yield more intuitive results for users with very narrow rating distributions. A comprehensive set of experiments, with state-of-the-art recommendation algorithms in four real-world datasets, show improved ranking performance for these percentile transformations. 

   more » « less
3. Transhumanism and Education: Embodied Learning in an Era of Altered Bodies

   Eisenberg, Michael (June 2019, International Conference in the Learning Sciences)

   In the past decade, both cognitive science and the learning sciences have been significantly altered by an increased attention to the theme of embodiment. Broadly speaking, this theme complements (or pushes back against) the notion of purely abstract, “disembodied” cognition and emphasizes the role of physical interaction with the environment in the course of learning and development. A common, if usually implicit, assumption in this work is that learners’ bodies are more or less constant from one era to another: after all, human senses, limbs, physiology, and the basic parameters of cognition are part of an ongoing evolutionary human endowment. This assumption, while historically reasonable, is likely to need reconsideration in the near future, as a variety of “transhumanist” technologies (enhanced senses, bodies, and internalized interfaces with the outside physical environment) become more prevalent in children’s lives. This paper discusses several foundational issues and questions that are poised to emerge, and to challenge our enduring ideas about children and education, in the foreseeable future. 

   more » « less
4. Review-Based Cross-Domain Collaborative Filtering: A Neural Framework

   Doan, T.N; Sahebi, S. (January 2019, Proceedings of the Third Workshop on Recommendation in Complex Scenarios)

   Cross-domain collaborative filtering recommenders exploit data from other domains (e.g., movie ratings) to predict users’ interests in a different target domain (e.g., suggest music). Most current cross-domain recommenders focus on modeling user ratings but pay limited attention to user reviews. Additionally, due to the complexity of these recommender systems, they cannot provide any information to users to support user decisions. To address these challenges, we propose Deep Hybrid Cross Domain (DHCD) model, a cross-domain neural framework, that can simultaneously predict user ratings, and provide useful information to strengthen the suggestions and support user decision across multiple domains. Specifically, DHCD enhances the predicted ratings by jointly modeling two crucial facets of users’ product assessment: ratings and reviews. To support decisions, it models and provides natural review-like sentences across domains according to user interests and item features. This model is robust in integrating user rating and review information from more than two domains. Our extensive experiments show that DHCD can significantly outperform advanced baselines in rating predictions and review generation tasks. For rating prediction tasks, it outperforms cross-domain and single-domain collaborative filtering as well as hybrid recommender systems. Furthermore, our review generation experiments suggest an improved perplexity score and transfer of review information in DHCD. 

   more » « less
5. Large-scale Collaborative Ranking in Near-Linear Time

   Wu, Liwei; Hsieh, Cho-Jui; Sharpnack, James (January 2017, KDD)

   In this paper, we consider the Collaborative Ranking (CR) problem for recommendation systems. Given a set of pairwise preferences between items for each user, collaborative ranking can be used to rank un-rated items for each user, and this ranking can be naturally used for recommendation. It is observed that collaborative ranking algorithms usually achieve better performance since they directly minimize the ranking loss; however, they are rarely used in practice due to the poor scalability. All the existing CR algorithms have time complexity at least O(|Ω|r) per iteration, where r is the target rank and |Ω| is number of pairs which grows quadratically with number of ratings per user. For example, the Netflix data contains totally 20 billion rating pairs, and at this scale all the current algorithms have to work with significant subsampling, resulting in poor prediction on testing data. In this paper, we propose a new collaborative ranking algorithm called Primal-CR that reduces the time complexity toO(|Ω|+d1d2r), where d1 is number of users and d2 is the averaged number of items rated by a user. Note that d1, d2 is strictly smaller and open much smaller than |Ω|. Furthermore, by exploiting the fact that most data is in the form of numerical ratings instead of pairwise comparisons, we propose Primal-CR++ with O(d1d2(r + log d2)) time complexity. Both algorithms have better theoretical time complexity than existing approaches and also outperform existing approaches in terms of NDCG and pairwise error on real data sets. To the best of our knowledge, this is the first collaborative ranking algorithm capable of working on the full Netflix dataset using all the 20 billion rating pairs, and this leads to a model with much better recommendation compared with previous models trained on subsamples. Finally, compared with classical matrix factorization algorithm which also requires O(d1 d2r) time, our algorithm has almost the same efficiency while making much better recommendations since we consider the ranking loss. 

   more » « less