The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term **cross capabilities**. To systematically explore this concept, we first define seven core individual capabilities and then pair them to form seven common cross capabilities, each supported by a manually constructed taxonomy. Building on these definitions, we introduce *CrossEval*, a benchmark comprising 1,400 human-annotated prompts, with 100 prompts for each individual and cross capability. To ensure reliable evaluation, we involve expert annotators to assess 4,200 model responses, gathering 8,400 human ratings with detailed explanations to serve as reference examples. Our findings reveal that current LLMs consistently exhibit the ``Law of the Weakest Link,'' where cross-capability performance is significantly constrained by the weakest component. Across 58 cross-capability scores from 17 models, 38 scores are lower than all individual capabilities, while 20 fall between strong and weak, but closer to the weaker ability. These results highlight LLMs' underperformance in cross-capability tasks, emphasizing the need to identify and improve their weakest capabilities as a key research priority. The code, benchmarks, and evaluations are available on our [project website](https://www.llm-cross-capabilities.org).

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The increasing popularity of deep learning models has created new opportunities for developing artificial intelligence–based recommender systems. Designing recommender systems using deep neural networks (DNNs) requires careful architecture design, and further optimization demands extensive co-design efforts on jointly optimizing model architecture and hardware. Design automation, such as Automated Machine Learning (AutoML), is necessary to fully exploit the potential of recommender model design, including model choices and model–hardware co-design strategies. We introduce a novel paradigm that utilizes weight sharing to explore abundant solution spaces. Our paradigm creates a large supernet to search for optimal architectures and co-design strategies to address the challenges of data multimodality and heterogeneity in the recommendation domain. From a model perspective, the supernet includes a variety of operators, dense connectivity, and dimension search options. From a co-design perspective, it encompasses versatile Processing-In-Memory (PIM) configurations to produce hardware-efficient models. Our solution space’s scale, heterogeneity, and complexity pose several challenges, which we address by proposing various techniques for training and evaluating the supernet. Our crafted models show promising results on three Click-Through Rate (CTR) prediction benchmarks, outperforming both manually designed and AutoML-crafted models with state-of-the-art performance when focusing solely on architecture search. From a co-design perspective, we achieve 2× floating-point operations efficiency, 1.8× energy efficiency, and 1.5× performance improvements in recommender models.

Abstract Many Internet applications adopt real-time bidding mechanisms to ensure different services (types of content) are shown to the users through fair competitions. The service offering the highest bid price gets the content slot to present a list of items in its candidate pool. Through user interactions with the recommended items, the service obtains the desired engagement activities. We propose a contextual-bandit framework to jointly optimize the price to bid for the slot and the order to rank its candidates for a given service in this type of recommendation systems. Our method can take as input any feature that describes the user and the candidates, including the outputs of other machine learning models. We train reinforcement learning policies using deep neural networks, and compute top-K Gaussian propensity scores to exclude the variance in the gradients caused by randomness unrelated to the reward. This setup further facilitates us to automatically find accurate reward functions that trade off between budget spending and user engagements. In online A/B experiments on two major services of Facebook Home Feed, Groups You Should Join and Friend Requests, our method statistically significantly boosted the number of groups joined by 14.7%, the number of friend requests accepted by 7.0%, and the number of daily active Facebook users by about 1 million, against strong hand-tuned baselines that have been iterated in production over years.

The rise of deep neural networks offers new opportunities in optimizing recommender systems. However, optimizing recommender systems using deep neural networks requires delicate architecture fabrication. We propose NASRec, a paradigm that trains a single supernet and efficiently produces abundant models/sub-architectures by weight sharing. To overcome the data multi-modality and architecture heterogeneity challenges in the recommendation domain, NASRec establishes a large supernet (i.e., search space) to search the full architectures. The supernet incorporates versatile choice of operators and dense connectivity to minimize human efforts for finding priors. The scale and heterogeneity in NASRec impose several challenges, such as training inefficiency, operator-imbalance, and degraded rank correlation. We tackle these challenges by proposing single-operator any-connection sampling, operator-balancing interaction modules, and post-training fine-tuning. Our crafted models, NASRecNet, show promising results on three Click-Through Rates (CTR) prediction benchmarks, indicating that NASRec outperforms both manually designed models and existing NAS methods with state-of-the-art performance. Our work is publicly available here.

This paper proposes a multi-source data fusion algorithm for rail surface defect detection in both camera-based rail inspection images and ultrasound B-scan images. First, we design a rail surface segmentation algorithm based on image bilateral filtering, Sobel edge detection, and rail surface edge detection to extract the rail surface area. Second, we build a camera and ultrasound data fusion (CUFuse) model for rail surface defect detection, including two main networks: multi-source data feature extraction and multi-scale feature fusion networks. The multi-source data feature extraction network consists of two BoTNet 50 networks as feature extraction networks to extract five stages of features in camera-based images and ultrasound B-scan images. The multi-scale feature fusion network consists of five feature fusion modules to fuse the feature information output by the multi-source data feature extraction network. Finally, we use the CUFuse model to detect the rail surface defect dataset, and output five rail surface state types, including Light, Moderate, Severe, Normal, and Joint. The results show that the accuracy of the CUFuse model is 96.97%, which can accomplish the task of rail surface defect detection on railway sites.

Frequency control is an important problem in modern recommender systems. It dictates the delivery frequency of recommendations to maintain product quality and efficiency. For example, the frequency of delivering promotional notifications impacts daily metrics as well as the infrastructure resource consumption (e.g. CPU and memory usage). There remain open questions on what objective we should optimize to represent business values in the long term best, and how we should balance between daily metrics and resource consumption in a dynamically fluctuating environment. We propose a personalized methodology for the frequency control problem, which combines long-term value optimization using reinforcement learning (RL) with a robust volume control technique we termed "Effective Factor". We demonstrate statistically significant improvement in daily metrics and resource efficiency by our method in several notification applications at a scale of billions of users. To our best knowledge, our study represents the first deep RL application on the frequency control problem at such an industrial scale.

Multiplayer Online Battle Arena (MOBA) games have received increasing popularity recently. In a match of such games, players compete in two teams of five, each controlling an in-game avatar, known as heroes, selected from a roster of more than 100. The selection of heroes, also known as pick or draft, takes place before the match starts and alternates between the two teams until each player has selected one hero. Heroes are designed with different strengths and weaknesses to promote team cooperation in a game. Intuitively, heroes in a strong team should complement each other's strengths and suppress those of opponents. Hero drafting is therefore a challenging problem due to the complex hero-to-hero relationships to consider. In this paper, we propose a novel hero recommendation system that suggests heroes to add to an existing team while maximizing the team's prospect for victory. To that end, we model the drafting between two teams as a combinatorial game and use Monte Carlo Tree Search (MCTS) for estimating the values of hero combinations. Our empirical evaluation shows that hero teams drafted by our recommendation algorithm have a significantly higher win rate against teams constructed by other baseline and state-of-the-art strategies.

Matchmaking connects multiple players to participate in online player-versus-player games. Current matchmaking systems depend on a single core strategy: create fair games at all times. These systems pair similarly skilled players on the assumption that a fair game is best player experience. We will demonstrate, however, that this intuitive assumption sometimes fails and that matchmaking based on fairness is not optimal for engagement.