Abstract Transformer-based multimodal models often require expensive, full-model training on task-specific all-modality datasets to achieve high accuracy on targeted downstream tasks. To reduce this significant cost, we introduce SAFFE, a methodology for building accurate, task-specific multimodal models with minimal training, using only standard GPU hardware. SAFFE leverages off-the-shelf, pre-trained, frozen unimodal encoders for each input modality (e.g., text, image, or audio) and connects them through a lightweight, trainable component called the FusionAlign Module (FAM). FAM is a bottleneck mid-fusion neural network, trained on the target dataset to align the outputs of the independently pre-trained unimodal encoders. This approach eliminates the need for end-to-end training while maintaining strong accuracy for the downstream task. As a proof of concept, we validate SAFFE on image retrieval and language understanding tasks. SAFFE-derived models outperform state-of-the-art multimodal systems on datasets such as CIFAR-10, ImageNet-100, and COCO, achieving competitive results with significantly fewer trainable parameters and training time.

In the last decade, the popularity of UAVs has increased tremendously. Nowadays, many researchers are interested in UAV swarms. Coordinating a swarm of UAVs is a complicated task and many problems should be addressed before wide-spread adoption. In this work, we focus on the take-off for large-scale UAV swarms, with an extra focus on the assignment phase. The assignment phase is the first take-off stage whereby we decide which UAV on the ground goes to which place in the air. A good assignment algorithm, is quick, and at the same time reduce the total distance travelled as much as possible. We assess the performance of three different assignment algorithms: a heuristic, the original Kuhn-Munkres algorithm (KMA), and the KMA adapted for GPU use. Each algorithm was tested while varying the number of UAVs, as well as the type of flight formation. During the experiments, we measured the calculation time, total distance travelled, and number of flight paths crossing. In terms of total distance travelled, the KMA always outperforms the heuristic. However, the KMA takes longer (orders of magnitude) to calculate the assignment. Realistically, the KMA algorithm can only be used as long as the swarm does not contain more than 500 UAVs. From that point the GPU version of the KMA is faster. We can conclude that, in most cases, it is recommendable to use the KMA for the assignment as it will reduce the distance travelled to a minimum and, consequently, also reduce the number of flight paths crossing.

MOTIVATION: Molecular docking methods are extensively used to predict the interaction between protein-ligand systems in terms of structure and binding affinity, through the optimization of a physics-based scoring function. However, the computational requirements of these simulations grow exponentially with: (i) the global optimization procedure, (ii) the number and degrees of freedom of molecular conformations generated and (iii) the mathematical complexity of the scoring function. RESULTS: In this work, we introduce a novel molecular docking method named METADOCK 2, which incorporates several novel features, such as (i) a ligand-dependent blind docking approach that exhaustively scans the whole protein surface to detect novel allosteric sites, (ii) an optimization method to enable the use of a wide branch of metaheuristics and (iii) a heterogeneous implementation based on multicore CPUs and multiple graphics processing units. Two representative scoring functions implemented in METADOCK 2 are extensively evaluated in terms of computational performance and accuracy using several benchmarks (such as the well-known DUD) against AutoDock 4.2 and AutoDock Vina. Results place METADOCK 2 as an efficient and accurate docking methodology able to deal with complex systems where computational demands are staggering and which outperforms both AutoDock Vina and AutoDock 4. AVAILABILITY AND IMPLEMENTATION: https://[email protected]/Baldoimbernon/metadock_2.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Summary Virtual Screening (VS) methods simulate molecular interactions in silico to look for the best chemical compound that interacts with a given molecular target. VS is becoming increasingly popular to accelerate the drug discovery process and constitute hard optimization problems with a huge computational cost. To deal with these two challenges, we have created METADOCK, an application that (1) enables a wide range of metaheuristics through a parametrized schema and (2) promotes the use of a multi‐GPU environment within a heterogeneous cluster. Metaheuristics provide approximate solutions in a reasonable time frame, but, given the stochastic nature of real‐life procedures, the energy budget goes hand in hand with acceleration to validate the proposed solution. This paper evaluates energy trade‐offs and correlations with performance for a set of metaheuristics derived from METADOCK. We establish a solid inference from minimal power to maximal performance in GPUs, and from there, to optimal energy consumption. This way, ideal heuristics can be chosen according not only to best accuracy and performance but also to energy requirements. Our study starts with a preselection of parameterized metaheuristic functions, building blocks where we will find optimal patterns from power criteria while preserving parallelism through a GPU execution. We then establish a methodology to figure out the best instances of the parameterized kernels based on energy patterns obtained, which are analyzed from different viewpoints, ie, performance, average power, and total energy consumed. We also compare the best workload distributions for optimal performance and power efficiency among Pascal and Maxwell GPUs on popular Titan models. Our experimental results demonstrate that the most power efficient GPU can be overloaded in order to reduce the total amount of energy required by as much as 20%, finding unique scenarios where Maxwell does it better in execution time, but with Pascal always ahead in performance per watt, reaching peaks of up to 40%.