This paper examines how the sequencing of images and text within multi-modal prompts influences the reasoning performance of large language models (LLMs). We performed empirical evaluations using three commercial LLMs. Our results demonstrate that the order in which modalities are presented can significantly affect performance, particularly in tasks of varying complexity. For simpler tasks involving a single image, modality sequencing had a clear impact on accuracy. However, in more complex tasks involving multiple images and intricate reasoning steps, the effect of sequencing diminished, likely due to the increased cognitive demands of the task. Our findings also highlight the importance of question/prompt structure. In nested and multi-step reasoning tasks, modality sequencing played a key role in shaping model performance. While LLMs excelled in the initial stages of reasoning, they struggled to re-incorporate earlier information, underscoring the challenges of multi-hop reasoning within transformer architectures. This suggests that aligning the sequence of modalities with the logical flow of reasoning steps is more critical than modality order alone. These insights offer valuable implications for improving multi-modal prompt design, with broader applications across fields such as education, medical imaging, and cross-modal learning.

Basecalling is an essential step in nanopore sequencing analysis where the raw signals of nanopore sequencers are converted into nucleotide sequences, i.e., reads. State-of-the-art basecallers employ complex deep learning models to achieve high basecalling accuracy. This makes basecalling computationally-inefficient and memory-hungry; bottlenecking the entire genome analysis pipeline. However, for many applications, the majority of reads do no match the reference genome of interest (i.e., target reference) and thus are discarded in later steps in the genomics pipeline, wasting the basecalling computation. To overcome this issue, we propose TargetCall, the first pre-basecalling filter to eliminate the wasted computation in basecalling. TargetCall's key idea is to discard reads that will not match the target reference (i.e., off-target reads) prior to basecalling. TargetCall consists of two main components: (1) LightCall, a lightweight neural network basecaller that produces noisy reads; and (2) Similarity Check, which labels each of these noisy reads as on-target or off-target by matching them to the target reference. TargetCall aims to filter out all off-target reads before basecalling. The highly-accurate but slow basecalling is performed only on the raw signals whose noisy reads are labeled as on-target. Our thorough experimental evaluations using both real and simulated data show that TargetCall 1) improves the end-to-end basecalling performance while maintaining high sensitivity in keeping on-target reads, 2) maintains high accuracy in downstream analysis, 3) precisely filters out up to 94.71% of off-target reads, and 4) achieves better performance, throughput, sensitivity, precision, and generality compared to prior works. We open-source TargetCall at https://github.com/CMU-SAFARI/TargetCall

Recent studies reveal that social advertising is more effective than conventional online advertising. This is mainly because conventional advertising targets at individual's interest while social advertising is able to produce a large cascade of further exposures to other users via social influence. This motivates us to study the optimal social advertising problem from platform's perspective, and our objective is to find the best ad sequence for each user in order to maximize the expected revenue. Although there is rich body of work that has been devoted to ad sequencing, the network value of each customer is largely ignored in existing algorithm design. To fill this gap, we propose to integrate viral marketing into existing ad sequencing model, and develop both non-adaptive and adaptive ad sequencing policies that can maximize the viral marketing efficiency.

Geneticists can use the latest AI and Big Data analytics technology to study, diagnose, and even treat cancer. Cancer is one of the most active fields in genomics, spurring mountains of research papers and clinical trials. WuXi NextCODE is committed to pushing this field forward, and so we had a special "Genomes for Breakfast" session devoted to this topic at the recent ASHG17 event. The Cancer Genome Atlas (TCGA) is one of the most useful public genomic cancer databases available. It has led to critical discoveries, including entirely new drug targets and better insights into tumor origination, development, and spread.