Publications

Improving Automatic VQA Evaluation Using Large Language Models
Oscar Mañas
Benno Krojer
8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accur… (see more)acy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.
Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)
Promoting Fair Vaccination Strategies through Influence Maximization: A Case Study on COVID-19 Spread
Nicola Neophytou
Afaf Taïk
The aftermath of the Covid-19 pandemic saw more severe outcomes for racial minority groups and economically-deprived communities. Such dispa… (see more)rities can be explained by several factors, including unequal access to healthcare, as well as the inability of low income groups to reduce their mobility due to work or social obligations. Moreover, senior citizens were found to be more susceptible to severe symptoms, largely due to age-related health reasons. Adapting vaccine distribution strategies to consider a range of demographics is therefore essential to address these disparities. In this study, we propose a novel approach that utilizes influence maximization (IM) on mobility networks to develop vaccination strategies which incorporate demographic fairness. By considering factors such as race, social status, age, and associated risk factors, we aim to optimize vaccine distribution to achieve various fairness definitions for one or more protected attributes at a time. Through extensive experiments conducted on Covid-19 spread in three major metropolitan areas across the United States, we demonstrate the effectiveness of our proposed approach in reducing disease transmission and promoting fairness in vaccination distribution.
T-NET: Weakly Supervised Graph Learning for Combatting Human Trafficking
Pratheeksha Nair
Javin Liu
Catalina Vajiac
Andreas Olligschlaeger
Duen Horng Chau
Mirela T. Cazzolato
Cara Jones
Christos Faloutsos
Human trafficking (HT) for forced sexual exploitation, often described as modern-day slavery, is a pervasive problem that affects millions o… (see more)f people worldwide. Perpetrators of this crime post advertisements (ads) on behalf of their victims on adult service websites (ASW). These websites typically contain hundreds of thousands of ads including those posted by independent escorts, massage parlor agencies and spammers (fake ads). Detecting suspicious activity in these ads is difficult and developing data-driven methods is challenging due to the hard-to-label, complex and sensitive nature of the data. In this paper, we propose T-Net, which unlike previous solutions, formulates this problem as weakly supervised classification. Since it takes several months to years to investigate a case and obtain a single definitive label, we design domain-specific signals or indicators that provide weak labels. T-Net also looks into connections between ads and models the problem as a graph learning task instead of classifying ads independently. We show that T-Net outperforms all baselines on a real-world dataset of ads by 7% average weighted F1 score. Given that this data contains personally identifiable information, we also present a realistic data generator and provide the first publicly available dataset in this domain which may be leveraged by the wider research community.
Abstract 6324: Antagonism-enforced braking system to enhance CAR T cell therapeutic specificity
Taisuke Kondo
François X. P. Bourassa
Sooraj R. Achar
Justyn DuSold
Pablo Cespedes
Madison Wahlsten
Audun Kvalvaag
Guillaume Gaud
Paul E. Love
Michael Dustin
Grégoire Altan-Bonnet
Naomi Taylor
Chimeric Antigen Receptor (CAR) T cell immunotherapy represents a breakthrough in the treatment of hematological malignancies. However, the … (see more)rarity of cell surface protein targets that are specific to cancerous but not vital healthy tissue has hindered its broad application to solid tumor treatment. While new logic-gated CAR designs have shown reduced toxicity against healthy tissues, the generalizability of such approaches across tumors remains unclear. Here, we harness a universal characteristic of endogenous T cell receptors (TCRs), their ability to discriminate between self and non-self ligands through inhibition of response against self (weak) antigens, to develop a broadly applicable method of enhancing immunotherapeutic precision. We hypothesized that this discriminatory mechanism, known as antagonism, would apply across receptors, allowing for a transfer of specificity from TCRs onto CARs. We therefore systematically mapped out the responses of CAR T cells to joint TCR and CAR stimulations. We first engineered murine T cells with an ovalbumin-specific TCR to express a CAR targeting murine CD19 and discovered that the expression of a strong TCR antigen on CD19+ leukemia enhanced CAR T killing. Importantly though, the presence of a weak TCR antigen antagonized CAR T responses, assessed by in vitro multiplexed dynamic profiling as well as in vivo cytotoxicity. We developed a mathematical model based on cross-receptor inhibitory coupling that accurately predicted the extent of TCR/CAR antagonism across a wide range of immunological settings. This model was validated in a CD19+ B16 mouse melanoma model showing that TCR/CAR antagonism decreased the infiltration of a tumor-reactive T cell cluster, while TCR/CAR agonism enhanced infiltration of this T cell cluster. We then applied our quantitative knowledge of TCR/CAR crosstalk to design an Antagonism-Enforced Braking System (AEBS) for CAR T cell therapy. This was assessed in a model system using a CAR targeting the tyrosine-protein kinase erbB-2 (HER2) together with a hedgehog acyltransferase (HHAT) peptide-specific TCR that binds strongly to mutated tumor neoantigen while retaining weak affinity for the wild-type self-antigen on healthy tissue. We established a humanized in vivo model of CAR T function and found that AEBS CAR T cells maintained high anti-tumor activity against a human lung adenocarcinoma (PC9) but notably, their anti-tissue cytotoxicity against human bronchial epithelial cells (BEAS-2B) was minimized. AEBS CAR T cells therefore sharpen the discriminatory power of synthetic anti-tumor lymphocytes. Our work highlights a novel mechanism by which TCRs can enforce CAR T cell specificity, with practical implications for the rational design of future anti-leukemia immunotherapies. Citation Format: Taisuke Kondo, François X. Bourassa, Sooraj Achar, Justyn DuSold, Pablo Cespedes, Madison Wahlsten, Audun Kvalvaag, Guillaume Gaud, Paul Love, Michael Dustin, Gregoire Altan-Bonnet, Paul François, Naomi Taylor. Antagonism-enforced braking system to enhance CAR T cell therapeutic specificity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6324.
Essential surgery delivery in the Northern Kivu Province of the Democratic Republic of the Congo
Luc Kalisya Malemo
Ava Yap
Boniface Mitume
Christian Salmon
Kambale Karafuli
Rosebella Onyango
Vulnerability of terrestrial vertebrate food webs to anthropogenic threats in Europe
Louise M. J. O'Connor
Francesca Cosentino
Michael B. J. Harfoot
Luigi Maiorano
Chiara Mancino
Wilfried Thuiller
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
Jonathan Lebensold
Maziar Sanjabi
Pietro Astolfi
Kamalika Chaudhuri
Mike Rabbat
Chuan Guo
Language Models Can Reduce Asymmetry in Information Markets
Nasim Rahaman
Martin Weiss
Manuel Wüthrich
Erran L. Li
Bernhard Schölkopf
Multi-Resolution Continuous Normalizing Flows
Vikram Voleti
Chris Finlay
Assistive sensory-motor perturbations influence learned neural representations
Pavithra Rajeswaran
Alexandre Payeur
Amy L. Orsborn
Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using B… (see more)rain-Computer Interfaces (BCIs), which map neural activity into movement via a decoder. We analyzed motor cortex activity as monkeys practiced BCI with a decoder that adapted to improve or maintain performance over days. Population dimensionality remained constant or increased with learning, counter to trends with non-adaptive BCIs. Yet, over time, task information was contained in a smaller subset of neurons or population modes. Moreover, task information was ultimately stored in neural modes that occupied a small fraction of the population variance. An artificial neural network model suggests the adaptive decoders contribute to forming these compact neural representations. Our findings show that assistive decoders manipulate error information used for long-term learning computations, like credit assignment, which informs our understanding of motor learning and has implications for designing real-world BCIs.
From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
Khaoula Chehbouni
Megha Roshan
Emmanuel Ma
Futian Andrew Wei
Afaf Taïk
Jackie Ck Cheung