Development of a novel colorimetric immunoassay for C-Reactive Protein using colloidal nanoparticles by Tjitra, Niklas Lesmana

“…In this project, colorimetric gold nanoparticle assays based on local surface plasmon coupling phenomena were developed using anti-CRP antibodies and affimer proteins. ELISA experiments were first performed to confirm the binding of antibodies and affimer proteins to CRP. …”
Get full text

Power management system design and optimization for European Student Moon Orbitor (ESMO) by Muhammad Dzahir Mohamed Zain Affandi.

“…ESMO is a European Space Agency (ESA) initiative to involve the universities to build the first student satellite to orbit the Moon. …”
Get full text

Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing by Gimpel, Henner, Laubacher, Robert, Meindl, Oliver, Wöhl, Moritz, Dombetzki, Luca

“…Recent advancements in large language models (LLMs) have demonstrated human-level performance in natural language processing. …”
Get full text

Secret collusion among AI agents: multi-agent deception via steganography by Motwani, SR, Baranchuk, M, Strohmeier, M, Bolina, V, Torr, PHS, Hammond, L, Schroeder de Witt, C

“…We propose a formal threat model for AI agents communicating steganographically and derive rigorous theoretical insights about the capacity and incentives of large language models (LLMs) to perform secret collusion, in addition to the limitations of threat mitigation measures. …”

TIM: a time interval machine for audio-visual action recognition by Chalk, J, Huh, J, Kazakos, E, Zisserman, A, Damen, D

“…On EPICKITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. …”

Can large language model agents simulate human trust behaviors? by Xie, C, Chen, C, Jia, F, Ye, Z, Shu, K, Bibi, A, Hu, Z, Torr, P, Ghanem, B, Li, G

“…Our study provides new insights into the behaviors of LLM agents and the fundamental analogy between LLMs and humans.…”

Systemic interrogation of immune-oncology-related proteins in patients with locally advanced prostate cancer undergoing androgen deprivation and intensity-modulated radiotherapy by Guldvik, IJ, Ramberg, H, Kristensen, G, Røder, A, Mills, IG, Lilleby, W, Taskén, KA

“…PurposeThe primary objective was to establish whether blood-based leucine-rich alpha-2-glycoprotein (LRG1) can predict outcomes in patients with locally advanced prostate cancer undergoing androgen-deprivation therapy (ADT) and radiotherapy (RT) and to determine how it may relate to 92 immune-oncology (I-O)-related proteins in this setting.MethodsBaseline blood level of LRG1 from patients treated with ADT and RT enrolled in the CuPCa (n = 128) and IMRT (n = 81) studies was measured using ELISA. A longitudinal cohort with matched blood samples from start of ADT, start of RT, and end of RT protocol from 47 patients from the IMRT cohort was used to establish levels of I-O proteins by high-multiplexing Proximal Extension Assay by Olink Proteomics. …”

Characterization of immune response and duration of protection in buffaloes immunized with haemorrhagic septicaemia vaccines by Chandrasekaran, S., Kennett, L., Yeap, P.C., Muniandy, N., Rani, B., Mukkur, T.K.S.

“…These results suggested that there was a relationship between ELISA antibody titres and active protection in buffaloes. …”
Get full text

Mechanism of damnacanthal induced apoptosis in CEM-SS cell line by Gopalsamy, Banulata, Saiful Yazan, Latifah, Abdul Hamid, Hisyam

“…Cell viability and morphology was tested with trypan blue assay, flow cytometry analysis detected the apoptotic activity of damnacanthal, caspase colorimetric protease assay tested the Caspase 2, 3, 6, 8, and 9’s involvement and Enzyme-linked Immunosorbent Assay (ELISA) was carried out to quantify the Human p53, Bcl-2, and Bax expression levels. …”
Get full text

LLMR: Real-time Prompting of Interactive Worlds using Large Language Models by De La Torre, Fernanda, Fang, Cathy Mengying, Huang, Han, Banburski-Fahey, Andrzej, Amores Fernandez, Judith, Lanier, Jaron

“…We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult cases where ideal training data is scarce, or where the design goal requires the synthesis of internal dynamics, intuitive analysis, or advanced interactivity. …”
Get full text

Methods for Extracting and Analyzing Political Content on TikTok by Fadel, Marie Diane

“…Additionally, I utilized Large Language Models (LLMs) to evaluate the relevance and persuasive impact of the content, and these machine-generated insights were then benchmarked against human judgments. …”
Get full text

Advancing health coaching: a comparative study of large language model and health coaches by Ong, Qi Chwen, Ang, Chin-Siang, Chee, Davidson Zun Yin, Lawate, Ashwini, Sundram, Frederick, Dalakoti, Mayank, Pasalic, Leonardo, To, Daniel, Erlikh Fox, Tatiana, Bojic, Iva, Car, Josip

“…With zero-shot learning ability, LLMs could revolutionize health coaching by providing better accessibility, scalability, and customization. …”
Get full text
Get full text

Development and application of novel proteomics methods in proteomics research by Hao, Piliang

“…The existing challenges for accurately identifying and quantifying protein deamidation sites in proteomics include tremendous false positive identifications of deamidated peptides from database searches, substantial interference of artificial deamidation from sample preparation, difficulties in differentiating and quantifying the isomeric n-Asp and isoAsp deamidation products in proteome scale, and inability of validating quantification of deamidated peptides by either ELISA or multiple reaction monitoring. In this thesis, novel proteomic methods were developed to overcome these challenges and facilitate the large-scale characterization of protein deamidation. …”
Get full text

Neural abstractive summarization: improvements at the sequence-level by Ravaut, Mathieu

“…Lastly, we turn our focus to summarization with Large Language Models (LLMs). LLMs have enabled great progress in summarization, producing grammatical, fluent and relevant outputs in zero-shot, without dataset-specific fine-tuning. …”
Get full text

Leveraging linguistic knowledge to enhance low-resource NLP applications by Zhu, Zixiao

“…With the rise of large language models (LLMs), traditional fine-tuning has become prohibitive for many users due to computational demands. …”
Get full text

Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation by Zulfikar, Wazeer Deen, Chan, Samantha, Maes, Pattie

Get full text

Large Language Model-based Test Case Generation for GP Agents by Jorgensen, Steven, Nadizar, Giorgia, Pietropolli, Gloria, Manzoni, Luca, Medvet, Eric, O'Reilly, Una-May, Hemberg, Erik

Get full text

Examples out of Thin Air: AI-Generated Dynamic Context to Assist Program Comprehension by Example by Mattis, Toni, Krebs, Eva, Rinard, Martin C., Hirschfeld, Robert

Get full text

The Power of Perception in Human-AI Interaction: Investigating Psychological Factors and Cognitive Biases that Shape User Belief and Behavior by Lee, Eunhae

“…This thesis investigates the psychological factors that influence belief in AI predictions, comparing them to belief in astrology- and personality-based predictions, and examines the "personal validation effect" in the context of AI, particularly with Large Language Models (LLMs). Through two interconnected studies involving 238 participants, the first study explores how cognitive style, paranormal beliefs, AI attitudes, and personality traits impact perceptions of the validity, reliability, usefulness, and personalization of predictions from different sources. …”
Get full text

An enhanced deep reinforcement learning ensemble empowered by large language model by Li, Xinyi

“…The framework termed ”Large Language Model-Enhanced Deep Reinforcement Learning Ensemble” (LLM-DRE), stands at this crossroad, ingeniously combining the robust decision-making capabilities of DRL with the nuanced contextual understanding of LLMs. At its core, LLM-DRE effectively processes and synthesizes disparate forms of market data to fine-tune trading strategies, enabling an enriched assessment of financial environments. …”
Get full text