Algoverse LogoAlgoverse

Research at Algoverse

Learn about our mission, explore our acclaimed conference publications, and delve into past student research papers.

Algoverse AI Research is dedicated to empowering students to create authentic and impactful AI research. Our distinctive emphasis on quality and process enables our students to produce exceptional research published at leading NLP conferences worldwide. We strive to push the boundaries of large language models (LLMs) on standard benchmarks while pioneering machine learning applications across diverse disciplines. This commitment to innovation and excellence sets us apart from other programs.

Our PhD mentors have extensive experience conducting cutting-edge research at top AI institutions and research labs around the globe. They are deeply invested in each student's project, providing essential mentorship in scoping research proposals, implementing code, and academic writing. Through this guidance, our students are uniquely equipped to produce high-quality research papers and successfully navigate the publication process at prestigious conferences. Past papers of our students have been cited by researchers at Microsoft, Oxford, and University of Washington.

Conference Publications

Summer 2024 Cohort

Translation Bias and Accuracy in Multilingual LLMs for Cross-Language Claim Verification

Accepted to Attribution @ NeurIPS 2024 in Vancouver, Canada

Authors: Aryan Singhal, Veronica Shao, Gary Sun, Ryan Ding

Acceptance to NeurIPS

QIANets for Reduced Latency and Improved Inference Times in CNN Models

Accepted to Compression @ NeurIPS 2024 in Vancouver, Canada

Authors: Zhumazhan Balapanov, Edward Magongo, Vanessa Matvei, Olivia Holmberg

Acceptance to NeurIPS

Enhancing Language Model Reasoning via Weighted Reasoning in Self-Consistency

Accepted to MathAI @ NeurIPS 2024 in Vancouver, Canada

Authors: Tim Knappe, Ryan Li, Ayush Chauhan, Kaylee Chhua

Acceptance to NeurIPS

Fine-Tuning Language Models for Ethical Ambiguity

Accepted to SoLaR @ NeurIPS 2024 in Vancouver, Canada

Authors: Pranav Senthilkumar, Visshwa Bala, Prisha Jain, Aneesa Maity

Acceptance to NeurIPS

NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with LLMs

Accepted to SoLaR @ NeurIPS 2024 in Vancouver, Canada

Author: William Tan

Acceptance to NeurIPS

Differentiation of Acute Disseminated Encephalomyelitis from Multiple Sclerosis Using a Novel Brain Lesion Segmentation and Classification Pipeline

Accepted to IEEE BHI 2024 in Houston, Texas, USA

Authors: Osama Radi, Aiden Huang, Kira Murukami

Acceptance to IEEE BHI 2024

Medical Imaging Complexity and its Effects on GAN Performance

Accepted to GAISynMeD @ ACCV 2024 in Hanoi, Vietnam

Authors: William Cagas, Chan Ko, Blake Hsiao, Shryuk Grandhi, and Rishi Bhattacharya

Acceptance to ACCV
Spring 2024 Cohort

DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using LLMs

Accepted to AIM-FM @ NeurIPS 2024 in Vancouver, Canada

Accepted to EMNLP Positive Impact Track 2024 in Miami, Florida

Authors: Rajat Rawat, Hudson McBride, Rajarshi Ghosh, Dhiyaan Nirmal, Jong Moon, Dhruv Alamuri

Acceptance to NeurIPS
Acceptance to EMNLP

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark

Accepted to NeurIPS High School Track 2024 in Vancouver, Canada

Accepted to EMNLP Positive Impact Track 2024 in Miami, Florida

Authors: Abhay Gupta, Philip Meng, Ece Yurtseven

Acceptance to NeurIPS
Acceptance to EMNLP
Fall 2023 Cohort

Question-Analysis-Prompting Improves LLM Performance in Reasoning Tasks

Accepted to ACL SRW 2024 in Bangkok, Thailand

Author: Dharunish Yugeswardeenoo

Acceptance to ACL SRW

Applied Machine Learning Research

Explore our applied machine learning research, driving innovation across diverse fields and solving real-world challenges.

Large Language Models Research

Delve into cutting-edge research on large language models, pushing the boundaries of natural language understanding and generation.

Applications for Spring 2025 are now open.

App Deadline: Saturday, Dec. 14th, 11:59pm PT