March 4, 2025 | 5 minute read
Algoverse ICLR 2025 Acceptances
We are excited to announce the acceptances of 5 Algoverse Research Papers at ICLR 2025!
The International Conference on Learning Representations (ICLR) is one of the most prestigious conferences in deep learning. Publications at ICLR showcase significant advancements in representation learning and neural network methods, often involving collaborations between top universities and industry research labs such as OpenAI (example). For more information, visit the ICLR official website or view its ranking via Google Scholar.
1. MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered
Accepted to Building Trust in LLMs @ ICLR 2025 in Singapore
Accepted to NAACL SRW 2025 in Albuquerque, New Mexico, USA
Authors: Imran Mirza, Cole Huang, Ishwara Vasista, Rohan Patil
2. EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models
Accepted to Building Trust in LLMs @ ICLR 2025 in Singapore
Accepted to NAACL SRW 2025 in Albuquerque, New Mexico, USA
Authors: Abhay Gupta, Jacob Cheung, Philip Meng, Shayan Sayyed
3. Finding Sparse Autoencoder Representations Of Errors In CoT Prompting
Accepted to Building Trust in LLMs @ ICLR 2025 in Singapore
Authors: Justin Theodorus, V Swaytha, Shivani Gautam, Adam Ward, Mahir Shah
4. Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
Accepted to SynthData @ ICLR 2025 in Singapore
Authors: Muna Said, Aarib Haider, Rabia Usman, Sonia Okon
5. Efficient Transformers via MPO-Based Low-Rank Factorization and Pruning
Accepted to Sparsity in LLMs @ ICLR 2025 in Singapore
Authors: Sam Mikhak and Venkata Sai Gummidi
We are incredibly proud of our students' achievements and look forward to seeing their continued impact on the field.