NON-PROFIT RESEARCH LAB
Researching the ordinary. Discovering the extraordinary.
ExtraOrdinaryLab advances fundamental research across language, speech, and world models.
The Achilles’ Heel of Angular Margins: A Chebyshev Polynomial Fix for Speaker Verification.
Read paper ↗
Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal.
Read paper ↗
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth.
Read paper ↗
Raising the Bar for Adversarial Defence Benchmarks.
Read paper ↗
Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos.
Read paper ↗
01 / 05