Rahil Parikh

Locus sets the frontier for automating molecular design Our automated research system Locus develops scientific AI models that outperform SOTA expert solutions Unlocking the potential of scientific AI requires leveraging proprietary data. Locus achieves this autonomously 🧵👇 -- We test Locus across a number of tasks related to molecular scoring and design: training molecular property prediction models for a proprietary task, fine-tuning Boltz-2 to predict small-molecule potency, and building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold2. Each of these settings are real-world AI for science use cases, where tasks are often out-of-distribution for existing foundation models and limited in data, while featuring expensive and noisy evaluators. Compared to state-of-the-art baselines and LLM agents set to optimize these tasks, Locus achieves higher performance. Additionally, Locus generalizes better despite limited data, finds more sample efficient solutions, and explores a higher diversity of solutions.

3. In 'Acoustic To Articulatory Speech Inversion Using Multi-Resolution Spectro-Temporal Representations Of Speech Signals' we demonstrate a correlation between the brain's representation (cortical features) of speech and the vocal tract parameters using speech inversion

2. In 'Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework' (with @AmazonScience), we show that joint-training with AET improves ASC mainly due to the regularization effect of event tagging and not because the model has learnt the 'events'

Stoked to share that all 3 of our papers were accepted at @ISCAInterspeech 1. In 'An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models', we showed that in contrast to spec based models E2E models are very vulnerable to time-freq discontinuities