π§ Building AI, One Token at a Time
Hey there! I'm Suparshwa, an ML Engineer & Researcher, constantly tinkering with transformers, sensor fusion, and deep learning architectures.
π Exploring adaptive attention mechanisms to improve model efficiency
π€ Building ML models that power autonomous systems & AI applications
π Optimizing neural networks for speed, accuracy, and generalization
π Current Experiments:
β‘ Improving transfer learning via parallel encoders & dynamic loss-based activation
π Enhancing multi-modal perception for autonomous navigation
- Santa Clara
-
22:57
(UTC -07:00) - in/suparshwa31
Pinned Loading
-
-
-
-
obfuscated-gradients
obfuscated-gradients PublicForked from anishathalye/obfuscated-gradients
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
Jupyter Notebook
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

