projects

1. 01memoryresearch

   Bengal: Document Unlearning (SHRED)

   SHRED — a document-level LLM unlearning method developed under the U.S. government IARPA Bengal program. It combines self-distillation on the retain set with entropy demotion on the forget set to remove targeted knowledge (e.g., private IP documents) from pretrained LLMs without catastrophic damage to unrelated capabilities.

   githublink view →
2. 02safetyactive

   Physics-Based AI Image Detection

   Detecting AI-generated images through physics-based reasoning — analyzing depth maps, brightness-depth consistency, and light estimation to expose how AI fails to model real-world physics. A 3-feature classifier achieves 68.3% accuracy with just depth gradients and brightness edge analysis.

   githubview →
3. 03memoryactive

   DREAM-C2L: Continual Learning Framework

   Open-source framework for continual learning research. Enabling AI systems to learn continuously without catastrophic forgetting, adapting to new data while preserving prior knowledge.

   githubview →
4. 04safetycompleted

   Project Canary

   Foundational MOVE Fellowship project (Sept-Oct 2025) — a community-driven effort to train and refine frontier AI models. Completed 15,000+ tasks across 15 domains, improving Review 1 approval rates from 10% to 40%.

   view →
5. 05safetycompleted

   Project Orion

   Advanced MOVE Fellowship phase (Nov 2025) — specialized refinement of frontier AI models. Focused on high-quality reasoning chains, safety injections, and red-teaming through jailbreak testing. One-month intensive following Project Canary.

   view →