🔍 Explore curated resources on Reinforcement Learning with Verifiable Rewards (RLVR) and the reasoning limits of Large Language Models (LLMs).

Companion and standalone app for DCS World with map-based route planning and navigation, marker management, interactive Markdown/PDF checklists, annotations, notes, tab support, and live telemetry display (DataPad). Implemented using Jetpack Compose.

🤖 Implement whole-body model predictive control for legged loco-manipulation, optimizing dynamics and movement in robotic systems.

Multi-sensor deception engine for autonomous systems. Trusted vs veiled sensor data across depth, LiDAR, thermal/IR, RF, and temporal domains. A perception firewall for robots, drones, and IoT.

🍌 Generate high-quality image editing datasets effortlessly with NanoBanana Pro and FAL.ai API for various AI models.

🛠️ Implement efficient deformable grid sampling operations with bilinear interpolation in PyTorch, enhancing deep learning models for dense vision tasks.

📦 Simplify Fortran development with fortran-b0x, a toolkit for efficient coding, debugging, and project management.

🤖 Evaluate real robot policies using Gaussian splatting for soft-body simulations, enhancing the understanding of robot interactions in complex environments.