Optimization of model harnesses has started to gain traction. Interestingly, there are a lot of parallels between problems that have been addressed in the realm of compiler-driven program optimization and optimization of agentic execution. Like what?

From scene understanding to visual reasoning, we have come a long way. As wearables becomes ubiquitous, visual reasoning will play a vital role. Why?

As Physical AI gains momentum, developing World Models has received lot of attention. Are there nuggets one can borrow from deacdes long research on how kids learn?