Exploring memory-centric hardware for language model acceleration.

Architectures aimed at improving speculative token acceptance length.

Persistent GPU kernel research at CMU Catalyst Lab.

Interconnect topology exploration under practical workload constraints.

An end-to-end Verilog accelerator for MNIST inference.

Independent implementation of a MIPS-based processor.

Exploring reasoning paths for mathematics and physics problems.

Multimodal workflows and digital twins for factory safety.