AI & ML interests
Multi-Token Prediction (MTP), Non-Autoregressive Architectures, Efficient Sub-Billion LLMs, Edge Inference Optimization, Parallel Decoding.
models 0
None public yet
datasets 0
None public yet
Multi-Token Prediction (MTP), Non-Autoregressive Architectures, Efficient Sub-Billion LLMs, Edge Inference Optimization, Parallel Decoding.