AI & ML interests
Spiking Neural Networks (SNN) for efficient LLM distillation. We build 1B-parameter student models distilled from Llama 3, Qwen 3.6, and CodeLlama using biologically-inspired spike-based activation. Focus: ultra-low latency inference on consumer GPUs (RTX 5070 Ti), neuromorphic computing, and multi-teacher ensemble distillation. Open-source models for code generation and general reasoning.
vertex-snn 's models
None public yet