Posts on Bhavesh Kalisetti

A benchmark for coding agents based on difficult Pokemon battles, where agents build teams, learn from losses, and adapt their strategy.

A faster, approximate approach to KV-cache compaction that avoids the expensive full attention matmul.

Recently I was helping train a VLM from scratch and I noticed something odd: during training, the output norms of the projectorThe projector is the component of a VLM that transforms the patch embeddings outputted by the vision encoder to token embeddings…