https://udgamlabs.com/blog Releases, research and notes from Udgam Labs. en Mon, 12 Oct 2026 00:00:00 GMT https://udgamlabs.com/blog/chitra-tiny https://udgamlabs.com/blog/chitra-tiny A small diffusion transformer that makes 256×256 pictures from a sentence, trained on about 4.7 million public-domain and CC0 images. Open weights, measured results and known failures. Release Mon, 12 Oct 2026 00:00:00 GMT https://udgamlabs.com/blog/udgam-384m https://udgamlabs.com/blog/udgam-384m A 384M-parameter English model trained from scratch to turn requests into function calls, JSON and shell commands on the device. Best at knowing when to act; behind on exact calls. Release Sat, 10 Oct 2026 00:00:00 GMT https://udgamlabs.com/blog/english-125m https://udgamlabs.com/blog/english-125m We trained a 125.8M-parameter English model from random weights for about US$17 of cloud compute. It missed its performance target, and we released it anyway with every number. Release Tue, 29 Sep 2026 00:00:00 GMT https://udgamlabs.com/blog/hinglish-commands https://udgamlabs.com/blog/hinglish-commands A LoRA adapter for Qwen3-0.6B that turns English and Romanized Hinglish commands into structured intents. It lifts exact match on Hinglish-TOP from 9.90% to 54.88%. Release Tue, 22 Sep 2026 00:00:00 GMT