https://plancherb1.github.io/authors/yitaojiang/ Recent content on Brian Plancher Hugo -- gohugo.io en-us © {year} Brian Plancher Fri, 19 Jun 2026 00:00:03 +0000 https://plancherb1.github.io/authors/yitaojiang/ Fri, 19 Jun 2026 00:00:03 +0000 https://plancherb1.github.io/authors/yitaojiang/ https://plancherb1.github.io/publication/asciiart/ Fri, 19 Jun 2026 00:00:03 +0000 https://plancherb1.github.io/publication/asciiart/ We demonstrate that a text-only large language model (LLM) can be adapted into a VLA-style controller when visual observations are rendered into a text input using an ASCII representation. This ASCII-as-vision interface enables existing training and deployment stacks for LLMs to efficiently condition on visual state, follow natural-language instructions, and produce constrained, executable actions.