~/talk

EchoLadder: Progressive AI-Assisted Design of Immersive VR Scenes

links:none on file
links:none on file
links:none on file
links:none on file
name:Can Liu
links:none on file
slides:none on file

EchoLadder is a VR authoring pipeline that breaks vague verbal prompts into executable suggestions using a large vision-language model and a JSON action layer so users can apply / undo / regenerate modifications. It matches added objects from a pre-annotated asset library of 2,000+ assets and runs a labeling module that uses LMs to produce object metadata. An ablation with 18 participants and a user study with 12 participants show higher inspiration, relevance, and perceived control versus end-to-end auto-generation.

AI-written summary · about

  1. 0:00Introduction to EchoLadder
  2. 1:28Progressive design with AI
  3. 2:50Key interactions in EchoLadder
  4. 4:13Backend pipeline details
  5. 6:17Evaluation and user study
  6. 8:50Design strategy insights
  7. 9:34Future improvements and Q&A
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.