D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning
-
Updated
Feb 11, 2026 - Python
D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning
This repo is the official implementation of "Stage-adaptive Token Selection for Efficient Omni-modal LLMs"
[ICLR 2026] Official Codebase for AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
Add a description, image, and links to the omni-llm topic page so that developers can more easily learn about it.
To associate your repository with the omni-llm topic, visit your repo's landing page and select "manage topics."