WeChatCV / D-ORCA Star 12 Code Issues Pull requests D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning video-understanding tsinghua-university multimodal-llm video-llm dialogue-centric omni-llm audio-visual-llm Updated Feb 11, 2026 Python
ihp-lab / AVERE Star 5 Code Issues Pull requests [ICLR 2026] Official Codebase for AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization reinforcement-learning emotion-recognition iclr large-language-models multimodal-large-language-models iclr2026 omni-llm Updated Mar 19, 2026 Python