Understand this story
The English summary is being updated. See the reporting timeline below.
Latest development · Report
CUHK-Shenzhen and Microsoft Research Propose ConvexLLM, a Unified Multimodal Modeling ArchitectureDevelopments
1 confirmed developments
- Source:Sina Tech
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 19
Sina Tech
CUHK-Shenzhen and Microsoft Research Propose ConvexLLM, a Unified Multimodal Modeling Architecture
The Chinese University of Hong Kong, Shenzhen and Microsoft Research jointly proposed ConvexLLM, which uses C-Gate to map audio representations into the convex hull of a large language model’s text token embeddings, thereby drawing on the model’s existing knowledge and reasoning capabilities. ConvexLLM scored 75.36 across 11 VoiceBench tasks and achieved 90.33% and 80.40% on OpenBookQA and BBH, respectively. In a same-backbone comparison using Qwen3.5-2B, C-Gate achieved an overall speech score of 60.35, outperforming MLP at 58.80 and Q-Former at 54.19.
AI Trends