Search papers, labs, and topics across Lattice.
3
0
5
This paper describes the system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline and obtains 90.92% accuracy on the final official evaluation set.
Achieving substantial model compression with negligible accuracy loss could redefine deployment strategies for neural networks on edge devices.
Context-rich image captions are now possible by leveraging structured external knowledge, transforming how we understand image description generation.
