Search papers, labs, and topics across Lattice.
East China Normal University
2
0
6
InsightVQA reveals that current models struggle with high-dimensional emotion-cognitive reasoning, exposing critical gaps in visual understanding capabilities.
LLM-based ASR can be shrunk to 2.3B parameters and still beat larger models in real-world scenarios by carefully delineating encoder and LLM roles and using a multi-stage training approach.
