Search papers, labs, and topics across Lattice.
School of Control Science and Engineering, Shandong University
2
0
4
Executable visual transformations enable MLLMs to achieve continuous self-evolution without the pitfalls of pseudo-labels, leading to superior performance in dynamic VQA tasks.
Forget static datasets: this iterative training loop uses diagnostic feedback to continuously patch the blind spots in large multimodal models, leading to consistent performance gains.
