Search papers, labs, and topics across Lattice.
Harbin Institute of Technology
2
0
5
MLLMs can achieve 10% gains on multimodal reasoning benchmarks by using ground-truth anchored data curation and scaffold-stripping to avoid cognitive drift during self-evolution.
Forget static datasets – RL-based co-training unlocks +20% real-world VLA performance by interactively leveraging simulation while preserving real-world capabilities.