Search papers, labs, and topics across Lattice.
HKUST (Guangzhou)
3
0
7
Multimodal models forget how to see and reason after SFT, but PRISM realigns them before RL, boosting performance by up to 6%.
LLM-based peer review systems can be made significantly more robust against adversarial manipulation via a co-evolutionary GAN approach that anticipates novel attacks.
Scaling up LLMs boosts combinatorial creativity in code generation, but plateaus on exploratory tasks, revealing a "convergence-by-scaling" effect where larger models become less divergent.
