Yansong Feng

HIPPO reveals that hint-injected pairwise aggregation can effectively eliminate shortcut reasoning in LLMs, leading to more authentic and transferable reasoning skills.

Training with large block sizes cripples reasoning performance, but a novel curriculum approach unlocks strong reasoning capabilities in diffusion models.

Learned critics in RLHF can actually *increase* variance and hurt performance in sparse-reward settings, but a simple explained variance metric can tell you when to ditch the critic and get better results.

TriMix reveals that prioritizing small, specialized models can dramatically improve low-resource language adaptation, overturning the assumption that bigger models always lead the way.