Da-Wei Zhou

Rare concepts in LLM fine-tuning are significantly hindered by "prior barriers" that require targeted supervision, not just more data.

CLIP's cross-modal gap makes text-derived classifier weights actively harm class-incremental learning—discarding the text branch entirely in favor of closed-form visual SVMs delivers superior continual recognition.

Multimodal continual learning does not require rigid parameter isolation or massive replay buffers—external reasoning retrieval can dynamically compose modular capability paths while subspace recycling safely prevents cross-task interference.

Automating peer review to survive the flood of AI-generated papers creates an exploitable adversarial loop, incentivizing authors to game predictable evaluators and ultimately corrupting the downstream corpus used to train future frontier models.

Rhetorical framing can dramatically shift AI reviewers' scores, with evidence and novelty standing out as key influencers.