الباحثون

Bin Chong

المنشورات 2

نسخة أولية وصول مفتوح

CARAT: Do Materials LLMs Reason or Recite?

Jiajun Wu, Jian Yang, Zixiang Ni وآخرون · 2026

When a materials LLM answers a question about crystal structure, does it reason from the structure or copy an answer already printed in its input? Accuracy cannot tell: a structural description often prints the very field it is scored against. CARAT holds question and gold answer fixed across eight matched views, names …

نسخة أولية وصول مفتوح

AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents

Yufan Liu, Shang Luo, Yang Liu وآخرون · 2026

Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continuation on a probe-belief-action graph under an expected-loss objective covering sensing, physical recovery, and uncorrected failures. A joint posterior guides a one-step …

المؤلفون المشاركون