3 papers
cs.LG2026
ReTaCo: Residual-Target Control for On-Policy Distillation
Zixiang Ni, Zhuo Hu, Renjie Cao +8
On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher's full-vocabulary distributio…
cs.LG2026
CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
Shuheng Cao, Zhenhao Zhang, Ruiqi Chen +7
Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route…
cs.CL2026
Is LLM's Moral Decision Compositional?
Weijia Zhang, Ruiqi Chen, Yunze Xiao +1
Moral evaluations of language models typically infer a model's values from its choices between single acts, yet in everyday life a person is judged on their history of good and bad…