Authors

Hejian Sang

Publications 2

Preprint Open access

Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts

Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both s …

Preprint Open access

AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning

Han Yu, Wenhui Zhu, Xiwen Chen et al. · 2026

Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely treat cached entries as routing objects, estimating whether an old key will still be read, will recur, or can be replaced. This routing-only view overlooks two effects: lo …

Co-authors