3 papers
cs.AI2026
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
Yan Hong, Wei Li, Kedong Xiu +6
Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in non-updated behavior. Online d…
stat.ML2026
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
Yan Hong, Kedong Xiu, Wei Li +6
We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving gener…
cs.CV2025
Efficient Transfer Learning for Video-language Foundation Models
Haoxing Chen, Zizheng Huang, Yan Hong +5
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream…