collaborators

5 papers

cs.CL2026

Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression

Xiang Liu, Zhenheng Tang, Hong Chen +6

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the deg…

cs.LG2026

Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation

Hong Chen, Pengcheng Wu, Yuanguo Lin +4

We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tac…

cs.LG2025

Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation

Junzhuo Li, Bo Wang, Xiuze Zhou +1

Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open…

cs.CL2025

Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis

Junzhuo Li, Bo Wang, Xiuze Zhou +3

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to c…

cs.MM2025

Multi-view Hypergraph-based Contrastive Learning Model for Cold-Start Micro-video Recommendation

Sisuo Lyu, Xiuze Zhou, Xuming Hu

With the widespread use of mobile devices and the rapid growth of micro-video platforms such as TikTok and Kwai, the demand for personalized micro-video recommendation systems has…