Ning Liao

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

FineRMOE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

Many Can Beat One: MoE-Linear Attention for Full MLP Image Generation

Towards a Collaborative Memory for Agentic Workflow: Breaking the Prefix Barrier with Segment-Level KV Cache Sharing

Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective