MuLabPKU

Position Paper: In-Parameter Learning: Why Lifelong AI Systems Need More Than Longer Context

The repo for SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass

[ACL 2026 Findings] Law in Silico: Simulating Legal Society with LLM-Based Agents

Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss

This is the official implementation of "Relational In-Context Learning via Synthetic Pre-training with Structural Prior"

[ACL 2026 Oral] Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation