MuLabPKU ORG

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

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)

No description.

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

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

The official repository of "LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?" (NeurIPS DB Track 2025)

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

No description.

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

No description.

official code for "Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs" (NeurIPS 2025)

No description.

No description.

The official repository of The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling.

The official repository of "LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning".

[EMNLP 2025] HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

No description.