activity
20242026
collaborators

8 papers

cs.LG2026

Energy-Structured Low-Rank Adaptation for Continual Learning

Longhua Li, Lei Qi, Qi Tian +1

While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compac…

cs.LG2026

Essential Subspace Merging for Multi-Task Learning

Longhua Li, Lei Qi, Xin Geng +1

Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model. Its core ch…

cs.LG2026

Model Merging in the Essential Subspace

Longhua Li, Lei Qi, Qi Tian +1

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. De…

cs.SE2026

iScript: A Domain-Adapted Large Language Model and Benchmark for Physical Design Tcl Script Generation

Ning Xu, Zhaoyang Zhang, Senlin Shu +10

Modern EDA flows rely heavily on Tcl scripting, yet general LLMs perform poorly in this domain due to extreme data scarcity, domain-specific semantics, and the high reliability req…

cs.LG2025

Stratified Knowledge-Density Super-Network for Scalable Vision Transformers

Longhua Li, Lei Qi, Xin Geng

Training and deploying multiple vision transformer (ViT) models for different resource constraints is costly and inefficient. To address this, we propose transforming a pre-trained…

cs.CV2025

One-Shot Knowledge Transfer for Scalable Person Re-Identification

Longhua Li, Lei Qi, Xin Geng

Edge computing in person re-identification (ReID) is crucial for reducing the load on central cloud servers and ensuring user privacy. Conventional compression methods for obtainin…