activity
20242026
collaborators

9 papers

cs.LG2026

Low-Rank Adaptation Redux for Large Models

Bingcong Li, Yilang Zhang, Georgios B. Giannakis

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networ…

cs.LG2026

Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation

Yilang Zhang, Abraham Jaeger Mountain, Bingcong Li +1

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks…

cs.LG2026

ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling

Yilang Zhang, Bingcong Li, Niao He +1

Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep layers are often underutilized. This pap…

cs.LG2025

ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning

Yilang Zhang, Xiaodong Yang, Yiwei Cai +1

As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA)…

cs.LG2025

VASSO: Variance Suppression for Sharpness-Aware Minimization

Bingcong Li, Yilang Zhang, Georgios B. Giannakis

Sharpness-aware minimization (SAM) has well-documented merits in enhancing generalization of deep neural network models. Accounting for sharpness in the loss function geometry, whe…

cs.LG2025

Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning

Yilang Zhang, Bingcong Li, Georgios B. Giannakis

Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sa…