|
Workshop
|
|
Accelerating Memory-Efficient LLM Training and Fine-Tuning via Tracking the Gradient Subspace
Sahar Rajabi · Sirisha Rambhatla
|
|
|
Poster
|
Thu 16:30
|
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Vijay Chandra Lingam · Atula Neerkaje · Aditya Vavre · Aneesh Shetty · Gautham Krishna Gudur · Joydeep Ghosh · Eunsol Choi · Alex Dimakis · Aleksandar Bojchevski · Sujay Sanghavi
|
|
|
Workshop
|
|
Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models
Felix Stahlberg · Jared Lichtarge · Shankar Kumar
|
|
|
Workshop
|
|
RGP: Achieving Memory-Efficient Model Fine-tuning Via Randomized Gradient Projection
Ali Saheb Pasand · Pouya Bashivan
|
|
|
Workshop
|
|
On the Transferability of Parameter-Efficient Continual Learning for Vision Transformers
Leon Ackermann · Van-Linh Nguyen
|
|
|
Workshop
|
|
Memory-Efficient Large Language Model (LLM) Training and Fine-Tuning via Gradient Subspace Tracking
Sahar Rajabi · Sirisha Rambhatla
|
|
|
Workshop
|
|
FB-HyDON: Parameter-Efficient Physics-Informed Operator Learning of Complex PDEs via Hypernetwork and Finite Basis Domain Decomposition
Milad Ramezankhani · Rishi Parekh · Anirudh Deodhar · Dagnachew Birru
|
|
|
Poster
|
Wed 16:30
|
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
Liang Wang · Qiang Liu · Shaozhen Liu · Xin Sun · Shu Wu · Liang Wang
|
|
|
Workshop
|
|
FB-HyDON: Parameter-Efficient Physics-Informed Operator Learning of Complex PDEs via Hypernetwork and Finite Basis Domain Decomposition
Milad Ramezankhani · Rishi Parekh · Anirudh Deodhar · Dagnachew Birru
|
|
|
Poster
|
Thu 16:30
|
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Linglan Zhao · Xuerui Zhang · Ke Yan · Shouhong Ding · Weiran Huang
|
|
|
Poster
|
Wed 11:00
|
Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
Deep Pandey · Spandan Pyakurel · Qi Yu
|
|
|
Workshop
|
|
Slaying the HyDRA: Parameter-Efficient Hyper Networks with Low-Displacement Rank Adaptation
Xiangyu Chen · Ye Wang · Matthew Brand · Perry Wang · Jing Liu · Toshiaki Koike-Akino
|
|
