Li Shen

mathshenli's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored 20 papers 1 day ago

OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System

Paper • 2303.00501 • Published Mar 1, 2023 • 1

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Paper • 2304.11823 • Published Apr 24, 2023

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Paper • 2310.02575 • Published Oct 4, 2023 • 1

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Paper • 2310.07418 • Published Oct 11, 2023

Debias the Training of Diffusion Models

Paper • 2310.08442 • Published Oct 12, 2023

Merging Experts into One: Improving Computational Efficiency of Mixture of Experts

Paper • 2310.09832 • Published Oct 15, 2023 • 1

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Paper • 2305.18413 • Published May 28, 2023

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

Paper • 2311.16714 • Published Nov 28, 2023 • 1

CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification

Paper • 2306.04979 • Published Jun 8, 2023

Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

Paper • 2312.06173 • Published Dec 11, 2023

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Paper • 2106.10404 • Published Jun 19, 2021 • 1

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models

Paper • 2401.06628 • Published Jan 12, 2024

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

Paper • 2402.00433 • Published Feb 1, 2024

Representation Surgery for Multi-Task Model Merging

Paper • 2402.02705 • Published Feb 5, 2024 • 1

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping

Paper • 2402.07610 • Published Feb 12, 2024 • 8

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Paper • 2202.02643 • Published Feb 5, 2022 • 1

Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?

Paper • 2308.12898 • Published Aug 24, 2023

Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

Paper • 2203.09249 • Published Mar 17, 2022

Revisiting Knowledge Distillation for Autoregressive Language Models

Paper • 2402.11890 • Published Feb 19, 2024

MerA: Merging Pretrained Adapters For Few-Shot Learning

Paper • 2308.15982 • Published Aug 30, 2023