8 citations · 13 across the 12 of their papers we have counts for
12 papers
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
Yulu Gan, Phillip Isola
Pretraining produces a learned parameter vector that is typically treated as a starting point for further iterative adaptation. In this work, we instead view the outcome of pretrai…
FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos
Yulu Gan, Ligeng Zhu, Dandan Shan +8
Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent mo…
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Xin Qiu, Yulu Gan, Conor F. Hayes +6
Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment. Reinforcement learning (RL) has emerged as the dominant fine-tuning par…
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
Gaole Dai, Chun-Kai Fan, Yiming Tang +7
Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces. Starting…
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
Anthony Chen, Huanrui Yang, Yulu Gan +7
Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce…
Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology
Peixiang Huang, Songtao Zhang, Yulu Gan +6
Deep learning in digital pathology brings intelligence and automation as substantial enhancements to pathological analysis, the gold standard of clinical diagnosis. However, multip…
InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
Yulu Gan, Sungwoo Park, Alexander Schubert +2
Recent advances in generative diffusion models have enabled text-controlled synthesis of realistic and diverse images with impressive quality. Despite these remarkable advances, th…
DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
Mingjie Pan, Yulu Gan, Fangxu Zhou +4
Three-dimensional microscopy is often limited by anisotropic spatial resolution, resulting in lower axial resolution than lateral resolution. Current State-of-The-Art (SoTA) isotro…
Chain of Thought Prompt Tuning in Vision Language Models
Jiaxin Ge, Hongyin Luo, Siyuan Qian +3
Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most re…
Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
Senqiao Yang, Jiarui Wu, Jiaming Liu +6
The visual prompts have provided an efficient manner in addressing visual cross-domain problems. In previous works, Visual Domain Prompt (VDP) first introduces domain prompts to ta…
Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world
Yulu Gan, Mingjie Pan, Rongyu Zhang +4
When facing changing environments in the real world, the lightweight model on client devices suffers from severe performance drops under distribution shifts. The main limitations o…
Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
Yulu Gan, Yan Bai, Yihang Lou +4
Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly foc…