↓Skip to main content

🏢 ShanghaiTech University

Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
·1624 words·8 mins· loading · loading
Machine Learning Deep Learning 🏢 ShanghaiTech University
Deep Equilibrium Models excel on imbalanced data due to feature convergence and self-duality properties, unlike explicit models, as shown through Neural Collapse analysis.
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
·1556 words·8 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 ShanghaiTech University
A novel primal-dual method boosts offline safe reinforcement learning efficiency for convex CMDPs by using uncertainty parameters and achieving a sample complexity of O(1/(1-γ)√n).
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
·2593 words·13 mins· loading · loading
AI Generated Computer Vision 3D Vision 🏢 ShanghaiTech University
OctreeOcc uses octree queries for efficient and multi-granularity 3D occupancy prediction, surpassing state-of-the-art methods with reduced computational costs.
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
·3159 words·15 mins· loading · loading
AI Generated Computer Vision Image Segmentation 🏢 ShanghaiTech University
This research presents a novel method for robust semantic segmentation, achieving state-of-the-art results by generating coherent images with both semantic and covariate shifts and recalibrating uncer…
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
·1331 words·7 mins· loading · loading
Multimodal Learning Vision-Language Models 🏢 ShanghaiTech University
PromptFolio optimizes federated learning of vision-language models by combining global and local prompts, improving generalization and personalization, as proven theoretically and empirically.
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
·1971 words·10 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 ShanghaiTech University
QVPO, a novel online RL algorithm, leverages diffusion models’ multimodality to boost performance in continuous control tasks, overcoming limitations of unimodal policies.
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
·2131 words·11 mins· loading · loading
Computer Vision Image Generation 🏢 ShanghaiTech University
CryoGEM: Physics-informed generative model creates realistic synthetic cryo-EM datasets, boosting particle picking and pose estimation accuracy for higher-resolution protein structure determination.