↓Skip to main content

🏢 Beihang University

Why Go Full? Elevating Federated Learning Through Partial Network Updates
·3064 words·15 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Beihang University
FedPart boosts federated learning by updating only parts of the network, solving the layer mismatch problem, and achieving faster convergence with higher accuracy.
Uncovering the Redundancy in Graph Self-supervised Learning Models
·2804 words·14 mins· loading · loading
AI Generated Machine Learning Self-Supervised Learning 🏢 Beihang University
Graph self-supervised learning models surprisingly exhibit high redundancy, allowing for significant parameter reduction without performance loss. A novel framework, SLIDE, leverages this discovery f…
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
·1744 words·9 mins· loading · loading
Multimodal Learning Vision-Language Models 🏢 Beihang University
QUEST: Quadruple Multimodal Contrastive Learning tackles feature suppression by using quaternion embedding to extract unique information while penalizing excessive shared information influence, achiev…
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
·2335 words·11 mins· loading · loading
Computer Vision Object Detection 🏢 Beihang University
AdaptOD: a novel approach for robust OOD detection in long-tailed recognition, dynamically adapting outlier distributions to true OOD distributions using a dual-normalized energy loss for improved acc…
LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
·1927 words·10 mins· loading · loading
Natural Language Processing Large Language Models 🏢 Beihang University
TEA-GLM leverages LLMs for zero-shot graph learning by aligning GNN representations with LLM token embeddings, achieving state-of-the-art performance on unseen datasets and tasks.
How to Use Diffusion Priors under Sparse Views?
·2930 words·14 mins· loading · loading
Computer Vision 3D Vision 🏢 Beihang University
Inline Prior Guided Score Matching (IPSM) improves sparse-view 3D reconstruction by leveraging visual inline priors from pose relationships to rectify rendered image distribution and effectively guide…
From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
·3972 words·19 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 Beihang University
TTCT translates natural language constraints into effective training signals for safe reinforcement learning, enabling agents to learn safer policies with lower violation rates and zero-shot transfer …
Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation
·2718 words·13 mins· loading · loading
AI Generated Computer Vision Image Segmentation 🏢 Beihang University
DUSA:Unlocking Diffusion Models’ Discriminative Power for Efficient Test-Time Adaptation
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
·3923 words·19 mins· loading · loading
AI Generated Machine Learning Representation Learning 🏢 Beihang University
Hierarchical Distance Structural Encoding (HDSE) empowers graph transformers to better capture hierarchical graph structures, leading to improved performance in graph classification and regression tas…
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
·2489 words·12 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Beihang University
Dual Defense Federated Learning (DDFed) simultaneously boosts privacy and thwarts poisoning attacks in federated learning without altering the existing framework.
CLIP in Mirror: Disentangling text from visual images through reflection
·4284 words·21 mins· loading · loading
AI Generated Multimodal Learning Vision-Language Models 🏢 Beihang University
MirrorCLIP disentangles text from images in CLIP using mirror reflection differences, enhancing robustness against text-visual image confusion.
Block Sparse Bayesian Learning: A Diversified Scheme
·3512 words·17 mins· loading · loading
Machine Learning Deep Learning 🏢 Beihang University
Diversified Block Sparse Bayesian Learning (DivSBL) improves block sparse signal recovery by adapting to unknown block structures, enhancing accuracy and robustness over existing methods.
BiDM: Pushing the Limit of Quantization for Diffusion Models
·2390 words·12 mins· loading · loading
Computer Vision Image Generation 🏢 Beihang University
BiDM achieves full 1-bit quantization in diffusion models, significantly improving storage and speed without sacrificing image quality, setting a new state-of-the-art.
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
·2302 words·11 mins· loading · loading
Computer Vision 3D Vision 🏢 Beihang University
4Diffusion generates high-quality, temporally consistent 4D content from monocular videos using a unified multi-view diffusion model and novel loss functions.