Wei Feng

20

Papers

131

Total Citations

Papers (20)

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

SAVSR: Arbitrary-Scale Video Super-resolution via a Learned Scale-Adaptive Network

Long-Tailed Learning as Multi-Objective Optimization

Dual Semantic Guidance for Open Vocabulary Semantic Segmentation

Hypergraph Clustering Network with Partial Attribute Imputation

GReg: Geometry-Aware Region Refinement for Sign Language Video Generation

COVTrack: Continuous Open-Vocabulary Tracking via Adaptive Multi-Cue Fusion

FedAGC: Federated Continual Learning with Asymmetric Gradient Correction

Deep Multi-modal Graph Clustering via Graph Transformer Network

Scalable Federated One-Step Multi-View Clustering with Tensorized Regularization

Contrastive Multi-view Subspace Clustering via Tensor Transformers Autoencoder

COMMA: Co-articulated Multi-Modal Learning

Partial Multi-View Clustering via Self-Supervised Network

From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration

Generative Hard Example Augmentation for Semantic Point Cloud Segmentation

Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation

VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking

SU-RGS: Relightable 3D Gaussian Splatting from Sparse Views under Unconstrained Illuminations