Shijie Ma

msj9817's activity

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

authored a paper 7 days ago

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

Paper • 2508.07307 • Published 29 days ago

authored a paper 11 days ago

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Paper • 2508.20088 • Published 12 days ago • 20

authored 2 papers 3 months ago

A Comprehensive Survey on Continual Learning in Generative Models

Paper • 2506.13045 • Published Jun 16

Aligned Better, Listen Better for Audio-Visual Large Language Models

Paper • 2504.02061 • Published Apr 2

authored a paper 5 months ago

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

Paper • 2504.03755 • Published Apr 2 • 1

authored 10 papers 6 months ago

Towards Trustworthy Dataset Distillation

Paper • 2307.09165 • Published Jul 18, 2023

Open-world Machine Learning: A Review and New Outlooks

Paper • 2403.01759 • Published Mar 4, 2024

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution

Paper • 2405.18240 • Published May 28, 2024

Rethinking Pretraining as a Bridge from ANNs to SNNs

Paper • 2203.01158 • Published Mar 2, 2022

Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

Paper • 2403.03145 • Published Mar 5, 2024

Cross Pseudo-Labeling for Semi-Supervised Audio-Visual Source Localization

Paper • 2403.03095 • Published Mar 5, 2024

WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models

Paper • 2407.10131 • Published Jul 14, 2024

GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers

Paper • 2503.19480 • Published Mar 25 • 16

Active Generalized Category Discovery

Paper • 2403.04272 • Published Mar 7, 2024

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery

Paper • 2410.06535 • Published Oct 9, 2024