Menglin Jia

10

Papers

21

Total Citations

Papers (10)

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Zero-Shot Vision Encoder Grafting via LLM Surrogates

MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding

Class-Balanced Loss Based on Effective Number of Samples

Intentonomy: A Dataset and Study Towards Human Intent Understanding

Exploring Visual Engagement Signals for Representation Learning

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

Visual Prompt Tuning

Adaptive Caching for Faster Video Generation with Diffusion Transformers

Emergent Correspondence from Image Diffusion