ChenLab @ The Hong Kong Polytechnic University

university

https://chenlab.comp.polyu.edu.hk/

AI & ML interests

None defined yet.

yeliudev

updated 3 collections 4 months ago

PosterLLaVA

PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM • 3 items • Updated Apr 3

DiffArtist

DiffArtist: Towards Aesthetic-Aligned Diffusion Model Control for Training-free Text-Driven Stylization • 2 items • Updated Apr 3

VideoMind

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning • 6 items • Updated Apr 3

yeliudev

authored 2 papers 4 months ago

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

Paper • 2503.13444 • Published Mar 17 • 17

Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion

Paper • 2412.14462 • Published Dec 19, 2024 • 15

yeliudev

updated a model 6 months ago

PolyU-ChenLab/ETChat-Phi3-Mini-Stage-2-3

5B • Updated Jan 20 • 2

yeliudev

updated a collection 6 months ago

E.T. Bench

[NeurIPS 2024] Towards Open-Ended Event-Level Video-Language Understanding • 8 items • Updated Apr 3

yeliudev

published a model 6 months ago

PolyU-ChenLab/ETChat-Phi3-Mini-Stage-2-3

5B • Updated Jan 20 • 2

yeliudev

authored 4 papers 9 months ago

ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection

Paper • 2008.06254 • Published Aug 14, 2020

Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images

Paper • 2111.11057 • Published Nov 22, 2021

UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection

Paper • 2203.12745 • Published Mar 23, 2022

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

Paper • 2409.18111 • Published Sep 26, 2024 • 7