7 papers
Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Le Zhuo, Songhao Han, Yuandong Pu +8
While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and…
PICABench: How Far Are We from Physically Realistic Image Editing?
Yuandong Pu, Le Zhuo, Songhao Han +10
Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond complet…
UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
Xiangyu Wang, Donglin Yang, Yue Liao +5
Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction. While prior works have primarily focused…
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning
Siyuan Huang, Yue Liao, Siyuan Feng +5
The pursuit of data efficiency, where quality outweighs quantity, has emerged as a cornerstone in robotic manipulation, especially given the high costs associated with real-world d…
Mixture Compressor for Mixture-of-Experts LLMs Gains More
Wei Huang, Yue Liao, Jianhui Liu +6
Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert para…
LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
Fangxun Shu, Yue Liao, Le Zhuo +14
We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM…