Publications (28)
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
Xingyu Fu, Muyu He, Yujie Lu +2
We present a novel task and benchmark for evaluating the ability of text-to-image(T2I) generation models to produce images that align with commonsense in real life, which we call C…
ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition
Jiuniu Wang, Wenjia Xu, Xingyu Fu +2
Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has be…
There is a Time and Place for Reasoning Beyond the Image
Xingyu Fu, Ben Zhou, Ishaan Preetam Chandratreya +2
Images are often more significant than only the pixels to human eyes, as we can infer, associate, and reason with contextual information from other sources to establish a more comp…
FormCoach: Lift Smarter, Not Harder
Xiaoye Zuo, Nikos Athanasiou, Ginger Delmas +3
Good form is the difference between strength and strain, yet for the fast-growing community of at-home fitness enthusiasts, expert feedback is often out of reach. FormCoach transfo…
Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
Xingyu Fu, Ben Zhou, Sihao Chen +2
Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end model…
Reinforced Attention Learning
Bangzheng Li, Jianmo Ni, Chen Qu +5
Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multi…