Yuanxin Liu

5

Papers

57

Total Citations

Papers (5)

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations

A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation