6 papers
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Xiangyan Qu, Zhenlong Yuan, Jing Tang +9
Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) g…
Video-CoE: Reinforcing Video Event Prediction via Chain of Events
Qile Su, Jing Tang, Rui Chen +2
Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained…
Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
Zhenlong Yuan, Xiangyan Qu, Chengxuan Qian +8
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits the…
AutoDrive-R: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
Zhenlong Yuan, Chengxuan Qian, Jing Tang +7
Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capa…
FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos
Rui Chen, Lei Sun, Jing Tang +2
Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The…
Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
Rui Chen, Haizhou Ai, Chong Shang +2
It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical kn…