12 papers
Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation
Shuitsu Koyama, Kazuki Matsuda, Yuiga Wada +3
Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited alignment with human judgment…
Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation
Koki Seno, Daichi Yashima, Yusuke Takagi +2
Cross-embodiment data have become central to training robotic foundation models. To leverage such heterogeneous data, we focus on flow-based object manipulation, where robot flows…
ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation
Shuntaro Suzuki, Kento Tokura, Daichi Yashima +3
Text-to-audio (TTA) generation, synthesizing audio from natural language, has been widely studied for its ability to capture precise user intent. To effectively advance TTA models,…
MLLM-as-a-Judge Exhibits Model Preference Bias
Shuitsu Koyama, Yuiga Wada, Daichi Yashima +1
Automatic evaluation using multimodal large language models (MLLMs), commonly referred to as MLLM-as-a-Judge, has been widely used to measure model performance. If such MLLM-as-a-J…
ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning
Daichi Yashima, Shuhei Kurita, Yusuke Oda +3
In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate…
HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching
Daichi Yashima, Koki Seno, Shuhei Kurita +2
Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the globa…