11 papers
InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation
Mengao Zhao, Ziang Li, Chaodong Huang +15
Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test o…
EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
Xinjie Wang, Liu Liu, Taojun Ding +9
We present EmbodiedGen V2, a generative 3D world engine for building executable policy-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapi…
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Qijia He, Xunmei Liu, Hammaad Memon +6
Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability. In practice, original vector…
HoloBrain-0 Technical Report
Xuewu Lin, Tianwei Lin, Yun Du +12
In this work, we introduce HoloBrain-0, a comprehensive Vision-Language-Action (VLA) framework that bridges the gap between foundation model research and reliable real-world robot…
MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
Peng Xu, Shengwu Xiong, Jiajun Zhang +125
This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We…
Rethinking Human Preference Evaluation of LLM Rationales
Ziang Li, Manasi Ganti, Zixian Ma +3
Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretabil…
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
Linjie Li, Mahtab Bigverdi, Jiawei Gu +5
Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benc…
DancingBoard: Streamlining the Creation of Motion Comics to Enhance Narratives
Longfei Chen, Shengxin Li, Ziang Li +1
Motion comics, a digital animation format that enhances comic book narratives, have wide applications in storytelling, education, and advertising. However, their creation poses sig…
Prefer2SD: A Human-in-the-Loop Approach to Balancing Similarity and Diversity in In-Game Friend Recommendations
Xiyuan Wang, Ziang Li, Sizhe Chen +3
In-game friend recommendations significantly impact player retention and sustained engagement in online games. Balancing similarity and diversity in recommendations is crucial for…
EXMODD: An EXplanatory Multimodal Open-Domain Dialogue dataset
Hang Yin, Pinren Lu, Ziang Li +2
The need for high-quality data has been a key issue hindering the research of dialogue tasks. Recent studies try to build datasets through manual, web crawling, and large pre-train…
ALens: An Adaptive Domain-Oriented Abstract Writing Training Tool for Novice Researchers
Chen Cheng, Ziang Li, Zhenhui Peng +1
The significance of novice researchers acquiring proficiency in writing abstracts has been extensively documented in the field of higher education, where they often encounter chall…