5 papers
S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding
He Wang, Longteng Guo, Pengkang Huo +4
Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap between complex scientific imagery…
Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
Chuang Zhang, Zizhen Zhu, Yihao Wei +5
Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative RE…
MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity
Kaiyuan Zhang, Chenghao Yang, Zhoufutu Wen +19
As reasoning models scale rapidly, the essential role of multimodality in human cognition has come into sharp relief, driving a growing need to probe vision-centric cognitive behav…
RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
Cong Tai, Zhaoyu Zheng, Haixu Long +13
The emerging field of Vision-Language-Action (VLA) for humanoid robots faces several fundamental challenges, including the high cost of data acquisition, the lack of a standardized…
DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation
He Wang, Alexander Hanbo Li, Yiqun Hu +6
Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems. Recent studies primarily focus on enhancing in-cont…