6 papers
Earth Science Foundation Models: From Perception to Reasoning and Discovery
Xiangyu Zhao, Bo Liu, Yuehan Zhang +9
Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded reanalysis data, diverse geophysi…
DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics
Zimo Zhao, Maolin Wang, Bowen Yu +3
Post-training quantization (PTQ) is essential for efficient large language model inference, but reliably quantizing activations remains challenging when weights, activations, and K…
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Haiwen Diao, Penghao Wu, Hanming Deng +55
Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fra…
MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs
Xiangyu Zhao, Wanghan Xu, Bo Liu +7
The rapid advancement of multimodal large language models (MLLMs) offers new opportunities for complex scientific challenges, yet their application in earth science-especially at t…
GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning
Bo Liu, Xiangyu Zhao, Along He +3
Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images. While recent advances in…
Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding
Ke Zou, Yang Bai, Bo Liu +9
Medical phrase grounding is crucial for identifying relevant regions in medical images based on phrase queries, facilitating accurate image analysis and diagnosis. However, current…