activity
20242026
collaborators

8 papers

cs.AI2026

SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification

Xiangyu Zhao, Henry Hengyuan Zhao, Yiheng Wang +7

While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physi…

cs.AI2026

MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

Xiaoyu Dong, Zhi Li, Xiao-Ming Wu

Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus prim…

cs.AI2026

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…

cs.CL2026

SignDPO: Multi-level Direct Preference Optimisation for Skeleton-based Gloss-free Sign Language Translation

Muxin Pu, Xiao-Ming Wu, Mei Kuan Lim +3

We present SignDPO, a novel multi-level Direct Preference Optimisation (DPO) framework designed to enhance the alignment of skeleton-based Sign Language Translation. While current…

cs.AI2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Wanghan Xu, Yuhao Zhou, Yifan Zhou +104

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…

cs.CL2025

Understanding Layer Significance in LLM Alignment

Guangyuan Shi, Zexin Lu, Xiaoyu Dong +4

Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjus…