Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Chen Tang*, Yizhou Wang*, Jianyu Wu*, Lintao Wang*, Shixiang Tang, Pengze Li, Encheng Su, Jun Yao, Jiabei Xiao, Yuqi Shi, Jielan Li, Hongxia Hao, Zhangyang Gao, Fang Wu, Ben Fei, Xiangyu Yue, Pan Tan, Bozitao Zhong, Jinouwen Zhang, Aoran Wang, Yan Lu, Jiaheng Liu, Xinzhu Ma, Liang Hong, Mingyue Zheng, Phil Torr, Bowen Zhou, Wanli Ouyang, Lei Bai

A further step of SciReasoner. We propose native structural reasoning, making protein structures, crystal structures, and molecular topology first-class citizens of scientific LLM reasoning: coordinates, topologies, and periodic connectivities are discretized into a unified structure-aware vocabulary so that structural tokens become addressable evidence units. SciReasoner achieves state-of-the-art on 67 of 86 benchmarks (e.g., improving Gene Ontology Cellular Component F_max from 0.42 to 0.55 on low-homology proteins and single-step retrosynthesis accuracy from 0.63 to 0.72), and double-blind expert evaluation rates its reasoning traces preferred or comparable to a frontier LLM in 98% of cases.

project/pdf

LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation

Jiabei Xiao, Yizhou Wang, Chen Tang, Pengze Li, Wanli Ouyang, Shixiang Tang

We reframe scientific Introduction writing as a joint reasoning-and-structuring problem. LECTOR is a Logic-Expression Co-Reinforcement Learning framework that first builds a verifiable logic-reasoning graph from the paper body, then co-optimizes graph structural fidelity and narrative quality, substantially reducing citation hallucination.

pdf/code

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai

pdf/code/data and model

EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds

Lu Chen*, Yizhou Wang*, Shixiang Tang, Qianhong Ma, Tong He, Wanli Ouyang, Xiaowei Zhou, Hujun Bao, Sida Peng

project/pdf/code

Hulk: A universal knowledge translator for human-centric tasks

Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang

project/pdf/code

Dettoolchain: A new prompting paradigm to unleash detection ability of mllm

Yixuan Wu*, Yizhou Wang*, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Philip Torr, Jian Wu

pdf/code

Unihcp: A unified model for human-centric perceptions

Yuanzheng Ci*, Yizhou Wang*, Meilin Chen, Shixiang Tang, Lei Bai, Feng Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli Ouyang

pdf/code

Unsupervised object detection pretraining with joint object priors generation and detector learning

Yizhou Wang*, Meilin Chen*, Shixiang Tang, Feng Zhu, Haiyang Yang, Lei Bai, Rui Zhao, Yunfeng Yan, Donglian Qi, Wanli Ouyang

pdf

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

Yizhou Wang*, Shixiang Tang*, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang

pdf

Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification

Weizhen He, Yiheng Deng, Yunfeng Yan, Feng Zhu, Yizhou Wang, Lei Bai, Qingsong Xie, Rui Zhao, Donglian Qi, Wanli Ouyang, Shixiang Tang

pdf/code

Humanbench: Towards general human-centric perception with projector assisted pretraining

Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang

pdf/code