Publications (8)
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Sen Xu, Yi Zhou, Wei Wang +7
Challenging the prevailing consensus that small models inherently lack robust reasoning, this report introduces VibeThinker-1.5B, a 1.5B-parameter dense model developed via our Spe…
4D-CAAL: 4D Radar-Camera Calibration and Auto-Labeling for Autonomous Driving
Shanliang Yao, Zhuoxiao Li, Runwei Guan +8
4D radar has emerged as a critical sensor for autonomous driving, primarily due to its enhanced capabilities in elevation measurement and higher resolution compared to traditional…
Ins-ATP: Deep Estimation of ATP for Organoid Based on High Throughput Microscopic Images
Xuesheng Bian, Cheng Wang, Shuting Chen +7
Adenosine triphosphate (ATP) is a high-energy phosphate compound and the most direct energy source in organisms. ATP is an essential biomarker for evaluating cell viability in biol…
Monolayer MoS2/GaAs heterostructure self-driven photodetector with extremely high detectivity
Zhijuan Xu, Shisheng Lin, Xiaoqiang Li +5
Two dimensional material/semiconductor heterostructures offer alternative platforms for optoelectronic devices other than conventional Schottky and p-n junction devices. Herein, we…
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Sen Xu, Shixi Liu, Wei Wang +6
This technical report introduces VibeThinker-3B, a compact dense model with 3B parameters developed to investigate how far verifiable reasoning can be pushed within a strictly smal…
DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data
Junjie Wu, Jiangtao Xie, Zhaolin Zhang +4
Recently, Contrastive Language-Image Pre-training (CLIP) has shown promising performance in domain-specific data (e.g., biology), and has attracted increasing research attention. E…
USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways
Shanliang Yao, Runwei Guan, Yi Ni +4
Object tracking in inland waterways plays a crucial role in safe and cost-effective applications, including waterborne transportation, sightseeing tours, environmental monitoring a…
Learning Invariant Inter-pixel Correlations for Superpixel Generation
Sen Xu, Shikui Wei, Tao Ruan +1
Deep superpixel algorithms have made remarkable strides by substituting hand-crafted features with learnable ones. Nevertheless, we observe that existing deep superpixel methods, s…