6 papers
Seed2Scale: A Self-Evolving Data Engine for Embodied AI via Small to Large Model Synergy and Multimodal Evaluation
Cong Tai, Zhaoyu Zheng, Haixu Long +12
Existing data generation methods suffer from exploration limits, embodiment gaps, and low signal-to-noise ratios, leading to performance degradation during self-iteration. To addre…
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…
Dual-Label Learning With Irregularly Present Labels
Mingqian Li, Qiao Han, Ruifeng Li +2
In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears…
UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery
Ruifeng Li, Mingqian Li, Wei Liu +5
Drug discovery is crucial for identifying candidate drugs for various diseases.However, its low success rate often results in a scarcity of annotations, posing a few-shot learning…
GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs
Ruifeng Li, Mingqian Li, Wei Liu +1
Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning approaches are base…
Contextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discovery
Ruifeng Li, Wei Liu, Xiangxin Zhou +4
In the drug discovery process, the low success rate of drug candidate screening often leads to insufficient labeled data, causing the few-shot learning problem in molecular propert…