This work has used auto insurance data set and explored classification models and used Topological Node Feature(TNF) based spectral embedding for low dimensional data representation along with some popular embedding methods like MDS, Isomaps and t-SNE to overcome the problem of data imbalance.
Rohan Gupta, Lalith Srikanth Chintalapati, Satya Sai Mudigonda et al.· 0 citations
When the human reference scores zero on a metric, the released GTRS-Dense label generator for NAVSIM marks every candidate trajectory in the scene as passing it. NAVSIM's authors introduced this human-reference forgiveness to avoid penalizing contextually justified maneuvers when scoring one trajectory, and warned that...
Jiaxuan Guo, Jingxin Yang, Jiaqi Ye et al.· 0 citations
PASEO (Perturb-And-Solve for Efficient Operator conditioning), a method that uses a small (1M parameters) learned network to degrade diffusion model predictions in latent space, achieves strong perceptual quality while running up to 9x faster and using up to 34% less peak memory than the tested baselines.
Abduragim Shtanchaev, A. Asadulaev, Luiza Labazanova et al.· 0 citations
Domain incremental learning is essential for adapting ophthalmic deep learning models to sequential clinical domains while preserving diagnostic expertise. Existing domain incremental learning methods predominantly address the domain shift induced by style variations. However, they often overlook the severe class imbal...
Nan-Xi Yu, Kang Li, Ye Du et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multimodal tabular-image learning is gaining growing attention, yet it faces challenges due to tabular data unavailable at test time. A practical solution involves transferring tabular knowledge to images during training to enhance the performance of image models at inference. However, the overlooked yet important chal...
Longfei Huang, Shangdong Yang, Yang Yang· 0 citations
Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental monitoring. However, conventional federated learning (FL) is ill-suited to onboard satellite learning, as it assumes computational, memory, and communication resources beyo...
M. Shaaban, Mohamed Elmahallawy, Marius Bernahrndt et al.· 0 citations
Federated learning enables collaborative model training across institutions without centralizing data, yet high annotation costs, domain shifts, and class imbalance remain major obstacles, especially when irrelevant out-of-distribution (OOD) samples dilute the labeled data. Existing active learning methods target uncer...
David Due\~nas Gaviria, Shadi Albarqouni· 0 citations
Vision-language models are increasingly used for driving-scene understanding, yet the semantic relations expressed in their outputs are often difficult to verify against the underlying traffic situation. This paper introduces a deterministic multi-dataset predicate framework that derives driving-scene semantics from me...
Mohamed Chouai, Fazli Faruk Okumus, Stefan Kugele· 0 citations
This work proposes Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding, which outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.
Haojie Huang, Xin-Lei Yu, Cheng-Ming Xu et al.· 3 citations
We present DynActiveGS, a dynamic-aware active reconstruction framework based on 3D Gaussian Splatting (3DGS) for autonomous exploration in dynamic environments. The framework incrementally reconstructs a 3D Gaussian scene representation while suppressing motion-corrupted observations through online uncertainty predict...
Hongbo Duan, Pengting Luo, Chengzhi Zhao et al.· 0 citations
Flow-Map GRPO enables effective RL alignment of pretrained deterministic flow-map generators while retaining their original parameterization, without retraining them as native stochastic models.
Zhi-Qi Li, Wen Zhang, Bo Zhu· arXiv.org· 3 citations· ⚡2
The results position JuZhou 1.0 as a practical approach to mobile text-to-image generation and provide a concrete reference for Chinese-native generation, domestic-compute training, and fully offline on-device deployment after one-time installation.
Ce Chen, Cong-Rui Wang, Yong-Lin Li et al.· 0 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
