A question-relevant saliency map identifies and organizes key visual regions, explicitly modeling the spatial distribution of visual importance, and induces a curriculum-like semantic progression from primary to secondary cues, validating structured and sequential visual cognition.
PhyGile performs physics-prefix-guided robot-native motion generation at inference time, directly generating robot-native motions in a 262-dimensional skeletal space with physics-guided prefixes, thereby eliminating inference-time retargeting artifacts and reducing generation-execution discrepancies.
This work proposes a unified UCOD framework that enhances both the reliability of pseudo-labels and the fidelity of features, and introduces the Multi-Cue Native Perception module, which extracts intrinsic visual priors by integrating low-level texture cues with mid-level semantics.
Shuo Jiang, Gaojian Zhang, Mingxue Tan et al.· arXiv.org· 0 citations
An efficient deep learning framework for peatland fire detection based on a Walsh--Hadamard Transform enhanced ResNet-50 (WHT-ResNet-50), which improves feature representation while reducing model complexity and reduces inference cost while preserving detection accuracy is proposed.
Emadeldeen Hamdan, A. F. Tharima, Mohd Zahirasri Mohd Tohir et al.· 0 citations
The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized vision systems.
A computationally efficient hybrid deep-learning framework that combines the strengths of 2D and 3D models is proposed that presents a robust and efficient solution for high-quality 3D CT image post-processing.
J. Thalhammer, T. Dorosti, S. Peterhansl et al.· 2025 IEEE Nuclear Science Sy...· 0 citations
This work introduces novel split-image visual jailbreak attacks (SIVA) that exploit a new vulnerability in VLM safety alignment and introduces a novel adversarial knowledge distillation algorithm to substantially improve cross-model transferability.
Md. Rafi Ur Rashid, Sadik Hossain Shanto, Vishnu Asutosh Dasu et al.· arXiv.org· 1 citation
R3G, a modular Reasoning-Retrieval-Reranking framework, first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images.
Zhuo Chen, Zhengxian Wu, Zi-Rui Liao et al.· IEEE International Conferenc...· 4 citations
This work introduces POCI-Diff (Positioning Objects Consistently and Interactively), a framework that generates annotated synthetic scenes from explicit 3D bounding-box layouts with per-object semantic control and proposes a warping-free editing pipeline supporting object insertion, removal, and transformation via rege...
Andrea Rigo, Luca Stornaiuolo, Weijie Wang et al.· 2 citations
Experiments reveal that existing MLLMs underperform in safety-critical scenarios compared to normal scenes, but fine-tuning with WaymoQA significantly improves their reasoning ability, highlighting the effectiveness of the dataset in developing safer and more reasoning-capable driving agents.
Seung-Jun Yu, Seonho Lee, Namho Kim et al.· arXiv.org· 8 citations
This work introduces MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve VLMs on quantitative medical image analysis, and demonstrates how supervised and reinforcement fine-tuning on MedVision significantly enhances performance across detection, T/L size estimation, and A/D meas...
Yongcheng Yao, Yongshuo Zong, Raman Dutt 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.
