Positional embeddings encode the spatial position of each image patch in a Vision Transformer (ViT), allowing the model to distinguish different spatial arrangements of visual content. However, we know little about how the choice of embedding shapes a vision transformer's internal representation. In this work, we show...
Mahmoud Mannes, Nikhil Maturi, Parva Mehta et al.· 0 citations
Unsupervised anomaly detection, which learns only from normal images, is a central task in medical image analysis and remains an open problem. Reconstruction-based methods pass an image through an encoder-decoder network trained on normal data and detect anomalies from the residual between the image and its reconstruct...
Shouhei Hanaoka, Takahiro Nakao, Atsushi Takamatsu et al.· 0 citations
Zero-Shot Object Navigation (ZSON) in unknown multi-floor environments presents a significant challenge. Recent methods, mostly based on semantic value greedy waypoint selection, spatial topology-enhanced memory, and Multimodal Large Language Model (MLLM) as a decision-making framework, have led to improvements. Howeve...
Jingzhi Huang, Junkai Huang, Haoyang Yang et al.· 0 citations
This work develops a scalable online entropic OT approximation that enables substantially larger source-target couplings while preserving the benefits of OT, and proves strict reductions in full stochastic-gradient variance and integration error relative to independent pairing.
P. Chen, Sergey Levine· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Teacher-free one-step generative models such as W-Flow learn directly from distributional objectives, with the Sinkhorn divergence providing the strongest empirical performance among the energies studied in W-Flow. However, Sinkhorn divergence is based on balanced optimal transport, whose exact marginal constraints can...
Jongwook Jeon, Mingue Park, Jiwon Choi et al.· 0 citations
Multimodal medical data captures complementary aspects of disease. It provides a comprehensive basis for diagnosis and the identification of biological associations linked to progression or treatment response. Established contrastive learning approaches exploit shared information across modalities, but fall short in ex...
Ivana Jan\'i\v{c}kov\'a, Yen Y. Tan, Thomas H. Helbich et al.· 0 citations
Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction. To improve temporal interpretability, MILLET (Multiple Instance Learning with Temporal Explanation), which combines an...
Partial multi-label learning (PML) aims to train a classifier on datasets whose instances are over-annotated with not only relevant labels but also irrelevant labels, which is common when datasets are collected from crowd-sourcing platform. Existing works primarily approach it from a curriculum learning perspective, le...
Zhuoming Li, Yuheng Jia, Mi Yu et al.· 0 citations
Active learning changes the representations used to acquire subsequent labels. We study this interaction through Collapse-Based Active Neural Learning (C{\AE}NL), which separates acquisition, Dynamic Collapse Regularization (DCR), and its coefficient policy. DCR penalizes a normalized within-class to between-class scat...
Classifier-Free Guidance (CFG) with guidance scale $\gamma$ is commonly motivated by the $\omega$-powered conditional distribution obtained by setting $\omega=\gamma$, but CFG does not, in general, sample from this distribution exactly. We study whether the powered target can instead be learned explicitly. We introduce...
Maciej Falkiewicz, Frantzeska Lavda, Jason Ramapuram et al.· 0 citations
Knowledge distillation transfers representational knowledge from a large teacher network to a compact student. Existing relational and contrastive distillation methods treat all samples uniformly, spending equal gradient on well-matched and poorly-matched regions of the representation space alike. We propose Representa...
Real-world datasets often exhibit severe class imbalance, degrading the performance of deep learning models, particularly on rare classes. While imbalance is well studied in binary and multiclass settings, it is substantially more challenging in multilabel problems due to complex label co-occurrence. In clinical applic...
Priel Hazan, Nir Almog, Noam Keidar 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.
