Cumulative Sample Loss (CSL) is computed as the mean annotation-conditioned loss of an audit frame across checkpoints trained on a *disjoint* reference set and acts as a dynamic fingerprint and captures the persistent disagreement between its annotation and learned visual-temporal structure.
A deep ensemble of the two co-first-place 2025 models is formed and a lightweight residual refiner trained on the ensemble's own outputs under an $\ell_1$ loss augmented with a structural-similarity term whose weight $\lambda$ the authors vary, which improves an already strong ensemble without any large-scale retrainin...
This work introduces SPAR3S, a sparse voxel-aligned 3D latent generative model for conditional scene completion without requiring ground-truth 3D data for supervision, and trains a masked autoregressive transformer that jointly models voxel occupancy and latent token values, enabling efficient and spatially consistent...
Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel et al.· 1 citation
This survey provides a first systematic overview of the emerging area of vision meets graphs, which treats visual depictions of graphs as first-class inputs for reasoning and learning, and organize existing work into three threads.
Xinjian Zhao, Wei Pang, Zhixuan Yu et al.· Proceedings of the Thirty-Fi...· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper adapts set difference captioning to autonomous driving by focusing on object-centric patches derived from object detection, which simplifies aggregation and enables attribution of differences to specific object instances or categories and introduces a new benchmark, AD-Diff Bench.
Julian Truetsch, Felix Hauser, Christoph Stiller et al.· 0 citations
CoverPruner is proposed, a training-free pruner that asks the complementary demand-side question: after a token is removed, which surviving original token represents it for the target VLM?
Qin Zhu, Wei-Hang You, Han-Qi Jiang et al.· 3 citations
Evidence-Gated Regularization (EGR) is proposed, a modality-agnostic training objective that introduces zero inference-time overhead and derives a per-frame and per-sensor task-relevance signal to gate two state-conditional consistency objectives: invariance on low-evidence sensors, and single-sensor sufficiency on hig...
This work delivers an interpretable, privacy-by-design, edge-ready system that can provide real-time feedback during case submission to filter ungradable photo sets before review, and formalizes epidermal micro-relief as a computable biomarker of image quality.
Robert Engel· IEEE/ACM International Confe...· 0 citations
This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and urges the research community to identify sources of supervision more explicitly. Many recent methods in computer vision build upon representations learned from large-scale unlabeled data, and ar...
This work introduces IDSpace, a new dataset consisting of high-quality synthetic documents across ten European ID types and proposes model-guided Bayesian optimization, which tunes generation parameters to maximize both visual similarity and prediction consistency with target-domain models given only a few samples from...
Lulu Xie, Yan-Cheng Wang, Kanchan Chowdhury et al.· 0 citations
We present, to the best of our knowledge, the first publicly available resource for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography. Because no PLAX-EF datasets previously existed, our work focuses on an innovative data generation strategy to overcome this scarcity....
Zhiyuan Gao, Dominic Yurk, Yaser S. Abu-Mostafa· 0 citations
This work shows that NTK-driven neural fields can be made both non-linear and meta-learnable, narrowing the gap between analytic kernels and practical few-shot reconstruction.
Amir Mallak, Alaa Maalouf, Lior Wolf et al.· IEEE Transactions on Pattern...· 1 citation
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.
