CLUE (Calibrated Latent Uncertainty Estimation), which combines self-consistent teacher calibration and distribution-based confidence probing to produce calibrated predictions, is introduced, which achieves equivalent or stronger performance than zero-shot baselines up to 32B parameters across all modalities.
Dengjia Zhang, Alexander Martin, William Jurayj et al.· arXiv.org· 4 citations
Video diffusion models can enable embodied agents to anticipate plausible futures from the recent past, but they are typically trained offline on curated datasets--a mismatch with the agents' learning setup at deployment: online, from a single video stream that sequentially outputs one frame at a time. We bridge this t...
Jason Yoo, Yingchen He, Saeid Naderiparizi et al.· 0 citations
MMAP is presented, a novel Multimodal Missing-aware Alignment Pretraining method for learning image-tabular representations from incomplete data that outperforms strong multimodal and unimodal baselines on two challenging longitudinal clinical tasks for Alzheimer's disease.
Fiona Kekwick, Matthew Baugh, Bernhard Kainz et al.· 0 citations
Directional embedding velocity emerges as a property of clinically grounded rather than general biomedical pretraining, showing that foundation model embeddings can encode pre-diagnostic mammographic change without task-specific adaptation.
Kalina P. Slavkova, Eric Brattain, A. Gowd et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Results show that recurrent token mixing can provide an efficient alternative to global softmax attention for high-resolution dense prediction and edge deployment, and are shown to be faster than FLA v0.5.
Zhe Feng, Long-Fei Liu, Wei Liu et al.· 0 citations
Remote-sensing (RS) multimodal large language models (MLLMs) are trained and evaluated only in English, while text-only instruction data covers over 100 languages. We propose MODL (Mutually Orthogonal Domain-Language composition), a recipe that adds new languages to an English RS MLLM without a single multilingual RS e...
Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect a model's true decision process and may therefore mislead clinicians. We investigate this problem using a Vision Transformer-based breast MRI classifier trained on the OD...
Peachapong Poolpol, Henrik H. J. Detjen, Eike Petersen· 0 citations
Many vision applications ask several independent, forced-choice questions about the same image. Visual Jev encodes the image and public context once, executes isolated question suffixes as a batch, and reads candidate probabilities from the backbone's language-model head. Across four benchmarks, answer-supervised post-...
Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects in 2D and reconstruct them independently struggle in such scenes: a missed object is never reconstructed, a merged detection can fuse two objects, and separately reconstru...
Dongwon Son, Junhyek Han, Yoon-Je Cho et al.· 0 citations
Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typically perform 3D instance segmentation on point clouds or rely on offline 2D mask-matching pipelines. However, 3D instance segmentation is limi...
Jiang-Shan Gong, Yuqun Wu, Qiqian Fu et al.· 1 citation
Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representations (INRs) address this by learning smooth, general-purpose embeddings that can be queried at any coordinate. Downstream models combine these embeddings with sparse labe...
Isaac Corley, Arjun Rao, Esther Rolf et al.· 0 citations
Footwear outsole impressions are a common form of forensic pattern evidence, yet quantitative methods for estimating wearer attributes from these images remain relatively underdeveloped. We investigate binary sex estimation from footwear outsole impressions by comparing convolutional neural network (CNN) transfer learn...
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.
