Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical research on human performance in detecting deepfake face images has not kept pace. It remains unclear if (and how) detection performance varies across ge...
Zhiqing Guo, Lixin Jia, Luning Sun et al.· 0 citations
In-air handwriting recognition based on radio frequency (RF) signals offers a promising solution for human-computer interaction, yet existing methods are often limited by predefined writing planes, constrained writing styles, and small recognition vocabularies. To address these limitations, we propose m^2VLMs, a modali...
Vision-language models (VLMs), like human learners, are frequently exposed to new visual concepts, but how they map novel visual references to language after exposure remains largely underexplored, particularly when those references contradict prior knowledge from pre-training. To study this, we present the Novel Visua...
Ada Defne T\"ur, Gaurav Kamath, Joyce Chai et al.· 0 citations
Referring understanding is a fundamental task that bridges natural language and visual content by localizing objects described in free-form expressions. However, existing works are constrained by limited language expressiveness, lacking the capacity to model object dynamics in spatial numbers and temporal states. To ad...
Yani Zhang, Dongming Wu, Wencheng Han et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing attack costs and amplifying security and privacy risks. Yet fragmented terminology and evaluation practices hinder understanding of what transfers, why it tra...
Guangjing Wang, Ce Zhou, Yuanda Wang et al.· 0 citations
Object hallucination in vision-language models (VLMs) is usually measured by checking each object a caption names against the image. Most benchmarks and detectors alike treat every object mention as a claim that the object is present. This assumption fails when a caption names an object without asserting it, as in "a b...
Medical Vision-Language Models (Med-LVLMs) have shown strong performance in Medical Visual Question Answering (MVQA), yet they may still produce factually inconsistent responses. Retrieval-Augmented Generation (RAG) can mitigate this issue by incorporating external clinical evidence; however, retrieval is often guided...
Daniela Jimenez-Pano, Hugo Jair Escalante, Delia Iraz\'u Hern\'andez-Far\'ias· 0 citations
A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition canno...
Weiyang Jin, Jiwen Yu, Sihan Xu et al.· 0 citations
When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which it has been written or rendered. In this paper, we investigate whether, and how, the style in which a word is visualized in an image impact...
Deep learning-based nuclei analysis in histopathology relies heavily on large-scale, expert-curated datasets that are costly and difficult to scale across organs. To address this, we propose a scalable framework leveraging cell-level spatial transcriptomics (ST) as an alternative supervision source for nuclei classific...
Kazuya Nishimura, Ryoma Bise, Haruka Hirose et al.· 0 citations
We introduce Material Coating, a novel image editing task that simulates applying a thin material layer onto an object while preserving its underlying coarse and fine geometry. Material coating is fundamentally different from existing "material transfer" methods, which are designed to replace an object's intrinsic mate...
Sagie Levy, Elad Aharoni, Matan Levy et al.· 0 citations
Many challenges in scientific imaging involve solving ill-posed inverse problems, where the goal is to recover spatio-temporal fields from indirect, noisy, and highly sparse measurements - often without access to ground truth data or reliable simulators. To address this challenging scenario, we present NeuralDMD, an in...
Ali SaraerToosi, Renbo Tu, Esther Y. H. Lin 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.
