This work systematically analyzes all 1,702 CHI 2026 full papers and identifies 125 that annotate videos, and derives a five-dimensional taxonomy spanning analytic purpose, viewpoint, phenomenon, reasoning requirement, and annotation authority to map the capabilities and limitations of a general-purpose VLM.
Xi-Yuan Shen, Jiuyang Lyu, Seokhyun Hwang et al.· 0 citations
Generative image models can produce highly realistic images, raising concerns about potential misuse in creating deceptive content. Current deepfake approaches face several challenges, including limited generalizability, lack of interpretability, and poor actionability. To help address these, we present ASAP, an intera...
Jinbin Huang, Yuki Ueno, Chen Chen et al.· Information Visualization· 0 citations
This work proposes DreamAvoid, a critical-phase test-time dreaming framework that enables VLA models to anticipate and avoid failures, and introduces an autonomous boundary learning paradigm to refine the system's understanding of the subtle boundary between success and failure.
Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model.
On 200 COCO photographs, Qwen3-VL-4B pi...
Alfredo F. Frontera Del Valle· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure suc...
Maijunxian Wang, Ruisi Wang, Juyi Lin et al.· 0 citations
Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical image analysis. B-cos networks modify the parameterization of convolutional and classification layers to measure class evidence via feature-weight alignment, enabling built-in, class-spec...
Shreyash Arya, Shashank Agnihotri, Marcel Kleinmann et al.· 0 citations
Traditional decision tree models, which rely exclusively on numerical variables, often face challenges in handling high-dimensional data and are limited in their ability to incorporate textual information effectively. To address these limitations, we propose the integrated multivariate segmentation tree (IMST), a compr...
It is shown that using the standard velocity prediction in flow matching in this high-dimensional space requires the model to fit orthogonal noise directions outside the low-dimensional signal manifold, making optimization inefficient, and motivated using the clean data parameterization ($\boldsymbol{x}_{0}$-prediction...
Chao Feng, Zhi-Yang Xu, Bo-Wei Chen et al.· 0 citations
This paper builds upon the large-scale dataset pairing MetOp radiances with ERA5 PBLH labels, and presents the best-performing architecture found: a dual-encoder Transformer whose masked-input handling lets it operate in all weather conditions.
Lorenzo Innocenti, Luca Catalano, Edoardo Arnaudo et al.· 0 citations
K-Means clustering is addressed with K-Means clustering, achieving near-lossless accuracy and a mean speed-up over the full-precision model, and it is revealed that excluding from quantization the layers whose speed-up is negligible, regardless of their sensitivity, can be counterproductive.
D. Población-Criado, D. García-Gasulla, Eduardo Quiñones· 0 citations
Robotic assembly in high-mixture settings requires adaptable systems that can handle diverse parts, yet current approaches typically rely on policies specialized to each insertion task. Although this can reach high success rates, it makes the process of deploying systems for new problems tedious and time consuming. We...
Nicklas Hansen, Iretiayo Akinola, Yi-Jie Guo et al.· 0 citations
Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability methods typically evaluate uncertainty at individual time steps and do not explicitly model how a system progresses toward failure. We introduce Visual Tripwires, a predictiv...
Anoushka Harit, Rehan Zuberi, William Prew 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.
