Self-supervised video models are increasingly framed as world models, yet they are still evaluated almost entirely on clean video and reported as a final task score, obscuring how their representations behave under the degraded and ambiguous conditions a deployed world model must handle. We present the first systematic...
Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam et al.· 0 citations
We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrained diffusion model separately for each masked image at deployment. We introduce a middle-ground model, termed Amortized Inpainting with Diffusion (AID), which keeps a pr...
As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding? We identify a pervasive vulnerability, the Cartesian Shortcut: models frequently discretize the orthogonal grid-based layouts...
Xia Hu, Zhenrui Yue, Brian Potetz et al.· 0 citations
Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust evaluation benchmarks and high-quality preference data. To address this, we propose a unified framework spanning benchmark design, data const...
Yuancheng Wei, Linli Yao, Lei Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition, largely because natural image datasets provide limited supervision for low-level visual skills. Can targeted synthetic supervision address these weaknesses without reference images or manua...
Guanyu Zhou, Yida Yin, Wenhao Chai et al.· 0 citations
Goal-conditioned visual navigation has been a long-standing testbed for embodied AI. We study a natural language-conditioned variant, language-conditioned visual navigation (LCVN), in which an embodied agent must follow a natural language instruction given only an initial egocentric observation. Without access to goal...
Yifei Dong, Fengyi Wu, Yilong Dai et al.· 0 citations
Delta-K is proposed, a backbone-agnostic, plug-and-play inference framework that resolves omission by operating directly in the shared cross-attention Key space and significantly improves compositional alignment across both modern DiT and foundational U-Net architectures without requiring spatial masks, auxiliary train...
Image--text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality rather than by semantics. We propose ITO, a framework addressing this limitation through two complementary mechanisms with d...
Hanpeng Liu, Zidan Wang, Shuoxi Zhang et al.· 0 citations
The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engineering and "cherry-picking" - towards fine-grained, controllable generation and high-fidelity post-processing. In professional AI-assisted filmmaking, it is crucial to perform pr...
Xiangbo Gao, Renjie Li, Xinghao Chen et al.· 0 citations
Infrared gas leak detection is important for industrial safety and environmental monitoring, but automatic detection remains challenging because gas plumes are often faint, small, semi-transparent, and weakly bounded. This study proposes an Edge-Aware and Content-Adaptive Feature Fusion Detector (ECAF-Det) for infrared...
Dongsheng Li, Tianli Ma, Siling Wang et al.· 0 citations
Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical interpretation often requires integrating evidence across multiple images, such as different modalities, views, or time points. However, large-scale medical multi-image data and traini...
Zhen Chen, Yihang Fu, Rong Zhou et al.· 0 citations
The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for its delicate multimodal alignment. In this work, we propose FoCLIP, a feature-space misalignment framework for fooling...
Yulin Chen, Zeyuan Wang, Tianyuan Yu et al.· 0 citations
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
