We propose Map2Thought, a framework that enables explicit and interpretable spatial reasoning for 3D VLMs. The framework is grounded in two key components: Metr...
PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision a...
A multi-tier approach to segmentation, color correction, and domain-specific enhancement The post From RGB to Lab: Addressing Color Artifacts in AI Image Compos...
We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic conten...
We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even ...
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder...
Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features extracted from foundation models generalize better to Out-...
Recent advancements in video models have shown tremendous progress, particularly in long video understanding. However, current benchmarks predominantly feature ...
In this paper, we find that the generation of 3D human motions and 2D human videos is intrinsically coupled. 3D motions provide the structural prior for plausib...
Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effecti...
Adaptive video streaming has facilitated improved video streaming over the past years. A balance among coding performance objectives such as bitrate, video qual...
Talking head generation is increasingly important in virtual reality (VR), especially for social scenarios involving multi-turn conversation. Existing approache...
Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this require...
Artificial intelligence (AI) has the potential to transform medical imaging by automating image analysis and accelerating clinical research. However, research a...
Apple researchers have published a study about Manzano, a multimodal model that combines visual understanding and text-to-image generation, while significantly...
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on ...
Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its origina...
3D pose estimation from sparse multi-views is a critical task for numerous applications, including action recognition, sports analysis, and human-robot interact...
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of ...
As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving perf...
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal ...
Monocular visual SLAM enables 3D reconstruction from internet video and autonomous navigation on resource-constrained platforms, yet suffers from scale drift, i...
Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods r...
Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, includin...
