Computer Vision
Enabling computers and devices to understand what they see.
Projet
MindJourney
MindJourney is a framework that equips AI agents with a “simulation loop” to explore hypothetical 3D viewpoints before answering spatial reasoning questions—tackling a core limitation of vision-language models (VLMs), which recognize objects well in 2D…
Possibilité de carrière
Research Science: Internship opportunities
Microsoft Research Asia (MSRA) is now poised to extend roles into Singapore and looking for research interns in Foundation Model innovations (LLM, vision, multi-modality, etc.), Deep Learning and Reinforcement Learning Foundation, Industrial AI application (e.g.,…
Possibilité de carrière
Applied Scientist – Gaming AI
At Gaming AI, we are exploring emerging technology trends to craft the next era of gaming. We are looking for an Applied Scientist, Gaming AI with high quality machine learning and engineering skills, bringing proven problem-solving…
Télécharger
TRELLIS
TRELLIS is a large 3D asset generation model that creates high-quality 3D assets from simple text or image inputs. Using a unified latent space (SLAT), it delivers detailed, textured 3D models in formats like meshes,…
Possibilité de carrière
Senior Researcher
Conduct research and lead research collaborations that yield new insights, theories, analyses, data, algorithms, and/or prototypes that advance the state-of-the-art of computer science and engineering, as well as general scientific knowledge. This opportunity will allow…
Vidéo
VoluMe: Authentic 3D Video Calls from Live Gaussian Splat Prediction
Virtual 3D meetings offer the potential to enhance copresence, increase engagement and thus improve effectiveness of remote meetings compared to standard 2D video calls. However, representing people in 3D meetings remains a challenge; existing solutions…
Possibilité de carrière
Senior/Principal Researcher
Microsoft Research Asia (MSRA) is now extending its footprint into Hongkong and looking for a Senior Researcher specializing in AI with a strong focus on Multimedia and Vision, Immersive & Embodied AI, Multimodal Foundation Models,…