Sort by
Refine Your Search
-
Country
-
Field
-
a highly motivated Research Fellow/Engineer to join a strategic collaboration with Procter & Gamble (P&G). This project aims to develop next-generation AI technologies for concept-driven video
-
project aims to develop next-generation AI technologies for concept-driven video understanding from consumer-recorded facial care videos. Unlike conventional action recognition, the research focuses
-
multiple LLM-powered agents operate concurrently to explore user-generated worlds and trigger diverse contextual scenarios. Develop a unified multimodal detection pipeline that integrates video, audio, and
-
to customers, develop and iterate designs through sketches, prototypes, renderings and communicate with stakeholders. Work on projects that spread across product development, print, packaging, video storytelling
-
with the Principal Investigator (PI) and industry partner to ensure all project deliverables are met Design and implement evaluation frameworks and metrics for vision-language models Develop annotated video datasets
-
, as part of a wider project, to conduct research on: Signal processing combined with AI-based modification on speech signals. The need is for a real-time system, so efficient coding is important. Key
-
on projects that spread across product development, print, packaging, video storytelling, brand identity, and interactive projects for screens, devices, and space. Build physical and digital models and
-
contextual scenarios. Develop a unified multimodal detection pipeline that integrates video, audio, and text leveraging fine-tuned Vision-Language Models (VLMs) from WP3, supporting zero-shot reasoning and
-
, as part of a wider project, to conduct research on: LLM/VLM, media comparison, AI-assisted explainability. The need is for a real-time system, so efficient coding is important. Key Responsibilities
-
deliverables are met Design and implement evaluation frameworks and metrics for vision-language models Develop annotated video datasets and capability-tagged evaluation tasks Build end-to-end evaluation