35
10
Pakistan
1 year of experience
An AI Undergrad passionate about building valuable and scalable AI applications. Connect if we have the same interests.
"EduWise is an advanced AI Voice-Enabled Virtual Assistant designed to redefine the e-learning experience. Utilizing the cutting-edge AI technology, this platform aims to cater to students who crave a more personalized, immersive, and interactive learning environment. EduWise is more than just a chatbot. It not only enables conversational interactions but also provides insightful course recommendations. Its proprietary recommendation system analyses key parameters, such as past student enrollments, course assignments, teacher ratings, and teaching experience, to suggest the most relevant courses, subjects, or teachers based on the student's personal data and interests. The problem EduWise addresses is the lack of personalized guidance in e-learning platforms, often leading to suboptimal course selections and learning experiences. With EduWise, we are bringing the concept of personalized mentorship to e-learning, thus enhancing the engagement and effectiveness of online education. Targeting students and lifelong learners worldwide, EduWise's innovative features help users make informed decisions and streamline their learning paths. EduWise is more than a tool; it's your personal academic advisor, tutor, and guide rolled into one intelligent platform."
1 Aug 2023
PhenoVis is a revolutionary educational platform that transcends traditional learning boundaries, inviting students to embark on a captivating journey of scientific exploration. Through cutting-edge 3D simulations, PhenoVis bridges the gap between theory and reality, offering learners an immersive experience of complex scientific phenomena. Imagine delving into the intricacies of physics, chemistry, and biology within interactive virtual environments. With real-time visualizations and interactive elements, students grasp concepts with unparalleled depth and engagement. PhenoVis empowers curiosity-driven learning, fostering a profound connection to scientific principles and encouraging a lifelong pursuit of knowledge. Join us in reshaping education through the transformative power of PhenoVis.
14 Aug 2023
Our project aims to create an AGI agent for research and validation. The agent conducts deep research, takes notes, and generates a research document summarizing a given claim. It follows a specific workflow, starting with the user providing a claim and supporting information. The agent then uses deep research tools to gather information, search the web, scrape relevant data, and summarize it in notes files. It iterates on different topics and uses a writer tool to generate a final research document. The project includes various components such as internet search and scraping, the Deep Research Toolkit, and SuperAGI tooling. Overall, the project aims to provide an efficient and thorough AGI agent for research, understanding claims, and validating information, while also highlighting potential areas for further investigation or evidence that refutes the claim Ultimately, we want to make research process up to 10x times faster.
21 Aug 2023
In response to the demand for customizable AI assistants, we propose a solution leveraging the Clarifai platform. This involves developing adaptable workflows and models to overcome limitations of rigid approaches. Key technical elements: 1. **Workflow Generation:** A dynamic engine constructs workflows based on intuitive emoji sequences, enabling complex mathematical logic execution. 2. **Metadata Ingestion:** Our solution processes diverse enterprise data, enhancing AI's contextual understanding beyond images. 3. **Prompt Engineering:** Specialized models for domains and tasks using techniques like prompting and fine-tuning. 4. **Orchestration:** An end-to-end framework manages workflow generation, data ingestion, model training, and execution. Implementation: - Clarifai clients, APIs, and gRPC for scalability. - Kubernetes-based microservices for workflow steps. - CI/CD via GitHub Actions, facilitating versioning and testing. - Monitoring with Grafana, Prometheus, and Sentry. - Caching strategies for performance optimization. - Airflow for workflow pipelines. Context: - Users: Data scientists, ML engineers, SWEs. - Industries: Finance, insurance, healthcare. - Use cases: Personalized recommendations, customer service automation. Next Steps: - Develop MVP workflow generator. - Ingest sample metadata for data processing. - Curate prompts and fine-tune models. - Scale tests on larger datasets. - Establish CI/CD pipeline. - Implement monitoring and instrumentation. - Iterate for continued enhancements. Our solution aims to revolutionize AI assistance for enterprises, driven by Clarifai's platform and innovative technical approaches, offering flexibility and efficiency in workflow development and execution.
28 Aug 2023
You have outlined the process quite comprehensively: 1. Utilize the EnCodec model to encode audio files into vector representations, saved as text files. 2. Process these text embeddings using the "emojiintrospector" tool to generate emoji sequences that represent the audio. 3. Validate the emoji outputs across test audio samples to ensure that the harmonic relationships are maintained. Key points: - EnCodec encodes audio to discrete embeddings, output as text. - The "emojiintrospector" tool maps these text embeddings to emojis. - Generated audio samples with 3 harmonics are encoded. - Analyze the emoji outputs to identify common patterns representing harmonic frequencies. - This demonstrates that the pipeline retains the harmonic structure in the emoji mapping. - The resulting emoji sequences can be used for visualization or further analysis.
31 Aug 2023
Problem Statement: Traditional recruitment methods fail to engage a significant segment of the workforce: those not actively seeking new opportunities but willing to consider a change. This oversight results in a vast untapped resource, widening the employee gap in many companies. Solution: EyeCue is the solution to this challenge, utilizing AI-generated videos to capture the attention of both active and passive candidates. Our targeted approach focuses on regions and job clusters, highlighting top job offerings and attracting a diverse pool of talent. How It Works: * Research-Based Strategy: EyeCue begins with an in-depth analysis of a company's unique attributes, based on employee reviews and company culture insights. * Image Selection and Evaluation: AI technology curates and evaluates images to best represent the company, focusing on visual appeal to both active and passive candidates. * Storyboard and Content Creation: An AI-generated storyboard is developed, ensuring the video content is engaging and relevant to the targeted audience. * Voiceover Integration: AI-generated voiceovers are added to enhance engagement and relay the company's message effectively. * Social Media-Optimized Videos: The final product is an engaging video, optimized for social media platforms, designed to capture the attention of potential candidates, including those not actively seeking new opportunities. Benefits: * Engages Passive Candidates: Captures the attention of a vast segment of potential candidates who are not actively job searching. * Bridges the Employee Gap: By inspiring passive candidates, EyeCue addresses the employee gap many companies face. * Cost-Efficient and Time-Saving: Automates the recruitment process, reducing reliance on traditional methods. * Targeted and Effective: Focuses on specific regions and job clusters for more effective recruitment. * Increased Reach and Engagement: Leverages social media to reach a broader audience.
22 Jan 2024