Mahnoor Malik@noorifications__

The problem we are trying to solve is that of accessibility of the internet by people to disabilities. Accessibility in the sense that people with disabilities eg, people with ADHD, find it hard to navigate through complex and long webpages and end up getting less from what is meant to benefit them the most. Our solutiion is Accessify, A chrome extension that uses generative AI (Gemini Ultra APIs) to be able to simplify the process of navigating through webpages. Gemini Takes in the webpage, summarises and gives a more comprehensible, understandable and storylike version of the website which can make it easy for them to navigate thorugh the site. Accessify also offers additional features such as images summarisation and it is also able to explain an image inthe context pf the words that is found around it. This will help those with poor vision, color blindness, etc to better understand their webpages. Also, a Text-to-Speech model also makes it easy for people who are blind or who just prefer spoken words to listen to the better version of the website. In the future, we hope to make Accessify open source and others can contribute to it. Other features that we will want to include oin the feature is saving preference data to be able to provide better services to our audience, improving the view of the extension, add other feaures like contrast enhancement, and integrate it with an IoT device - Braille writer that can help translate Words to Braille for those with visual impairment to use. We hope to see people with disabilitiies flourish despite their seemingly disadvantaged state, but with accessify, we can change the game. Thank you.

This project explores the advancement of predictive modeling within artificial intelligence, aiming to equip robots with the ability to forecast future events. This capability is designed to mirror the predictive thinking observed in humans, thus enhancing the practical applications and benefits of robotic systems in various sectors. The innovative approach taken involves a unique method of teaching AI systems, like Claude, to interpret and predict future scenarios based on visual inputs, similar to watching television. The methodology focuses on treating visual input as a series of storytelling frames. Claude, for instance, would analyze two given frames, understanding the content and actions within them, and then leverage its natural language generation capabilities to predict and describe what might occur in the subsequent frame. This project not only advances the field of predictive modeling in AI but also opens new pathways for interactive and anticipatory technologies, fostering a closer synergy between human cognitive processes and artificial intelligence.

Graph Detective harnesses the power of state-of-the-art Agent and Phi-2 technology to redefine fraud detection and prevention in the insurance, banking, and eCommerce sectors. By unveiling hidden connections and identifying patterns, it offers an unrivaled solution that combines Generative AI Agents with Phi-2's speed and precision, enabling investigators to tackle fraud with unparalleled efficiency and accuracy. This groundbreaking app not only simplifies data analysis by allowing direct interaction with the Generative AI Agent, bypassing the need for complex coding or manual analysis, but also stands out for its ability to deliver consistent results without the common pitfalls of data hallucination, requiring minimal tuning. With fraud impacting the financial sectors to the tune of $308 billion annually in the United States alone, Graph Detective is poised to revolutionize the industry by offering an unmatched efficiency improvement over traditional methods, ensuring it remains at the forefront of meeting the evolving needs of fraud detection and prevention professionals. What sets our app apart is its unique integration of Phi-2 and Generative AI Agents, providing a solution that not only quickly identifies fraud patterns but is also easy to implement within Agent frameworks (such as CrewAI and LangGraph), making it a game-changer in the fight against sophisticated fraud schemes.

Drive efficiency, automation, and innovation by streamlining workflows and integrating seamless processes. ⏳ You have 48 hours to complete the challenge and compete for prizes. 🚀 Learn and build AI solutions with IBM Granite. 💡 Create impactful solutions that drive smarter business operations. ⭐ Gain expert guidance throughout the hackathon. 🤝 Collaborate or work solo to bring your ideas to life. 💰 $10,000 prize pool for the winners! 🧑🏻‍💻 Sign up before the Kick-Off Stream and start shaping the future with IBM Granite!

🌟 Explore new AI capabilities 🤝 Collaborate and build something extraordinary. 👥 Take part alone or form a team with other participants. 🎓 Receive guidance from expert mentors. 🏆 Compete for $20,000 in Prizes. 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!

⌚ Dive into a 48-hour journey of creativity. 🚀 Compete to craft an app supercharged by Llama 3. 🎓 Expert mentors will guide you every step of the way. 🏆 Win an opportunity to participate in the Lablab NEXT acceleration program, exciting cash prizes, credits, and gear from LlamaIndex, Together AI & Zilliz 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!