Jul 2023
24 Mon
25 Tue
26 Wed
27 Thu
28 Fri
29 Sat 05:00 PM – 07:00 PM IST
30 Sun
In the last 5 months, Generative AI Community has organised:
Pratyush is a researcher at Microsoft Research and AI4Bharat (IIT M) with a focus on systems and deep learning for language technologies. He is deeply interested in realising AI as a force of social good.
Talk Theme: Brief story of AI4Bharat - the mission and what we have achieved. Will then move on to LLMs, provide some technical insight into intrinsic dimensionality in deep learning, and his take on how innovation will develop in building custom LLMs
Sachin Dharashivkar will speak about LLM Finetuning and RLHF
Sachin is a founder who is exploring use cases of AI agents. He enjoys training Reinforcement Learning agents and exploring novel applications of Large Language Models.
Talk Theme: Introduction to Supervised and Reinforcement Finetuning.
Three steps of training chatGPT style models. How to perform supervised finetuning. Why is Reinforcement Learning from Human Feedback important and How to train Reward and Policy models.
Location: Bengaluru. Exact location is shared in the invite on approval.
Hosted by
Supported by
Venue host
Akshat Gupta
@akshatg
Submitted Jul 20, 2023
Abstract
In recent times, Live Streaming platforms are gaining popularity where live content is being shown to users. Typically, the videos created by the creators range from 15 minutes to an hour. After intensive research, it was found that a sizable chunk of users drops within first 30 seconds of the video. Another piece of research shows that, on average, a user only has an attention span of 30 seconds. And this number is even lower in Gen Z, which is our main target audience. To solve this problem, we would want to identify the juiciest segments from videos as well as add external features that would prompt a user to land on the base video, overall increasing user engagement and jazziness of the video. Also, we want to make a customizable framework that would cater not only to snippets but also trailers, mashups, etc.
Literature Review
To solve this problem, we did extensive research on the tools that already exist on the market to solve it. When searched globally, there is no single tool or solution that aims to solve this. There are several solutions that try to tackle this in bits and pieces, but not fully. We then read some research papers on how we can do this end-to-end, and from here we got a couple of ideas to try.
Approach
We broke our solution into two parts: how to get the base snippet (the juiciest part within the videos) and what are the different post-processing techniques that we can apply to it. To summarise our solution,
Base snippet:
Post processing:
Impact and Future Work
We deployed our solution at scale (500 video snippets per day) in India. We saw a staggering increase of close to 80% in overall time spent and user engagements. As next steps, we are planning to scale this solution to Indonesia and then to the US. We are also aiming to create a new feed just for these videos. We will also be focusing on further improvements, both in base snippets and post-processing.
Hosted by
Supported by
Venue host
{{ gettext('Login to leave a comment') }}
{{ gettext('Post a comment…') }}{{ errorMsg }}
{{ gettext('No comments posted yet') }}