Ella Minzhi Li
@ellaminzhili.bsky.social
Visiting PhD at Stanford🌲, CS PhD student at NUS 🇸🇬, PhD Fellow @ Google, NLP researcher📒
https://yocodeyo.github.io
Working on Social Intelligence and Evaluation
https://yocodeyo.github.io
Working on Social Intelligence and Evaluation
Reposted by Ella Minzhi Li
My first bluesky post will be for my first project as a postdoc at Stanford.
Talk Arena is our first step towards building audio LMs into interactive agents. Try it out and let me know what you think. talkarena.org
Talk Arena is our first step towards building audio LMs into interactive agents. Try it out and let me know what you think. talkarena.org
Talk Arena
Interactive evaluation for audio models
talkarena.org
December 10, 2024 at 1:39 AM
My first bluesky post will be for my first project as a postdoc at Stanford.
Talk Arena is our first step towards building audio LMs into interactive agents. Try it out and let me know what you think. talkarena.org
Talk Arena is our first step towards building audio LMs into interactive agents. Try it out and let me know what you think. talkarena.org
Reposted by Ella Minzhi Li
With an increasing number of Large *Audio* Models 🔊, which one do users like the most?
Introducing talkarena.org — an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on user preferences rather than static benchmarks.
🧵 (1/5)
Introducing talkarena.org — an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on user preferences rather than static benchmarks.
🧵 (1/5)
December 10, 2024 at 12:01 AM
With an increasing number of Large *Audio* Models 🔊, which one do users like the most?
Introducing talkarena.org — an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on user preferences rather than static benchmarks.
🧵 (1/5)
Introducing talkarena.org — an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on user preferences rather than static benchmarks.
🧵 (1/5)