Albert Gu

@_albertgu

assistant prof @mldcmu. chief scientist @cartesia. leading the ssm revolution.

Joined December 2018

Following

21.4K

Followers

Replies Reposts Media

Albert Gu
@_albertgu
Aug 27
sonic-3.6 is out, with a large improvement over (the already #1) sonic-3.5 in just a few months! the research team's focus on fundamentals is accelerating progress at the frontier of architectures and audio
Cartesia
@cartesia
Aug 27
Sonic-3.6 is now generally available. In January we made a bet: stop tuning the existing paradigm, rebuild from the architecture up. How we topped our own best model in two months → cartesia.ai/blog/sonic-3.6…
00:00
2
Albert Gu
@_albertgu
Aug 17
the team continues cooking 👩‍🍳 this is now an unprecedented gap on both the super competitive Provider Voices leaderboard as well as the newer Controlled Voices leaderboard (a stronger benchmark that can't be benchmaxxed, requiring truly better algorithms) Cartesia's TTS model is
Artificial Analysis
@ArtificialAnlys
Aug 17
Cartesia's Sonic 3.6 takes the #1 spot on both the Provider Voice and Controlled Voice Artificial Analysis Speech Arena leaderboards, surpassing Speechify AI's Simba 3.2 and Alibaba's Qwen-Audio-3.0-TTS-Plus, with Sonic 3.5 holding #2 on Controlled Voice Sonic 3.6 is the latest
5
Albert Gu
@_albertgu
Jul 28
Evaluations are difficult and vague for all generative models, and benchmarks only capture a small slice. Our blog post dives into the nuances for TTS
Cartesia
@cartesia
Jul 28
"Is this TTS model good?" gets harder to answer as models improve. "Good" is at least five axes: correctness, naturalness, contextual correctness, robustness, and most evals only capture the first. We wrote up the failure modes that make TTS eval hard: cartesia.ai/blog/is-this-t…
3
Albert Gu
@_albertgu
Jul 8
Cartesia is hosting an ICML party tomorrow (Thursday) night! it'll go late, but come early or i may have to bounce you again
Cartesia's ICML After Party · Luma
From luma.com
10
Albert Gu
@_albertgu
Jun 26
Transformers are better at copying, while RNNs are better at modeling "meaning-bearing words—the nouns, verbs, & adjectives that say what a sentence is about"
Ai2
@allen_ai
Jun 25
Hybrid (transformer–RNN) models are fast becoming a serious alternative to the transformer, but a big question remains: how do they process tokens differently & how does this impact performance? We compared our transformer (Olmo 3) & hybrid (Olmo Hybrid) models to find out. 🧵
6