Wilson Zhao
@wilzh40
Followers
234
Following
999
Media
5
Statuses
80
fan of beep boop music + things in transit (transients) future author of "the art and zen of motorcycle crashing" opinions are my own
SF Bay Area
Joined August 2014
RT @jesseengel: Realtime interactive generative models FTW! . Announcing a new 🌊 of details and features for Magenta RealTime, the open wei….
0
146
0
re: "informative gradients that can be efficiently computed" what NP problem would this reduce to? or is this more of an intuitive gut check (which I generally agree!).
@AlexGDimakis @_jasonwei Right so P=NP iff all problems have informative gradients that can be efficiently computed lol yet another P?NP statement.
0
0
1
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
508
775
5K
so cool! will give it a spin.
We’ve released The Infinite Crate, a plugin to play with Lyria RealTime directly in the DAW (or as a standalone app)! Super happy to see this out in the world and have real-time generation better integrated with music production tools 🎶 . Download here:
0
0
2
RT @Ilaria__Manco: We’ve released The Infinite Crate, a plugin to play with Lyria RealTime directly in the DAW (or as a standalone app)! Su….
magenta.withgoogle.com
Magenta presents Live Generative Music in your DAW using the Gemini API.
0
1
0
I've been playing since 2016 and just got to the valley of the dead. how are you going to design the reward fn? checkpoints?.
A couple bits of news:. 1. Happy to share my first (human) NetHack ascension-next step is RL agents :) . 2. I wrote a post discussing some @NetHack_LE challenges & how they map to open problems in RL & agentic AI. Still the best RL benchmark imo.
1
0
1
RT @saurabh_shah2: Prediction: there will be a paper (or OAI blog post) with a graph showing as you scale simulation compute + reduce sim2r….
0
2
0
RT @ArxivSound: ``Deconstructing Jazz Piano Style Using Machine Learning,'' Huw Cheston, Reuben Bance, Peter M. C. Harrison, .
arxiv.org
Artistic style has been studied for centuries, and recent advances in machine learning create new possibilities for understanding it computationally. However, ensuring that machine-learning models...
0
1
0
RT @zacknovack: Releasing Stable Audio Open Small!.75ms GPU latency!.7s *mobile* CPU latency!.How?. w/Adversarial Relativistic Contrastive….
0
15
0
RT @brendanh0gan: new vllm verifiable rl task - interacting with a gui . I auto-generate interfaces with random shapes, buttons & a window….
0
31
0
RT @stephen_wolfram: From the point of view of science I've never been too excited about the Game of Life. But now I realize that what's re….
0
241
0
launched something cool today with an amazing team. multimodal *emotional* ai >>>.
Today, we’re releasing Octave: the first LLM built for text-to-speech. 🎨Design any voice with a prompt.🎬 Give acting instructions to control emotion and delivery (sarcasm, whispering, etc.).🛠️Produce long-form content on our Creator Studio. Unlike traditional TTS that just
1
0
7
RT @graycrawford: So proud to bring you Video to Audio! 🔊. I’m fascinated with how this audio model responds to diverse videos so flexibly….
0
7
0
RT @MosesOh4: It was great running into old Magenta folks at Neurips! @jesseengel @jpgard @wilzh40 @douglas_eck @GoogleMagenta
https://t.co….
0
2
0
