This is a very exciting journey for me personally to see the model becoming better and better. Can't wait to do even more! See the announcement and some results from our model here: 2/2

Excited to co-host a new Workshop on Intelligent Sports Technologies at ACM MM Asia 2023 with Prof. Wen-Chih Peng and Prof. YuShuen Wang! Please consider submitting your awesome work on intelligent sports technology to the workshop!

RT @AdobeResearch: Adobe researchers are presenting new #ComputerVision work at this week’s #CVPR2023. In addition to the publications, @Ad…

RT @DrJimFan: What GPT-4 gains in IQ, it sacrifices in empathy. Below is someone with suicidal thought seeking help. GPT-4 answers like an…

I will buy a humanoid robot, right now, if it can fold clean laundry for me three days a week, even if it cost 1k or more.

RT @rasbt: Since transformers have such a big impact on everyone's research agenda, I wanted to flesh out a short reading list for machine…

RT @DrJimFan: Music & sound effect industry has not fully understood the size of the storm about to hit. There’re not just one, or two, bu…

reading this article I see the scope and how deep this cuts for independent artists. It makes me sad to read it and even more so knowing there's a chance they might lose.

@DrJimFan This feels dangerous: our knowledge base relies on our knowledge base, and things stop evolving, or evolve into a heavily biased world

RT @ylecun: If language were sufficient to express human thought, why would we need visual arts, music, dance?

RT @karpathy: debugging in Python: - `print()`s alone: too simple - `import pdb; pdb.set_trace()`: too complex - `import code; code.interac…

Happy new year!

RT @omarsar0: Excited to publish the Prompt Engineering Guide, a new repo for discovering papers, guides, tools, and datasets to learn abou…

RT @DrJimFan: ChatGPT is the closest model we have that looks like AGI, but still suffers from hallucination and tends to write plausible-l…

Coding in my first years of PhD be like...

#ProjectBlink

RT @AnimaAnandkumar: Physics-informed neural operator (PINO) for multi-body dynamics. The 3D PDE is challenging, but nicely decomposes into…