Xavier Gonzalez
@xavierjgonzalez
Followers
265
Following
1K
Statuses
66
PhD candidate in AI and Machine Learning at @Stanford. Advised by @scott_linderman. All views my own.
Stanford, CA
Joined January 2021
So excited by our latest @NeurIPSConf paper on parallelizing nonlinear RNNs! With my amazing collaborators @awarr9, @jimmysmith1919, and @scott_linderman. We are building on the beautiful DEER algorithm by YH Lim, @mfkasim, et al. (. Thread below!
Did you know that you can parallelize *nonlinear* RNNs over their sequence length!? Our @NeurIPSConf paper "Towards Scalable and Stable Parallelization of nonlinear RNNs," which introduces quasi-DEER and ELK to parallelize ever larger and richer dynamical systems! 🧵 [1/11]
1
4
17
Excited to share that our latest research on parallelizing nonlinear RNNS is being featured on the arXiv discussion forum @askalphaxiv. I will be on alphaXiv to answer any questions you have on the paper.
0
5
24
RT @heyyalexwang: did you know you've been doing test-time learning this whole time? transformers, SSMs, RNNs, are all test-time regressor…
0
108
0
RT @JayAlammar: Alphaxiv is an awesome way to discuss ML papers -- often with the authors themselves. Here's an intro and demo by @rajpalle…
0
22
0
RT @wonmin_byeon: We are hiring a PhD intern at NVIDIA research. If you are interested, email me your CV. Research topics: SSM/Mamba, ot…
0
85
0
I believe the alphaXiv is an important step forward in disseminating knowledge. Thank you @rajpalleti314 and the whole @askalphaxiv team for your amazing work on this platform!
Goodreads for arXiv papersđź’ˇ What if instead of arbitrary algorithms and tweets, arXiv papers were curated by your research community? Introducing communities on alphaXiv: bridging papers, discussions, and people in one space.
1
1
9
RT @rm_rafailov: We have a new position paper on "inference time compute" and what we have been working on in the last few months! We prese…
0
236
0
RT @scott_linderman: If you'd like to learn more about parallelizing nonlinear RNNs, check out our blog post! It goes step by step through…
0
5
0
RT @MasonKamb: Excited to finally share this work w/ @SuryaGanguli. Tl;dr: we find the first closed-form analytical theory that replicates…
0
152
0
RT @SuryaGanguli: Our new paper! "Analytic theory of creativity in convolutional diffusion models" lead expertly by @MasonKamb
https://t.co…
0
74
0
Does anyone know if @weights_biases supports conditional sweeps? i.e. something like, sweep over 10 values of knob b, but only if knob a is set to false?
0
0
0
RT @jimmysmith1919: We are announcing our Series A led by @AMD Ventures! It is a privilege to work with such an amazing team. More to come…
0
3
0
We also just dropped a new blog that steps through both the the math and the code! Blog: Poster: With my amazing collaborators @awarr9 , @jimmysmith1919 , and @scott_linderman
0
2
37
RT @GabrielPoesia: If you're at NeurIPS, come tomorrow for the Oral+Poster on "Learning Formal Mathematics from Intrinsic Motivation"! Real…
0
18
0
RT @njwfish: Excited to share our new work on causal sensitivity analysis for fairness metrics at #NeurIPS2024! We've developed a causal se…
0
3
0
RT @amberhu63: I'm really excited to be presenting our work on interpretable modeling of neural dynamics at #NeurIPS2024 this week! It was…
0
2
0
RT @scott_linderman: I'm excited to share our #NeurIPS2024 paper, "Modeling Latent Neural Dynamics with Gaussian Process Switching Linear D…
0
18
0
Extremely high praise from the creator of CORNN! CORNN is a mind-boggling approach that trains RNNs using techniques from convex optimization! Thank you @fatihdin4en!
Any work by @xavierjgonzalez is bound to impress! Looking forward to using this in my own research!
0
0
3
@tginart @NeurIPSConf @awarr9 @jimmysmith1919 @scott_linderman @mfkasim Yes! It would be great to see you there! Our poster is Friday 11/13 from 11-2 pacific time, East Exhibit Hall A-C #2010
0
0
0