Jonathan

@scaling01 Many years ago, he handpicked wrongly labelled samples in MNIST🤣 which proves that models reaching 100% accuracy in MNIST aren’t reliable.

of course merged by the 500IQ Tsinghua GOAT himself

@jxmnop Oh I remember him! Years ago he picked out the wrongly labelled samples in MNIST🤣

this guy invented VLLM. he's basically the john wick of CUDA kernels

@CVPR @Qi12Tom @aliathar94 @_vztu So, is there any approximate timeline? We will be greatly pleased for knowing the timescale (like within 6hrs, 12hrs, a day, etc.)

@Qi12Tom @aliathar94 @_vztu Most are done, through checks and balances between PCs, Senior ACs, ACs and AC triplets. The focus now is on the few left where there are discrepancies. Stay tuned.

😟Hey friends, star/reply to this tweet if you're also waiting for @CVPR decisions

@CVPR Almost There Is All You Need for Hosting CVPR 🤓🤓🤓

Looking for the EXACT #CVPR2025 decision release time? Don’t ask, we don’t know either 😉 Good luck! Timelines: cvpr.thecvf.com/Conferences/20…

@GregKara6 @Lang__Leon @NeurIPSConf Cheating in a Chinese university will appear in your record (note that it’s a must), affecting further opportunities including graduate studies and job seeking. Based on your prejudice and your American teacher’s lack in knowledge, I seriously don’t expect you to fact-check.

NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly. NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.

@AlgebraicAmin01 @HajijMustafa Chris Bondar’s PhD thesis may be useful 👀

@HajijMustafa Do you mind recommending some TDL lectures/tutorials / resources for neophytes?

Strong opinion: The shift from topological data analysis (TDA) to topological deep learning (TDL) parallels the evolution from signal processing to deep learning, moving from feature extraction on raw data to learning hierarchical abstractions from latent representations.

@seagull2148 @onNewHorizons Interesting! I also just finished a work on RC and happen to read this🤣

Excited to announce that our review paper on Reservoir Computing with Prof. Danilo V. Vargas is accepted in IEEE Access, a top open-access journal. It serves as a comprehensive guidebook to the recent advances in #ReservoirComputing. Enjoy it at ieeexplore.ieee.org/document/10196…