Our paper got accepted to #NeurIPS #neurips2024 . Special thanks to the collaborators, Soo Min Kwon, Qing Qu @qu_1006 , and Hun-Seok Kim!

Cannot agree more.

NeurIPS deadline is in less than 24 hours 🔥🔥🔥.

RT @savvyRL: ICLR goes to Asia for the first time! Yay!!!!

I am going to attend #ICLR2024 next week. Please DM me if you want to chat with me!.My poster: # 242 at the Wed 10:45 am session. Paper, Video and more:

RT @JsonBasedman: Ok hold up, pump the brakes. Are you telling me that Lisa Su, the CEO of AMD, and Jensen Huang, the CEO of NVIDIA, are CO….

RT @y0b1byte: All @iclr_conf papers compressed live here:

Is Low-Rank structure the best for end-to-end, layer-wise, adaptive weight compression for efficient DNNs and #LLMs?. Our ICLR24 paper finds more sophisticated, machine-designed structured matrices for each(!) layer by Gradient Descent!.arxiv:

RT @theDeepView: We spend all week researching the top AI tools so you don't have to. Get insights, tools, and news for free when you jo….

RT @PHDcomics: Seminar accessories

RT @aleks_madry: ImageNet is the new CIFAR! My students made FFCV (, a drop-in data loading library for training mo….

RT @jbhuang0604: How to make steady progress in my research?. I worked so damn hard but "IT JUST DOESN'T WORK!"😤 .How can I unblock myself….

RT @natashajaques: I couldn't resist. With contributions from @maxhkw

RT @gabrielpeyre: Birkhoff’s contraction for Hilbert’s metric is a key tool to quantify convergence.of Markov-Chains (Perron-Frobenius). ht….

RT @lilianweng: 😊Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised l….

RT @DeepMindAI: Out-of-sample generalisation of memory in deep reinforcement learning agents: we demonstrate how two different kinds of mem….

RT @tdietterich: I just published What does it mean for a machine to ‘understand’? .1/.

I just joined Twitter!!.