RT @karpathy: New 3h31m video on YouTube: "Deep Dive into LLMs like ChatGPT" This is a general audience deep dive into the Large Language…

@jw2yang4ai @iclr_conf Cool works and nice ideas! Congrats @jw2yang4ai

RT @fly51fly: [LG] Task Vectors in In-Context Learning: Emergence, Formation, and Benefit L Yang, Z Lin, K Lee, D Papailiopoulos... [Univer…

RT @Boyiliee: 🚀 Introducing 𝐖𝐨𝐥𝐟 🐺: a mixture-of-experts video captioning framework that outperforms GPT-4V and Gemini-Pro-1.5 in general s…

RT @COLM_conf: COLM 2025: Oct 7-9 (conference), Oct 10 (workshops) Montreal, Canada Abstract deadline: March 20, 2025 Paper deadline: Mar…

RT @kchonyc: synthetic data is the weirdest name for data augmentation.

@jiasenlu @Diyi_Yang Wow really nice workshop! I want to be there too, but I will leave tomorrow 🥲

RT @fly51fly: [CL] Training Large Language Models to Reason in a Continuous Latent Space S Hao, S Sukhbaatar, D Su, X Li… [Meta] (2024) htt…

(I forgot this) This workshop is organized by a great team: @jiasenlu @yanbei_c @ai_den_lee @seo_minjoon @mmiemon @LINJIEFUN Sangho Lee!

RT @jiasenlu: (1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap betwee…

@XiaohuaZhai @OpenAI @giffmana @__kolesnikov__ Wow, that's huge news🤯! Congrats to you all. I'm looking forward to what you guys will do there!

@_sungmin_cha @NeurIPSConf See you there! ;)

@chriswolfvision @naverlabseurope @kgcs96 @JeromeRevaud @WeinzaepfelP @romain_bregier @Vinc3nt_Leroy @dlarlus @mbsariyildiz @fabienbaradel @ThomasLUC4S @rafasamrez Good luck, everyone!

RT @HaritzPuerto: 🧵 It is assumed that Membership Inference Attacks (MIA) do not work on LLMs, but our new paper shows it can work at the r…

RT @dlarlus: 📢 Job Alert 📢 @naverlabseurope My team is looking for a Research Scientist in Visual Representation Learning - More info http…

RT @SeonghyeonYe: 🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using…