🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I am really excited to reveal what Google DeepMind's Open Endedness Team has been up to 🚀. We introduce Genie 🧞, a foundation world model trained exclusively from Internet videos that can generate an endless variety of action-controllable 2D worlds given image prompts.

Great new work from our team and colleagues at Google DeepMind! On the Massive Text Embedding Benchmark (MTEB), Gecko is the strongest model to fit under 768-dim. Try it on Google Cloud. Use it for RAG, retrieval, vector databases, etc.

Happy news: ICLL is accepted to ICML, 2024!

Nice new read on tokenization! You've heard about the SolidGoldMagikarp token, which breaks GPT-2 because it was present in the training set of the Tokenizer, but not the LLM later. This paper digs in in a lot more depth and detail, on a lot more models, discovering a less

sign up for the wait-list here docs.google.com/forms/d/e/1FAI…

It was great to work with Minsuk and excited to see this released. Looking at individual model outputs this way helps one see which examples/tasks are truly wins across model versions and which ones are just due to randomness of generation or raters.

Great to see Gemini 1.5 doing well on this new video understanding benchmark!

We have an experimental updated version of Gemini 1.5 Pro that is #1 on the LMSYS Org Chatbot Arena. This model is a significant improvement over earlier versions of Gemini 1.5 Pro (it cracks into 1300+ elo score territory). I'm really proud of the whole team of people that

I have been thinking about this since ChatGPT came out. Using RLHF never fully made sense to me given how restricted it is compared to regular RL. There should be a way simpler non-exploring method to distill RM knowledge into the main model.

We'll present this at #NeurIPS

Welcome, AlphaChip! Today, we are sharing some exciting updates on our work published in nature in 2021 on using reinforcement learning for ASIC chip floorplanning and layout. We’re also naming this work AlphaChip. Since we first published this work, our use of this approach

Machine unlearning ("removing" training data from a trained ML model) is a hard, important problem. Datamodel Matching (DMM): a new unlearning paradigm with strong empirical performance! w/ Kristian Georgiev Roy Rinberg Sam Park Shivam Garg Aleksander Madry Seth Neel (1/4)

I will be in ATTRIB workshop tomorrow (attrib-workshop.cc). Stop by if you’d like to chat with me and connect with other great researchers in this area.

andi (twocents.money) I worked on the M series while at Apple. The main advantage that stuck out to me was actually that they were able to acquire dozens of top Intel engineers 5-10 years ago as Intel started struggling and making poor decisions. For example, Intel had a couple sites around the

arxiv.org/abs/2411.03923 "From Figure 3(a), it is apparent that many of the benchmarks we considered are substantially contaminated in the Llama 1 pre-training corpus as well as in the Pile. For 8 of the 13 datasets that we considered, on average more than 50% of the samples are

This model’s “thinking” capabilities are driving major gains: 🧑‍🔬Top performance on math and science benchmarks (AIME, GPQA) 💻Exceptional coding performance (LiveCodeBench) 📈Impressive performance on complex prompts (Humanity’s Last Exam) #1 on lmarena.ai (formerly lmsys.org) leaderboard 🏆

Presenting our work on training data attribution for pretraining this morning: iclr.cc/virtual/2025/p… -- come stop by in Hall 2/3 #526 if you're here at ICLR!

Our latest Gemini 2.5 Pro update is now in preview. It’s better at coding, reasoning, science + math, shows improved performance across key benchmarks (AIDER Polyglot, GPQA, HLE to name a few), and leads lmarena.ai with a 24pt Elo score jump since the previous version. We also