Scaling LLMs with more data is hitting its limits. To address more complex tasks, we need innovative approaches. Shifting from teaching models what to answer to how to solve problems, leveraging test-time compute and meta-RL, could be the solution. Check out Rafael's 🧵 below!

Ever watched someone solve a hard math problem? Their first attempt is rarely perfect. They sketch ideas, cross things out, and try new angles. This process of exploration is key to human reasoning and our latest research formalizes this as Meta Chain-of-Thought (1/8) 🧵👇

Deepseek has escaped containment

Meta-RL- learning to think

SynthLabs presents: Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

Pokémon Go to the Claude

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models "In this work, we present Big-Math, a dataset of over 250,000 high-quality math questions with verifiable answers, purposefully made for reinforcement learning (RL). To create

Releasing Big-MATH—the first heavily curated & verifiable dataset designed specifically for large-scale RL training & LLM reasoning! 📝 250,000+ problems, 47k NEW Q's ✅ 10x larger than existing datasets like MATH 🧑‍⚖️ Verifiable—we eliminated 400k+ problems Details below! 🧵👇

Start exploring Big-MATH today! 📄 Paper: arxiv.org/abs/2502.17387 💻 Code: github.com/SynthLabsAI/bi… 📂 Dataset: huggingface.co/datasets/Synth…

Happy to finally announce Big-MATH, the largest math reasoning dataset purposefully designed for large-scale RL! We worked tirelessly, cleaning and filtering math datasets so that you don't have to!

Read how SynthLabs, a startup developing AI solutions tailored for logical reasoning, is advancing AI post-training with our @TractoAI: nebius.com/customer-stori… 🔹 Goal: Develop an ML system that empowers reasoning models to surpass pattern matching and implement sophisticated

Are you a frontier lab investing untold sums in training? Are you trying to stay competitive? Are you finding that your competitors' models are ... thinking a bit too much like yours? Then antidistillation.com might be for you! Sam Altman Elon Musk

Why did only humans invent graphical systems like writing? 🧠✍️ In our new paper at CogSci Society, we explore how agents learn to communicate using a model of pictographic signification similar to human proto-writing. 🧵👇

We have released VARS-fUSI: Variable sampling for fast and efficient functional ultrasound imaging (fUSI) using neural operators. The first deep learning fUSI method to allow for different sampling durations and rates during training and inference. biorxiv.org/content/10.110… 1/

>What do you do? >RL Agents for <X>

Our first long-horizon agentic software engineering model is here! We've shipped a model that matches Claude on Cascade in a lot of ways. However the most exciting thing about this release is the trajectory we're on. So much left to do... we're hiring!

excellent work by Jason Weston & team—extending our "Generative Reward Models" work with RL (GRPO) to optimize LLM reasoning during judgment scalable (synthetic) evaluation continues to be AI's key bottleneck!

btw we have ongoing research on this front! we're open-science, pro-publication, and love collaboration. want to push this frontier forward? we're growing our SF team & always open to research partners—reach out, my DMs are open 📩