🔥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

Introducing 🌈 Rainbow Teaming, a new method for generating diverse adversarial prompts for LLMs via LLMs It's a versatile tool 🛠️ for diagnosing model vulnerabilities across domains and creating data to enhance robustness & safety 🦺 Co-lead w/ Sharath Raparthy & Andrei Lupu

How can we train LLM Agents, to learn from their own experience autonomously? Introducing ArCHer, a simple (i.e., small change on top of standard RLHF) and effective way of doing so with multi-turn RL 🧵⬇️ Paper: arxiv.org/abs/2402.19446 Website: yifeizhou02.github.io/archer.io/

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵 dpmd.ai/3TiYV7d

We are now having full conversations with Figure 01, thanks to our partnership with OpenAI. Our robot can: - describe its visual experience - plan future actions - reflect on its memory - explain its reasoning verbally Technical deep-dive 🧵:

So excited and so very humbled to be stepping in to head AI Safety and Alignment at Google DeepMind. Lots of work ahead, both for present-day issues and for extreme risks in anticipation of capabilities advancing.

I'm strongly supportive of this letter and its core message. We need a nuanced approach to the risks and benefits of AI, and more transparency is key to enable a wide group of stakeholders to join the conversation!

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵 dpmd.ai/3vUlgjC

Introducing DrEureka🎓, our latest effort pushing the frontier of robot learning using LLMs! DrEureka uses LLMs to automatically design reward functions and tune physics parameters to enable sim-to-real robot learning. DrEureka can propose effective sim-to-real configurations

super exciting work! Congrats Bernal!

Microsoft presents Self-Exploring Language Models: Active Preference Elicitation for Online Alignment SELM significantly boosts the performance on instructionfollowing benchmarks such as MT-Bench and AlpacaEval 2.0 repo: github.com/shenao-zhang/S… abs: arxiv.org/abs/2405.19332

Rule-based rewards (RBRs) use model to provide RL signals based on a set of safety rubrics, making it easier to adapt to changing safety policies wo/ heavy dependency on human data. It also enables us to look at safety and capability in a more unified lens as a more capable

10 years after DQN, what are deep RL’s impacts on robotics? Which robotic problems have seen the most thrilling real-world successes thanks to DRL? Where do we still need to push the boundaries, and how? Our latest survey explores these questions! Read on for more details. 👇

As I reflect on my journey as a faculty member over the past 7 years, I am overwhelmed with pride and gratitude. What started as a single-student-single-PI lab has blossomed into a vibrant group of almost 20 brilliant PhD students, along with numerous masters and undergraduate

For this week’s NLP Seminar, we are thrilled to host Nicholas Tomlin to talk about Reasoning with Language Models! When: 4/17 Thurs 11am PT Non-Stanford affiliates registration form: forms.gle/cxRmN3oovz8w7a…

The long-term goal of AI is to build models that can handle arbitrary tasks, not just ones they’ve been trained on. We hope our new *benchmark generator* can help measure progress toward this vision

[1/n] 🚀 Thrilled to unveil our latest breakthrough: AttentionInfluence! A groundbreaking, training-free, zero-supervision approach for selecting reasoning-rich pretraining data—just by masking attention heads! ✨ No labels. No retraining. A mere pretrained 1.3B-parameter model

Learned a lot while working with Xiang, Yuetai, Tuney, Xiaoyu and all my collaborators. Wasn’t easy for me but super glad that all my collaborators are helping me out throughout. It’s cool to experience the magic of RL tuning on LLMs, and there are so much more to explore!

Absolutely one of my favorite posts recently! Highly recommended