You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<div>Introducing <ahref="https://aguvis-project.github.io/"target="_blank"className="underline">Aguvis</a> - A unified vision-based strong agent model for autonomous GUI interaction across web, desktop &mobileplatforms.</div>
<div><ahref="https://huggingface.co/hkunlp/instructor-large"target="_blank"className="underline">Instructor embeddings</a> recently hit 5 million downloads on huggingface!</div>
<div>6 years after our <ahref="https://yale-lily.github.io/spider"target="_blank"className="underline">Yale Spider 1.0</a>, we're introducing <ahref="https://spider2-sql.github.io/"target="_blank"className="underline">Spider 2.0</a>, the real-world enterprise agentic Text-to-SQL workflow challenge in the LLM era!</div>
<div>Excited to see <ahref="https://www.anthropic.com/news/3-5-models-and-computer-use"target="_blank"className="underline">Anthropic</a> using our <ahref="https://os-world.github.io"target="_blank"className="underline">OSWorld</a> (NeurIPS'24) to benchmark their computer use!</div>
<div>We have released <ahref="https://os-world.github.io/"target="_blank"className="underline">OSWorld</a>, A unified, real computer env for multimodal agents to evaluate open-ended computer tasks with arbitrary apps and interfaces on Ubuntu, Windows, &macOS! </div>
<div>We have released <ahref="https://github.com/xlang-ai/OpenAgents"target="_blank"className="underline">💥OpenAgents💥</a>, an open platform designed for language agents in the wild! For more details, you can visit our <ahref="https://arxiv.org/abs/2310.10634"target="_blank"className="underline">paper</a> and the <ahref="https://github.com/xlang-ai/OpenAgents"target="_blank"className="underline">code</a>! </div>
<div>We have released <ahref="https://github.com/OpenLemur/Lemur"target="_blank"className="underline">Lemur70B</a>, 🚀 Open &SOTAFoundationModelsforLanguageAgents!TheclosestopenmodeltoGPT-3.5on🤖15agenttasks🤖!!Checkoutour<ahref="https://arxiv.org/abs/2310.06830"target="_blank"className="underline">paper</a> and feel free to download and use the model at <ahref="https://huggingface.co/OpenLemur"target="_blank"className="underline">HuggingFace</a>! </div>
<div>Introducing <ahref="https://text-to-reward.github.io/"target="_blank"className="underline">Text2Reward</a> - Using LLMs to generate dense reward functions from natural language for robotic RL policy training!</div>
0 commit comments