Latest News

Reinforcement Learning for Email Agents: OpenPipe’s ART·E Outperforms o3 in Accuracy, Latency, and Cost

OpenPipe has introduced ART·E (Autonomous Retrieval Tool for Email), an open-source research agent designed to answer user questions based on inbox contents with a focus on accuracy, responsiveness, and computational efficiency. ART·E demonstrates the practical utility of reinforcement learning (RL)…

Read MoreReinforcement Learning for Email Agents: OpenPipe’s ART·E Outperforms o3 in Accuracy, Latency, and Cost

UniME: A Two-Stage Framework for Enhancing Multimodal Representation Learning with MLLMs

The CLIP framework has become foundational in multimodal representation learning, particularly for tasks such as image-text retrieval. However, it faces several limitations: a strict 77-token cap on text input, a dual-encoder design that separates image and text processing, and a…

Read MoreUniME: A Two-Stage Framework for Enhancing Multimodal Representation Learning with MLLMs