PIKE-RAG
PIKE-RAG (sPecIalized KnowledgE and Rationale Augmented Generation) framework mainly consists of several basic modules, including document parsing, knowledge extraction, knowledge storage, knowledge retrieval, knowledge organization, knowledge-centric reasoning, and task decomposition and coordination while building coherent…
Collaborators: Prompt engineering with Siddharth Suri and David Holtz
Researcher Siddharth Suri and professor David Holtz give a brief history of prompt engineering, discuss the debate behind their recent collaboration, and share what they found from studying how people’s approaches to prompting change as…
Low latency carbon budget 2023
In 2023, global land carbon sinks—the Earth’s forests, soils, and vegetation that absorb CO2—experienced a dramatic decline, as revealed by a study published in National Science Review by several international research teams. Using dynamic global…
STACK 2024 – SPACE in the Age of AI: Measuring What Matters for Developer
Synopsis: In the rapidly evolving world of AI, measuring developer productivity and experience requires more than just tracking output—it demands a holistic approach that captures the multifaceted nature of engineering work while keeping the focus…
PadChest-GR dataset
A dataset called PadChest-GR (Grounded-Reporting), derived from PadChest, which can be used to train radiological reporting models for chest x-rays. We curated a public bilingual dataset of 4,555 CXR studies with evidence-based reports (3,099 abnormal…