HKUDS
PulseAugur coverage of HKUDS — every cluster mentioning HKUDS across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
RAG-Anything framework enables conversational AI with multimodal documents
RAG-Anything is an open-source Python framework designed to enable conversational AI with PDFs and Office documents that contain images, tables, and equations. Unlike traditional RAG methods that flatten documents to pl…
-
GraphRAG vs. LLM Wiki: Comparing LLM Knowledge Base Approaches
The article compares two approaches to building LLM-powered knowledge bases: GraphRAG and LLM Wiki. Both methods use LLMs to distill raw data into a more structured representation, but they face similar challenges such …
-
CLI-Anything project makes all software agent-native
CLI-Anything is a new open-source project that aims to make all software agent-native. Developed by HKUDS, the tool provides a command-line interface (CLI) hub that allows AI agents to interact with any software. The pr…
-
New algorithm TASKER improves video understanding and agentic tasks
Researchers have developed TASKER, a novel keyframe extraction algorithm designed to improve performance in both Video Question Answering (VideoQA) and video-guided agentic tasks. This algorithm, detailed in a new paper…
-
AI-Trader enhanced into production-ready, self-hostable version
A developer has enhanced the popular open-source AI-Trader project, which autonomously publishes trading signals and competes on leaderboards. The improved version, named Ai-Trader-Pro, addresses issues like lack of Doc…