VLLMs
PulseAugur coverage of VLLMs — every cluster mentioning VLLMs across labs, papers, and developer communities, ranked by signal.
-
New AI models enhance streaming video understanding with efficient memory management · 7 sources tracked
Researchers are developing new methods for streaming video understanding, focusing on efficient memory management for multimodal large language models (MLLMs). LatentStream and ShallowStream propose novel frameworks tha…
-
Parsewise launches API for verifiable document data extraction
Parsewise, a new startup founded by Greg and Max, has launched an API designed to extract and structure data from large collections of unstructured documents. The service focuses on providing verifiable data lineage, al…
-
Researchers develop Thought Graph Traversal to improve VLLM reasoning for X-ray reports
Researchers have developed a novel framework called Thought Graph Traversal (TGT) to enhance the reasoning capabilities of vision-language models (VLLMs) specifically for analyzing chest X-rays. This method integrates s…