Songze Li
PulseAugur coverage of Songze Li — every cluster mentioning Songze Li across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework uses LLMs to bridge semantic gap in knowledge graph reasoning
Researchers have developed a new framework called Enrich-on-Graph (EoG) to improve the reasoning capabilities of Large Language Models (LLMs) in knowledge-intensive tasks like knowledge graph question answering (KGQA). …
-
New framework exploits stability-plasticity in pretrained detectors for incremental object detection
Researchers have developed a new framework for incremental object detection that leverages the stability-plasticity asymmetry found in pretrained DETR-based detectors. This approach freezes localization heads to maintai…
-
New UI-in-the-Loop paradigm enhances LLM GUI reasoning
Researchers have introduced a new paradigm called UI-in-the-Loop (UILoop) to improve how multimodal large language models (MLLMs) understand and interact with graphical user interfaces (GUIs). This approach treats GUI r…