Han Xiao
PulseAugur coverage of Han Xiao — every cluster mentioning Han Xiao across labs, papers, and developer communities, ranked by signal.
-
GELATO architecture enables efficient multimodal embeddings
Researchers have introduced GELATO (Geometry-preserving Embeddings via Locked Aligned Towers), a new multimodal embedding model architecture. GELATO extends existing text embedding models by incorporating frozen encoder…
-
New methods leverage LLMs for advanced source code embedding · 2 sources tracked
Two new research papers introduce novel approaches to source code embedding using large language models. The first, LSem2Vec, combines LLMs with sentence embedding models to extract code semantics without task-specific …
-
On-device omni-modal search engine developed for Apple Silicon Macs
Researchers have developed omni-macos, a novel on-device omni-modal search engine designed to run entirely on Apple Silicon Macs. This system integrates text, code, documents, images, audio, and video into a unified rep…
-
Ledo L90 Delivers 60,000th Vehicle, Reaching Key Sales Milestone
Ledo L90 has achieved a significant milestone by delivering its 60,000th vehicle. The 60,000th unit was delivered to renowned extreme explorer Han Xiao at a Nio experience center in Huzhou. This achievement highlights t…
-
Jina AI releases new text embedding models with task-targeted distillation
Researchers have developed a new method for training text embedding models that combines distillation techniques with task-specific contrastive loss. This approach aims to create compact, high-performance embedding mode…