Search papers, labs, and topics across Lattice.
The University of Hong Kong
7
0
11
AOHP redefines how AI agents interact with operating systems, achieving a 21% boost in task completion and a dramatic cut in execution costs.
VideoAgent not only streamlines video editing with advanced automation but also achieves human-level quality in content creation, setting a new standard in the field.
Ling-2.6 and Ring-2.6 achieve unprecedented efficiency in agentic intelligence, enabling instant responses and deep reasoning at trillion-parameter scale.
LLMs still struggle to understand the meaning of common phrases, idioms, and compound words, revealing critical gaps in semantic reasoning.
Achieve robust maritime scene segmentation by jointly learning restoration, fusion, and segmentation, outperforming prior methods in complex, degraded conditions.
Navigate massive codebases with LLMs using a "scouting-first" approach that slashes token consumption without sacrificing reasoning accuracy.
Fine-tune your LLM faster on less data: this entropy-based data selection method slashes compute costs without sacrificing performance.
