NOSE: Enabling AI to Smell with a Unified Molecule‑Receptor‑Semantic Tri‑modal Representation

NOSE introduces a neural olfactory‑semantic embedding that unifies molecular structure, receptor sequences, and natural‑language odor descriptions into a continuous space, achieving state‑of‑the‑art results on eleven tasks and strong zero‑shot generalization for odor and receptor retrieval.

Deep Learningcontrastive learningmolecular design

0 likes · 8 min read

NOSE: Enabling AI to Smell with a Unified Molecule‑Receptor‑Semantic Tri‑modal Representation

DataFunTalk

Oct 5, 2025 · Artificial Intelligence

How Kuaishou Leverages Large‑Model AI to Boost Advertising Performance

This article outlines Kuaishou's two‑year exploration of multimodal large‑model techniques in advertising, detailing the challenges of content‑domain ad estimation, the COPE unified product representation framework, and the LEARN LLM knowledge‑transfer approach that together improve user interest modeling and business ROI.

LLM knowledge transferLarge Model AIadvertising optimization

0 likes · 6 min read

How Kuaishou Leverages Large‑Model AI to Boost Advertising Performance

DataFunSummit

Dec 11, 2024 · Artificial Intelligence

Exploring Large‑Model Applications in Advertising: The COPE and LEARN Frameworks at Kuaishou

This article reviews Kuaishou's two‑year exploration of large‑model and multimodal techniques for advertising, detailing the challenges of content‑domain ad estimation, the COPE unified product representation framework, and the LEARN LLM knowledge‑transfer approach, and reports the resulting business gains.

LLM knowledge transferadvertising recommendationcross‑domain behavior

0 likes · 16 min read

Exploring Large‑Model Applications in Advertising: The COPE and LEARN Frameworks at Kuaishou