Beyond Dual‑Tower: Advanced Distillation and Interaction Techniques for Recommendation Systems

This article reviews recent advances that enhance dual‑tower recommendation models by injecting interaction information through various knowledge‑distillation strategies and interaction‑enhanced architectures, summarizing methods such as PFD, ENDX, TRMD, VIRT, Distilled‑DualEncoder, ERNIE‑Search, ColBert, IntTower and MVKE.

AI researchdual-towerinteraction modeling

0 likes · 13 min read

Beyond Dual‑Tower: Advanced Distillation and Interaction Techniques for Recommendation Systems

Meituan Technology Team

Jun 11, 2020 · Artificial Intelligence

Pedestrian Trajectory Prediction: Methodology and Experience from the ICRA 2020 TrajNet++ Competition

The ICRA 2020 TrajNet++ competition challenged teams to predict 4.8‑second pedestrian paths from 3.6‑second observations, and Meituan’s winning solution used a Seq2Seq world‑model that encodes past trajectories, updates a spatio‑temporal interaction map, and decodes future positions, achieving a 1.24 m final displacement error and demonstrating readiness for real‑world unmanned delivery.

AIICRA 2020Prediction

0 likes · 14 min read

Pedestrian Trajectory Prediction: Methodology and Experience from the ICRA 2020 TrajNet++ Competition

Didi Tech

May 15, 2020 · Artificial Intelligence

Search Matching Models and Applications in DiDi Food

The article outlines DiDi Food’s search relevance challenge, defines semantic matching versus traditional keyword methods, describes the recall‑ranking pipeline, and reviews three families of deep matching models—representation‑based (e.g., DSSM), interaction‑based (e.g., DRMM) and hybrid (e.g., DUET)—including experimental results and a recruitment notice.

DiDi Fooddeep matchinginformation retrieval

0 likes · 16 min read