KDD Cup Winners Unify Recommendation Systems, Team Built Winning Code with DeepSeek
量子位 · wechat · 2026-08-18
Results from the TAAC×KDD Cup at KDD2026 revealed solutions for unifying sequence modeling and feature interaction in recommendation systems. The academic track winner proposed the CRAFT mechanism using an intent Token, while the industrial track winner used a Query Token hub to boost AUC by 0.0048 and cut compute costs by 18%. Notably, the industrial champion team revealed they built the entire model and experiments using only the free DeepSeek web interface.
More from Infra
- Musk says he wants 'maybe more than 10GW' of compute; Nvidia now counts SpaceX as a CSP and co-designs a space server — elonmusk · 2026-10-16
- Jensen Huang: Musk's AI buildout moved from K's to M's, now a CSP-tier NVIDIA customer — elonmusk · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16
- Meta's Muse Spark Open scores 39 vs 48 for closed Spark 1.3 on AA Intelligence Index — EAccelerate_42 · 2026-10-16
- LLM spots useless 95GB-per-frame memcpy in ffmpeg dblur, cutting runtime from 2452ms to 49ms — IgorCarron · 2026-10-16
- DeepSeek-V4-Flash on 4x Radeon AI PRO R9700: the 'refused' 4-card config hits ~79 tok/s — brainchillzZ · 2026-10-16