ByteDance (Feng Cheng et al.) · Generative Slate Ranking
OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking and Mix-Ranking with One Autoregressive Transformer
OneTrans-GSR is a decoder-only policy that extends ByteDance's deployed OneTrans backbone to generate full exposure slates end-to-end, replacing hand-crafted rules in reranking and mix-ranking. A reward model scores complete slates and guides reinforcement learning toward slate-level and long-term objectives. In online A/B tests it improved GMV per user by 2.63%, advertiser value by 2.06% and repurchase rate by 2.03%, while cutting end-to-end latency across both stages by 13%.
Open the source ↗Similar Research & Safety releases
- LongBanana
Kolors Team, Kuaishou Technology (Haoxiang Cao et al.) · Image Synthesis Benchmark · Week 47, 2026
- P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors
StepFun (Sinuo Wang et al.) · Parameter-prior distillation · Week 47, 2026
- HOPE: Higher-Order Pruning of Experts
Amazon (Alex M Tseng, Luca Zancato), via Hugging Face blog · MoE Expert Pruning · Week 47, 2026
- LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time
Teresa Delgado, Hugo Hazard, Martin Benfeghoul, Jun Wang, Zafeirios Fountas · KV Cache Compression · Week 47, 2026
- WorldParticle
MIT, University of British Columbia and collaborators (incl. Meta) · Unified Physics Simulator · Week 47, 2026
- Amortizing Maximum Inner Product Search with Learned Support Functions
Apple Machine Learning Research · Learned MIPS Routing · Week 46, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.