Listwise Generation Raises Short-Video Engagement in Existing Rankers
LIGE-GR adds causal list context, a list-level value function, and RL beam decoding to existing rankers, raising Reels time spent by 1.14%.
Sep 17, 20264 min2609.18148
2 articles on SOTA Papers
LIGE-GR adds causal list context, a list-level value function, and RL beam decoding to existing rankers, raising Reels time spent by 1.14%.
Dense and MoE variants combine thinking traces, local-global attention, QAT, and MTP drafting, reaching 1451 Arena Elo with a 31B dense model.
