activity
20242026
collaborators

10 papers

cs.IR2026

Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems

David Bauer, Cancan Zhang, Wenshun Liu +11

Recommendation systems have undergone significant transformations in the past years. The transition from traditional feature interaction modules to generative next-action predictio…

cs.IR2026

Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design

Bojian Hou, Xiaolong Liu, Xiaoyi Liu +26

Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-s…

cs.LG2026

LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation

Shali Jiang, Hua Zheng, Boyang Liu +40

Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing transfer ratio -- t…

cs.LG2026

Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization

Xuxing Chen, Yun He, Jiayi Xu +9

In machine learning, the goal of multi-task learning (MTL) is to optimize multiple objectives together. Recent works, for example, Multiple Gradient Descent Algorithm (MGDA) and it…

cs.LG2025

Hierarchical LoRA MoE for Efficient CTR Model Scaling

Zhichen Zeng, Mengyue Hang, Xiaolong Liu +11

Deep models have driven significant advances in click-through rate (CTR) prediction. While vertical scaling via layer stacking improves model expressiveness, the layer-by-layer seq…

cs.LG2025

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models

Hyunin Lee, Yong Zhang, Hoang Vu Nguyen +8

Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance…