collaborators

6 papers

cs.IR2026

Generative Pseudo-Labeling for Pre-Ranking with LLMs

Junyu Bi, Xinting Niu, Daixuan Cheng +4

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the tra…

cs.IR2026

HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

Kun Yuan, Junyu Bi, Daixuan Cheng +5

Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory…

cs.CV2026

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

Yuxi Liu, Yipeng Hu, Zekun Zhang +2

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent…

cs.LG2026

CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure

Boao Kong, Junzhu Liang, Yuxi Liu +2

Low-rank architectures have become increasingly important for efficient large language model (LLM) pre-training, providing substantial reductions in both parameter complexity and m…

math.OC2026

On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes

Boao Kong, Hengrui Zhang, Kun Yuan

We study stochastic gradient descent (SGD) for composite optimization problems with sequential operators subject to perturbations in both the forward and backward passes. Unlik…

cs.LG2026

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

Yuxi Liu, Renjia Deng, Yutong He +3

The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise o…