Zewen Jin

5 papers · 2025–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) ⭐ Rising Star (5)

Venues

AAAI (2) ACL (1) CVPR (1) NSDI (1)

Top co-authors

Cheng Li (5) Shengnan Wang (4) Youhui Bai (4) Ping Gong (3) Guanbin Xu (2) Juncheng Zhang (2) Jiaan Zhu (2) Zhihao Le (1) Jiawei Yi (1) Chengjie Tang (1)

Research topics

Machine Learning (4) Application Areas (4) Artificial Intelligence (3) Core AI (3) Optimization & Theory · Machine Learning (3) Deep Learning (2) Computer Vision (1) Architectures (1) Core Methods (1) Generation (1) Optimization & Theory · Deep Learning (1) Techniques (1)

Keywords

neural network optimization (2) communication efficiency (2) sparse attention (2) inference acceleration (2) model inference (2) mixture of expert (2) distributed training (1) pipeline parallelism (1) inference optimization (1) collective communication (1) diffusion transformer (1) adaptive clustering (1) parallel training (1) expert parallelism (1) large language model (1) learn to hash (1) model compression (1) top-k attention (1) video generation (1) distributed learning (1)

Papers

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation CVPR 2026 SMIDT: High-Performance Inference Framework for MoE Models with Dynamic Top-K Routing AAAI 2026 AutoCCL: Automated Collective Communication Tuning for Accelerating Distributed and Parallel DNN Training NSDI 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference ACL 2025