arxiv:2603.09229
Yujun Lin
synxlin
AI & ML interests
None yet
Recent Activity
authored a paper 20 days ago
Deep Gradient Compression: Reducing the Communication Bandwidth for
Distributed Training authored a paper 20 days ago
TorchSparse: Efficient Point Cloud Inference Engine authored a paper 20 days ago
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM
ServingOrganizations
arxiv:2602.02958
arxiv:2601.14243
arxiv:2512.02010
arxiv:2512.01031
arxiv:2511.16665
arxiv:2510.11696
arxiv:2509.25182
arxiv:2509.25180
arxiv:2506.19852
arxiv:2505.18875
arxiv:2502.14866
arxiv:2502.01776
arxiv:2501.18427
arxiv:2411.05007
arxiv:2410.10629
arxiv:2405.04532
arxiv:2204.10319
arxiv:2007.10319
arxiv:1712.01887
