3 papers
cs.LG2025
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
Yaoqi Chen, Jinkai Zhang, Baotong Lu +16
Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because t…
cs.CV2025
Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting
Maochen Yang, Zekun Li, Jian Zhang +2
Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed…
cs.IR2024
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Qi Chen, Xiubo Geng, Corby Rosset +28
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals. In this paper, we introduce MS MARCO Web Search, the first large-s…