1 citations · 1 across the 4 of their papers we have counts for
6 papers
ForgeTrain: Forging Production-Grade Training Frameworks via Harness-Driven AI Development
Qingfeng He, Zhui Zhu, Shangzhan Li +15
Training large models still relies on general-purpose frameworks such as Megatron-LM, whose generality tax constrains scenario-specific optimization and adds runtime overhead throu…
ForgeMegakernel: A General Framework for Efficient Auto-Regressive Model Decode Megakernels
Leshan Li, Zhui Zhu, Xianglong Deng +6
Auto-regressive model decode is bandwidth-bound, since every weight and key/value-cache byte crosses high-bandwidth memory once per token. A megakernel is an ideal solution, but ex…
SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation
Weichen Zhang, Kebin Liu, Fan Dang +3
Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods…
AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference via Dynamical Text Guidance
Weichen Zhang, Zhui Zhu, Ningbo Li +5
Vision-language models (VLMs) have achieved impressive performance on multimodal inference tasks, but the cost remains a significant challenge due to the large number of vision tok…
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Ke Ma, Jiaqi Tang, Bin Guo +8
Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptat…
Palantir: Towards Efficient Super Resolution for Ultra-high-definition Live Streaming
Xinqi Jin, Zhui Zhu, Xikai Sun +6
Neural enhancement through super-resolution (SR) deep neural networks (DNNs) opens up new possibilities for ultra-high-definition (UHD) live streaming over existing encoding and ne…