Summary of Fast Occupancy Network, by Mingjie Lu et al.
Fast Occupancy Networkby Mingjie Lu, Yuanxian Huang, Ji Liu, Xingliang Huang, Dong Li, Jinzhang Peng,…
Summary of Specfuse: Ensembling Large Language Models Via Next-segment Prediction, by Bo Lv et al.
SpecFuse: Ensembling Large Language Models via Next-Segment Predictionby Bo Lv, Chen Tang, Yanan Zhang, Xin…
Summary of Political-llm: Large Language Models in Political Science, by Lincan Li et al.
Political-LLM: Large Language Models in Political Scienceby Lincan Li, Jiaqi Li, Catherine Chen, Fred Gui,…
Summary of Steering Large Language Models to Evaluate and Amplify Creativity, by Matthew Lyle Olson et al.
Steering Large Language Models to Evaluate and Amplify Creativityby Matthew Lyle Olson, Neale Ratzlaff, Musashi…
Summary of A Lightweight U-like Network Utilizing Neural Memory Ordinary Differential Equations For Slimming the Decoder, by Quansong He et al.
A Lightweight U-like Network Utilizing Neural Memory Ordinary Differential Equations for Slimming the Decoderby Quansong…
Summary of Remix-dit: Mixing Diffusion Transformers For Multi-expert Denoising, by Gongfan Fang et al.
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoisingby Gongfan Fang, Xinyin Ma, Xinchao WangFirst submitted to…
Summary of Uncovering Uncertainty in Transformer Inference, by Greyson Brothers et al.
Uncovering Uncertainty in Transformer Inferenceby Greyson Brothers, Willa Mannering, Amber Tien, John WinderFirst submitted to…
Summary of Beexformer: a Fast Inferencing Transformer Architecture Via Binarization with Multiple Early Exits, by Wazib Ansar et al.
BEExformer: A Fast Inferencing Transformer Architecture via Binarization with Multiple Early Exitsby Wazib Ansar, Saptarsi…
Summary of Estimating the Treatment Effect Over Time Under General Interference Through Deep Learner Integrated Tmle, by Suhan Guo et al.
Estimating the treatment effect over time under general interference through deep learner integrated TMLEby Suhan…
Summary of Flash Communication: Reducing Tensor Parallelization Bottleneck For Fast Large Language Model Inference, by Qingyuan Li et al.
Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inferenceby Qingyuan Li, Bo…