Summary of Dycoke: Dynamic Compression Of Tokens For Fast Video Large Language Models, by Keda Tao et al.
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Modelsby Keda Tao, Can Qin,…
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Modelsby Keda Tao, Can Qin,…
Instance-Aware Generalized Referring Expression Segmentationby E-Ro Nguyen, Hieu Le, Dimitris Samaras, Michael RyooFirst submitted to…
OminiControl: Minimal and Universal Control for Diffusion Transformerby Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu…
High-Resolution Image Synthesis via Next-Token Predictionby Dengsheng Chen, Jie Hu, Tiezhu Yue, Xiaoming Wei, Enhua…
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understandingby Yiming Zhang, Zhuokai Zhao, Zhaorun Chen,…
Closer Look at Efficient Inference Methods: A Survey of Speculative Decodingby Hyun Ryu, Eric KimFirst…
Debiasing Watermarks for Large Language Models via Maximal Couplingby Yangxinyu Xie, Xiang Li, Tanwi Mallick,…
Bag of Design Choices for Inference of High-Resolution Masked Generative Transformerby Shitong Shao, Zikai Zhou,…
Communication Compression for Tensor Parallel LLM Inferenceby Jan Hansen-Palmus, Michael Truong Le, Oliver Hausdörfer, Alok…
Bangla Grammatical Error Detection Leveraging Transformer-based Token Classificationby Shayekh Bin Islam, Ridwanul Hasan Tanvir, Sihat…