Summary of Mrt5: Dynamic Token Merging For Efficient Byte-level Language Models, by Julie Kallini et al.
MrT5: Dynamic Token Merging for Efficient Byte-level Language Modelsby Julie Kallini, Shikhar Murty, Christopher D.…
Summary of Looking Beyond the Top-1: Transformers Determine Top Tokens in Order, by Daria Lioubashevski et al.
Looking Beyond The Top-1: Transformers Determine Top Tokens In Orderby Daria Lioubashevski, Tomer Schlank, Gabriel…
Summary of Dynamic Vocabulary Pruning in Early-exit Llms, by Jort Vincenti et al.
Dynamic Vocabulary Pruning in Early-Exit LLMsby Jort Vincenti, Karim Abdel Sadek, Joan Velja, Matteo Nulli,…
Summary of Probabilistic Language-image Pre-training, by Sanghyuk Chun and Wonjae Kim and Song Park and Sangdoo Yun
Probabilistic Language-Image Pre-Trainingby Sanghyuk Chun, Wonjae Kim, Song Park, Sangdoo YunFirst submitted to arxiv on:…
Summary of Multi-draft Speculative Sampling: Canonical Architectures and Theoretical Limits, by Ashish Khisti et al.
Multi-Draft Speculative Sampling: Canonical Architectures and Theoretical Limitsby Ashish Khisti, M.Reza Ebrahimi, Hassan Dbouk, Arash…
Summary of Adaedl: Early Draft Stopping For Speculative Decoding Of Large Language Models Via An Entropy-based Lower Bound on Token Acceptance Probability, by Sudhanshu Agrawal et al.
AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower…
Summary of Future Token Prediction — Causal Language Modelling with Per-token Semantic State Vector For Multi-token Prediction, by Nicholas Walker
Future Token Prediction – Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Predictionby…
Summary of Faster Language Models with Better Multi-token Prediction Using Tensor Decomposition, by Artem Basharin et al.
Faster Language Models with Better Multi-Token Prediction Using Tensor Decompositionby Artem Basharin, Andrei Chertkov, Ivan…
Summary of Amusd: Asynchronous Multi-device Speculative Decoding For Llm Acceleration, by Bradley Mcdanel
AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Accelerationby Bradley McDanelFirst submitted to arxiv on: 22…
Summary of Treebon: Enhancing Inference-time Alignment with Speculative Tree-search and Best-of-n Sampling, by Jiahao Qiu et al.
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Samplingby Jiahao Qiu, Yifu Lu, Yifan…