Stars
Fast inference from large lauguage models via speculative decoding
[ICLR 2022] "Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, and No Retraining" by Lu Miao*, Xiaolong Luo*, Tianlong Chen, Wuyang Chen, Dong Liu, Zhangyang Wang
Superposition Yields Robust Neural Scaling
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
Official PyTorch implementation for "Large Language Diffusion Models"
📰 Must-read papers and blogs on Speculative Decoding ⚡️
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
An open source implementation of CLIP.
Evaluate sensitivity of channel/vector connection to decrease width/depth of network. Which will accelerate inference speed and reduce storage usage without any other module or support
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)
Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.
Community maintained fork of pdfminer - we fathom PDF
[AAAI'23 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
[SynthText Chinese] Improved code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR…
[KOREAN] Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.
A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約
Official implementation for "GLASS: Global to Local Attention for Scene-Text Spotting" (ECCV'22)
Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)
GIT: A Generative Image-to-text Transformer for Vision and Language
End-to-End Object Detection with Transformers
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)