[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links

Lightweight plotting to the terminal. 4x resolution via Unicode.

DanbooRegion: An Illustration Region Dataset (ECCV 2020)

A PyTorch implementation of "CoAtNet: Marrying Convolution and Attention for All Data Sizes"

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

[CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction

Compare SELUs (scaled exponential linear units) with other activations on MNIST, CIFAR10, etc.

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

WarAgent: LLM-based Multi-Agent Simulation of World Wars

PyTorch implementation of Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016)

Efficient triton implementation of Native Sparse Attention.

A faster-rcnn model for anime character segmentation.

Code and Dataset from Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters

Tensorflow Implementation of Adversarial Attack to Capsule Networks

Language models are open knowledge graphs ( non official implementation )

GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM

Lifelong Learning with Dynamically Expandable Networks, ICLR 2018

Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

[CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

[NeurIPS 2024] Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

[ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection

Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion. CVPR_2021.

Query-Reduction Networks (QRN)

Official code repository for Sketch-of-Thought (SoT)