-
Seoul National University
- South Korea, Seoul
-
20:56
(UTC +09:00)
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
The Missing Point in Vision Transformers for Universal Image Segmentation
Investigation into the roles of Register and CLS Tokens in Vision Transformers
tulip-berkeley / open_clip
Forked from mlfoundations/open_clipAn open source implementation of CLIP (With TULIP Support)
PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437
An extremely fast Python package and project manager, written in Rust.
Seamless navigation between tmux panes and vim splits
A python debugger that can attach to running processes.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA etc.🔥
Script based installer for new users trying out Apache CloudStack
🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
When it comes to optimizers, it's always better to be safe than sorry
🌠 Neovim plugin to animate the cursor with a smear effect in all terminals
Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.
Official PyTorch Implementation of Efficient and Versatile Robust Fine-Tuning of Zero-shot Models, ECCV 2024
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
InstantDrag: Improving Interactivity in Drag-based Image Editing
Author's Implementation for E-LatentLPIPS
nvim-cmp source for nvim-dap REPL and nvim-dap-ui buffers
Efficient Triton Kernels for LLM Training
Official repository of the "Active Learning for Semantic Segmentation with Multi-class Label Query (NeurIPS'23)"
TensorDict is a pytorch dedicated tensor container.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"