Haz Sameen Shahgir's Projects
Official implementation of Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
A curated list of inference strategies and algorithms that boost Vision Language Model (VLM) performance
Bangla Sign Language Dataset (BdSL40) comprises of 611 videos over 40 BdSL words with 8 to 22 video clips per word.
Using flex and bison to make a compiler including symbol table, lexical analysis, syntax and semantic analysis and Assembly Code Generation for intel 8086
Offlines, Onlines and Projects of Level 3 Term 2
Some challenging cases for Image Generation using different image generating models
Follow along of the course homework of Stanford CS221
CSE316_Term_Project
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Winning Solution of DLSprint2022. The task was Automatic Speech Recognition on the Common Voices BN dataset. The model we used was wav2vec2.
DSPy: The framework for programming—not prompting—foundation models
Bangla Grammar Error Detection with T5 transformer
A simple class override that allows ensembling T5 models from huggingface/transformers during inference. Works with trainer().
Solve puzzles. Learn CUDA.
LLM training code for MosaicML foundation models
An autoregressive character-level language model for making more things
Efficient heuristic solver for the Cluster Editing problem
About Me
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Using UNET to remove reflection from images. Pedagogical model, not intended to be competitive.
This repository provides starter code and recommendations for starting the VIP CUP 2023 competition.
This repository provides starter code and recommendations for starting the VIP CUP 2023 competition.
PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)