clip

Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)

Code for "Dual-Level Adaptive Incongruity-Enhanced Model for Multimodal Sarcasm Detection".

[ICLR 2026] - Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery

The AI Radiologist You Can Chat With

Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.

Semantic alignment of astronomical data with natural language using multi-modal models. (Jax) Code associated with https://arxiv.org/abs/2403.08851 (COLM 2023).

Collection of OSS models that are containerized into a serving container

Finalist at Brainhack TIL 2024: Team 12000SGDPLUSHIE

An impelementation of image search engine using CLIP (Contrastive Language-Image Pre-Training

SAM + CLIP + DIFFUSION for image to edit objects in images using plain text

Pytorch Implementation of CLIP-Lite | Accepted at AISTATS 2023

🧠 Multimodal Retrieval-Augmented Generation that "weaves" together text and images seamlessly. 🪡

AI-powered fashion visual search and personalized styling assistant using CLIP, FAISS, and Gemma-3B in Streamlit. Search visually similar fashion items, simulate user history, and generate outfit suggestions using LLMs.

Exploring Visual Interpretability for Contrastive Language-Image Pretraining

[ICCV 2025] Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP

[ACMMM'24] MoBA: Mixture of Bi-directional Adapter for Multi-modal Sarcasm Detection

ComfyUI nodes useful to Tweak SDXL, Illustrious, and NAI models by adjusting specific 'slices'. These nodes break the U-Net and CLIP into areas of application (like Style, Lighting, Word Logic...) and use sliders to boost or lower the intensity of any of those sections without training.

Codebase for the paper titled 'A Shared Encoder Approach to Multimodal Representation Learning'