X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsense reasoning, and cross-modal retrieval).
- image-captioning
- video-captioning
- vision-and-language
- pretraining
PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".
Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
- pytorch
- imagenet
- convolutional-neural-networks
- cvpr2020
[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
Untitled Goose Tool is a robust and flexible hunt and incident response tool that adds novel authentication and data gathering methods in order to run a full investigation against a customer’s Azure Active Directory (AzureAD), Azure, and M365 environments.
A system of bots that collects clips automatically via custom made filters, lets you easily browse these clips, and puts them together into a compilation video ready to be uploaded straight to any social media platform. Full VPS support is provided, along with an accounts system so multiple users can use the bot at once. This bot is split up into three separate programs. The server. The client. The video generator. These programs perform different functions that when combined creates a very powerful system for auto generating compilation videos.
[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
- foundation-models
- lmm
- vision-and-language
- vision-language-model
Situational Awareness Server compatible with TAK clients
Label images and video for Computer Vision applications
The open, local take on Jev: typed decisions from an LLM, without generating a single token
The repository host gives no description.
Helps working with singletons - things like global settings that you want to edit from the admin site.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
Scientific Inkscape: Inkscape extensions for figure resizing and exporting
Local MCP work notes with persistent sessions, decisions, evidence and resumable tasks.
A collection of implementations of deep domain adaptation algorithms
- pytorch
- deep-transfer-learning
- domain-adaptation
- transfer-learning
Irregular methods on regular expressions
Fuzzy abbreviations, support for preprocessors (Sass, Less, Stylus) and a lot of other features in easily configurable set of tools for writing CSS faster
- sublime-text-3
- sublime-package
- snippets
- abbreviations
The samples provided in AWS Health Tools can help users to build automation and customized alerting in response to AWS Health events.
Geospatial extensions for Polars
3D Gaussian Splatting for Real-Time Radiance Field Rendering - Detailed Windows Install & Usage Instructions
Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.
FAME Automates Malware Evaluation
Benchmark for different operations in pandas against various dataframe sizes.