DL3DV-10K is a large-scale dataset of real-world scene-level videos with annotations, covering diverse scenes with different levels of reflection, transparency, and lighting. It includes 10,510 multi-view scenes with 51.2 million frames at 4k resolution, and offers benchmark videos for novel view synthesis (NVS) methods. The dataset is designed to facilitate research in deep learning-based 3D vision and provides valuable insights for future research in NVS and 3D representation learning.

MME-RealWorld is a benchmark designed to address real-world applications with practical relevance, featuring 13,366 high-resolution images and 29,429 annotations across 43 tasks. It aims to provide substantial recognition challenges and overcome common barriers in existing Multimodal Large Language Model benchmarks, such as small data scale, restricted data quality, and insufficient task difficulty. The dataset offers advantages in data scale, data quality, task difficulty, and real-world utility compared to existing benchmarks. It also includes a Chinese version with additional images and QA pairs focused on Chinese scenarios.

Merlin is a groundbreaking model capable of generating natural language responses intricately linked with object trajectories of multiple images. It excels in predicting and reasoning about future events based on initial observations, showcasing unprecedented capability in future prediction and reasoning. Merlin achieves state-of-the-art performance on the Future Reasoning Benchmark and multiple existing multimodal language models benchmarks, demonstrating powerful multi-modal general ability and foresight minds.

This is the official repository for 'Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing'. Magpie is a tool designed to synthesize high-quality instruction data at scale by extracting it directly from an aligned Large Language Models (LLMs). It aims to democratize AI by generating large-scale alignment data and enhancing the transparency of model alignment processes. Magpie has been tested on various model families and can be used to fine-tune models for improved performance on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench.

Uncheatable Eval is a tool designed to assess the language modeling capabilities of LLMs on real-time, newly generated data from the internet. It aims to provide a reliable evaluation method that is immune to data leaks and cannot be gamed. The tool supports the evaluation of Hugging Face AutoModelForCausalLM models and RWKV models by calculating the sum of negative log probabilities on new texts from various sources such as recent papers on arXiv, new projects on GitHub, news articles, and more. Uncheatable Eval ensures that the evaluation data is not included in the training sets of publicly released models, thus offering a fair assessment of the models' performance.

GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text components like AI prompts, code snippets, or textual specs against any evaluation metric. It employs LLMs to reflect on system behavior, using feedback from execution and evaluation traces to drive targeted improvements. Through iterative mutation, reflection, and Pareto-aware candidate selection, GEPA evolves robust, high-performing variants with minimal evaluations, co-evolving multiple components in modular systems for domain-specific gains. The repository provides the official implementation of the GEPA algorithm as proposed in the paper titled 'GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning'.

The 'llms' repository is a comprehensive guide on Large Language Models (LLMs), covering topics such as language modeling, applications of LLMs, statistical language modeling, neural language models, conditional language models, evaluation methods, transformer-based language models, practical LLMs like GPT and BERT, prompt engineering, fine-tuning LLMs, retrieval augmented generation, AI agents, and LLMs for computer vision. The repository provides detailed explanations, examples, and tools for working with LLMs.

DataFrame is a C++ analytical library designed for data analysis similar to libraries in Python and R. It allows you to slice, join, merge, group-by, and perform various statistical, summarization, financial, and ML algorithms on your data. DataFrame also includes a large collection of analytical algorithms in form of visitors, ranging from basic stats to more involved analysis. You can easily add your own algorithms as well. DataFrame employs extensive multithreading in almost all its APIs, making it suitable for analyzing large datasets. Key principles followed in the library include supporting any type without needing new code, avoiding pointer chasing, having all column data in contiguous memory space, minimizing space usage, avoiding data copying, using multi-threading judiciously, and not protecting the user against garbage in, garbage out.

This repository contains code for training reward models for Deep Reinforcement Learning-based Reward-modulated Hierarchical Fine-tuning (DRL-based RLHF), Iterative Selection Fine-tuning (Rejection sampling fine-tuning), and iterative Decision Policy Optimization (DPO). The reward models are trained using a Bradley-Terry model based on the Gemma and Mistral language models. The resulting reward models achieve state-of-the-art performance on the RewardBench leaderboard for reward models with base models of up to 13B parameters.

This repository provides a real-world trace dataset of LLM serving workloads for research and academic purposes. The dataset includes two files, BurstGPT.csv with trace data for 2 months including some failures, and BurstGPT_without_fails.csv without any failures. Users can scale the RPS in the trace, model patterns, and leverage the trace for various evaluations. Future plans include updating the time range of the trace, adding request end times, updating conversation logs, and open-sourcing a benchmark suite for LLM inference. The dataset covers 61 consecutive days, contains 1.4 million lines, and is approximately 50MB in size.

AudioSeal is a method for speech localized watermarking, designed with state-of-the-art robustness and detector speed. It jointly trains a generator to embed a watermark in audio and a detector to detect watermarked fragments in longer audios, even in the presence of editing. The tool achieves top-notch detection performance at the sample level, generates minimal alteration of signal quality, and is robust to various audio editing types. With a fast, single-pass detector, AudioSeal surpasses existing models in speed, making it ideal for large-scale and real-time applications.

Woodpecker is a tool designed to correct hallucinations in Multimodal Large Language Models (MLLMs) by introducing a training-free method that picks out and corrects inconsistencies between generated text and image content. It consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Woodpecker can be easily integrated with different MLLMs and provides interpretable results by accessing intermediate outputs of the stages. The tool has shown significant improvements in accuracy over baseline models like MiniGPT-4 and mPLUG-Owl.

BABILong is a generative benchmark designed to evaluate the performance of NLP models in processing long documents with distributed facts. It consists of 20 tasks that simulate interactions between characters and objects in various locations, requiring models to distinguish important information from irrelevant details. The tasks vary in complexity and reasoning aspects, with test samples potentially containing millions of tokens. The benchmark aims to challenge and assess the capabilities of Large Language Models (LLMs) in handling complex, long-context information.

FeedGen is an open-source tool that uses Google Cloud's state-of-the-art Large Language Models (LLMs) to improve product titles, generate more comprehensive descriptions, and fill missing attributes in product feeds. It helps merchants and advertisers surface and fix quality issues in their feeds using Generative AI in a simple and configurable way. The tool relies on GCP's Vertex AI API to provide both zero-shot and few-shot inference capabilities on GCP's foundational LLMs. With few-shot prompting, users can customize the model's responses towards their own data, achieving higher quality and more consistent output. FeedGen is an Apps Script based application that runs as an HTML sidebar in Google Sheets, allowing users to optimize their feeds with ease.

NineRec is a benchmark dataset suite for evaluating transferable recommendation models. It provides datasets for pre-training and transfer learning in recommender systems, focusing on multimodal and foundation model tasks. The dataset includes user-item interactions, item texts in multiple languages, item URLs, and raw images. Researchers can use NineRec to develop more effective and efficient methods for pre-training recommendation models beyond end-to-end training. The dataset is accompanied by code for dataset preparation, training, and testing in PyTorch environment.

MiniCheck is an efficient fact-checking tool designed to verify claims against grounding documents using large language models. It provides a sentence-level fact-checking model that can be used to evaluate the consistency of claims with the provided documents. MiniCheck offers different models, including Bespoke-MiniCheck-7B, which is the state-of-the-art and commercially usable. The tool enables users to fact-check multi-sentence claims by breaking them down into individual sentences for optimal performance. It also supports automatic prefix caching for faster inference when repeatedly fact-checking the same document with different claims.

This repository supports the YOLO series models and provides an AI auto-aiming tool based on YOLO-TensorRT for the game CrossFire. Users can refer to the provided link for compilation and running instructions. The tool includes functionalities for screenshot + inference, mouse movement, and smooth mouse movement. The next goal is to automatically set the optimal PID parameters on the local machine. Developers are welcome to contribute to the improvement of this tool.

DL3DV-10K is a large-scale dataset of real-world scene-level videos with annotations, covering diverse scenes with different levels of reflection, transparency, and lighting. It includes 10,510 multi-view scenes with 51.2 million frames at 4k resolution, and offers benchmark videos for novel view synthesis (NVS) methods. The dataset is designed to facilitate research in deep learning-based 3D vision and provides valuable insights for future research in NVS and 3D representation learning.

AliceVision is a photogrammetric computer vision framework which provides a 3D reconstruction pipeline. It is designed to process images from different viewpoints and create detailed 3D models of objects or scenes. The framework includes various algorithms for feature detection, matching, and structure from motion. AliceVision is suitable for researchers, developers, and enthusiasts interested in computer vision, photogrammetry, and 3D modeling. It can be used for applications such as creating 3D models of buildings, archaeological sites, or objects for virtual reality and augmented reality experiences.

AI-powered visual reasoning tools for broadcast, live streaming, and ProAV professionals. The Visual Reasoning Playground provides 17 ready-to-use tools demonstrating real-world applications of Vision Language Models (VLMs) using Moondream. From PTZ camera auto-tracking to multimodal audio+video automation, the tools offer functionalities like scene description, object detection, gesture control, smart counting, scene analysis, zone monitoring, color matching, multimodal fusion, smart photography, PTZ tracking, tracking comparison, scoreboard extraction, scoreboard OCR, framing assistance, PTZ color tuning, multimodal studio automation, voice triggers, and OBS plugin integration. The tools are designed to streamline tasks in live streaming, broadcast automation, camera control, content creation workflows, security monitoring, and more.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.