Best AI tools for< Reproduce Paper Results >

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

Comet ML is an extensible, fully customizable machine learning platform that aims to move ML forward by supporting productivity, reproducibility, and collaboration. It integrates with existing infrastructure and tools to manage, visualize, and optimize models from training runs to production monitoring. Users can track and compare training runs, create a model registry, and monitor models in production all in one platform. Comet's platform can be run on any infrastructure, enabling users to reshape their ML workflow and bring their existing software and data stack.

Jam is a bug-tracking tool that helps developers reproduce and debug issues quickly and easily. It automatically captures all the information engineers need to debug, including device and browser information, console logs, network logs, repro steps, and backend tracing. Jam also integrates with popular tools like GitHub, Jira, Linear, Slack, ClickUp, Asana, Sentry, Figma, Datadog, Gitlab, Notion, and Airtable. With Jam, developers can save time and effort by eliminating the need to write repro steps and manually collect information. Jam is used by over 90,000 developers and has received over 150 positive reviews.

Union.ai is an infrastructure platform designed for AI, ML, and data workloads. It offers a scalable MLOps platform that optimizes resources, reduces costs, and fosters collaboration among team members. Union.ai provides features such as declarative infrastructure, data lineage tracking, accelerated datasets, and more to streamline AI orchestration on Kubernetes. It aims to simplify the management of AI, ML, and data workflows in production environments by addressing complexities and offering cost-effective strategies.

ForgeFluencer is an AI application that serves as an essential toolkit for crafting AI influencers and generating consistent and compelling content. It offers a user-friendly platform optimized for desktop and mobile, allowing users to create models, control various aspects of content generation, edit images with AI, and more. With features like Virtual Wardrobe, Pose Controller, and Photo Studio, ForgeFluencer empowers users to elevate their projects with AI-generated content effortlessly.

Sacred is a tool to configure, organize, log and reproduce computational experiments. It is designed to introduce only minimal overhead, while encouraging modularity and configurability of experiments. The ability to conveniently make experiments configurable is at the heart of Sacred. If the parameters of an experiment are exposed in this way, it will help you to: keep track of all the parameters of your experiment easily run your experiment for different settings save configurations for individual runs in files or a database reproduce your results In Sacred we achieve this through the following main mechanisms: Config Scopes are functions with a @ex.config decorator, that turn all local variables into configuration entries. This helps to set up your configuration really easily. Those entries can then be used in captured functions via dependency injection. That way the system takes care of passing parameters around for you, which makes using your config values really easy. The command-line interface can be used to change the parameters, which makes it really easy to run your experiment with modified parameters. Observers log every information about your experiment and the configuration you used, and saves them for example to a Database. This helps to keep track of all your experiments. Automatic seeding helps controlling the randomness in your experiments, such that they stay reproducible.

FabFab is an AI-powered platform that offers unique, one-of-a-kind t-shirts designed by artificial intelligence. The platform combines art, technology, and individuality to create personalized wearable art pieces. FabFab aims to provide a platform for the harmonious coexistence of technology and human uniqueness, challenging conformity and hyper-personalization. Each shirt is part of the broader FabFab art project, where users become part of the creative process by interacting with the AI. The platform is a collective of resilient souls advocating for the evolution of individuality and human consciousness in alignment with AI.

RAGLAB is a modular, research-oriented open-source framework for Retrieval-Augmented Generation (RAG) algorithms. It offers reproductions of 6 existing RAG algorithms and a comprehensive evaluation system with 10 benchmark datasets, enabling fair comparisons between RAG algorithms and easy expansion for efficient development of new algorithms, datasets, and evaluation metrics. The framework supports the entire RAG pipeline, provides advanced algorithm implementations, fair comparison platform, efficient retriever client, versatile generator support, and flexible instruction lab. It also includes features like Interact Mode for quick understanding of algorithms and Evaluation Mode for reproducing paper results and scientific research.

Torch-Pruning (TP) is a library for structural pruning that enables pruning for a wide range of deep neural networks. It uses an algorithm called DepGraph to physically remove parameters. The library supports pruning off-the-shelf models from various frameworks and provides benchmarks for reproducing results. It offers high-level pruners, dependency graph for automatic pruning, low-level pruning functions, and supports various importance criteria and modules. Torch-Pruning is compatible with both PyTorch 1.x and 2.x versions.

LongLLaVA is a tool for scaling multi-modal LLMs to 1000 images efficiently via hybrid architecture. It includes stages for single-image alignment, instruction-tuning, and multi-image instruction-tuning, with evaluation through a command line interface and model inference. The tool aims to achieve GPT-4V level capabilities and beyond, providing reproducibility of results and benchmarks for efficiency and performance.

ML-Bench is a tool designed to evaluate large language models and agents for machine learning tasks on repository-level code. It provides functionalities for data preparation, environment setup, usage, API calling, open source model fine-tuning, and inference. Users can clone the repository, load datasets, run ML-LLM-Bench, prepare data, fine-tune models, and perform inference tasks. The tool aims to facilitate the evaluation of language models and agents in the context of machine learning tasks on code repositories.

Sarathi-Serve is the official OSDI'24 artifact submission for paper #444, focusing on 'Taming Throughput-Latency Tradeoff in LLM Inference'. It is a research prototype built on top of CUDA 12.1, designed to optimize throughput-latency tradeoff in Large Language Models (LLM) inference. The tool provides a Python environment for users to install and reproduce results from the associated experiments. Users can refer to specific folders for individual figures and are encouraged to cite the paper if they use the tool in their work.

This repository provides the official implementation of the paper 'On Embeddings for Numerical Features in Tabular Deep Learning'. It focuses on transforming scalar continuous features into vectors before integrating them into the main backbone of tabular neural networks, showcasing improved performance. The embeddings for continuous features are shown to enhance the performance of tabular DL models and are applicable to various conventional backbones, offering efficiency comparable to Transformer-based models. The repository includes Python packages for practical usage, exploration of metrics and hyperparameters, and reproducing reported results for different algorithms and datasets.

ChatAFL is a protocol fuzzer guided by large language models (LLMs) that extracts machine-readable grammar for protocol mutation, increases message diversity, and breaks coverage plateaus. It integrates with ProfuzzBench for stateful fuzzing of network protocols, providing smooth integration. The artifact includes modified versions of AFLNet and ProfuzzBench, source code for ChatAFL with proposed strategies, and scripts for setup, execution, analysis, and cleanup. Users can analyze data, construct plots, examine LLM-generated grammars, enriched seeds, and state-stall responses, and reproduce results with downsized experiments. Customization options include modifying fuzzers, tuning parameters, adding new subjects, troubleshooting, and working on GPT-4. Limitations include interaction with OpenAI's Large Language Models and a hard limit of 150,000 tokens per minute.

This repository contains the code and data for the paper 'Vision Language Models Are Blind'. It explores the limitations of large language models with vision capabilities (VLMs) in performing basic visual tasks that are easy for humans. The repository presents benchmark results showcasing the poor performance of state-of-the-art VLMs on tasks like counting line intersections, identifying circles, letters, and shapes, and following color-coded paths. The research highlights the challenges faced by VLMs in understanding visual information accurately, drawing parallels to myopia and blindness in human vision.

EvalAI is an open-source platform for evaluating and comparing machine learning (ML) and artificial intelligence (AI) algorithms at scale. It provides a central leaderboard and submission interface, making it easier for researchers to reproduce results mentioned in papers and perform reliable & accurate quantitative analysis. EvalAI also offers features such as custom evaluation protocols and phases, remote evaluation, evaluation inside environments, CLI support, portability, and faster evaluation.

This repository hosts the official code and data artifact for the paper 'Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context'. It introduces Monitor-Guided Decoding (MGD) for code generation using Language Models, where a monitor uses static analysis to guide the decoding. The repository contains datasets, evaluation scripts, inference results, a language server client 'multilspy' for static analyses, and implementation of various monitors monitoring for different properties in 3 programming languages. The monitors guide Language Models to adhere to properties like valid identifier dereferences, correct number of arguments to method calls, typestate validity of method call sequences, and more.

This repository contains a collection of papers and code for the CVPR 2024 conference. The papers cover a wide range of topics in computer vision, including object detection, image segmentation, image generation, and video analysis. The code provides implementations of the algorithms described in the papers, making it easy for researchers and practitioners to reproduce the results and build upon the work of others. The repository is maintained by a team of researchers at the University of California, Berkeley.

This repository contains the official implementation of RPG, a powerful training-free paradigm for text-to-image generation and editing. RPG utilizes proprietary or open-source MLLMs as prompt recaptioner and region planner with complementary regional diffusion. It achieves state-of-the-art results and can generate high-resolution images. The codebase supports diffusers and various diffusion backbones, including SDXL and SD v1.4/1.5. Users can reproduce results with GPT-4, Gemini-Pro, or local MLLMs like miniGPT-4. The repository provides tools for quick start, regional diffusion with GPT-4, and regional diffusion with local LLMs.

Official PyTorch implementation of Wanda (Pruning by Weights and Activations), a simple and effective pruning approach for large language models. The pruning approach removes weights on a per-output basis, by the product of weight magnitudes and input activation norms. The repository provides support for various features such as LLaMA-2, ablation study on OBS weight update, zero-shot evaluation, and speedup evaluation. Users can replicate main results from the paper using provided bash commands. The tool aims to enhance the efficiency and performance of language models through structured and unstructured sparsity techniques.

This repository contains code and results for jailbreaking leading safety-aligned LLMs with simple adaptive attacks. We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. We demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token ``Sure''), potentially with multiple restarts. In this way, we achieve nearly 100% attack success rate---according to GPT-4 as a judge---on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models---that do not expose logprobs---via either a transfer or prefilling attack with 100% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models---a task that shares many similarities with jailbreaking---which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection).

Co-LLM (Collaborative Language Models) is a tool for learning to decode collaboratively with multiple language models. It provides a method for data processing, training, and inference using a collaborative approach. The tool involves steps such as formatting/tokenization, scoring logits, initializing Z vector, deferral training, and generating results using multiple models. Co-LLM supports training with different collaboration pairs and provides baseline training scripts for various models. In inference, it uses 'vllm' services to orchestrate models and generate results through API-like services. The tool is inspired by allenai/open-instruct and aims to improve decoding performance through collaborative learning.

This repository contains code for reproducing experiments on lie detection in black-box LLMs by asking unrelated questions. It includes Q/A datasets, prompts, and fine-tuning datasets for generating lies with language models. The lie detectors rely on asking binary 'elicitation questions' to diagnose whether the model has lied. The code covers generating lies from language models, training and testing lie detectors, and generalization experiments. It requires access to GPUs and OpenAI API calls for running experiments with open-source models. Results are stored in the repository for reproducibility.

TableLLM is a large language model designed for efficient tabular data manipulation tasks in real office scenarios. It can generate code solutions or direct text answers for tasks like insert, delete, update, query, merge, and chart operations on tables embedded in spreadsheets or documents. The model has been fine-tuned based on CodeLlama-7B and 13B, offering two scales: TableLLM-7B and TableLLM-13B. Evaluation results show its performance on benchmarks like WikiSQL, Spider, and self-created table operation benchmark. Users can use TableLLM for code and text generation tasks on tabular data.

This repository contains the implementation of Self-Play of Adversarial Language Game (SPAG) as described in the paper 'Self-playing Adversarial Language Game Enhances LLM Reasoning'. The SPAG involves training Language Models (LLMs) in an adversarial language game called Adversarial Taboo. The repository provides tools for imitation learning, self-play episode collection, and reinforcement learning on game episodes to enhance LLM reasoning abilities. The process involves training models using GPUs, launching imitation learning, conducting self-play episodes, assigning rewards based on outcomes, and learning the SPAG model through reinforcement learning. Continuous improvements on reasoning benchmarks can be observed by repeating the episode-collection and SPAG-learning processes.

ADMET-AI is a platform for ADMET prediction using Chemprop-RDKit models trained on ADMET datasets from the Therapeutics Data Commons. It offers command line, Python API, and web server interfaces for making ADMET predictions on new molecules. The platform can be easily installed using pip and supports GPU acceleration. It also provides options for processing TDC data, plotting results, and hosting a web server. ADMET-AI is a machine learning platform for evaluating large-scale chemical libraries.

This repository contains a minimal, clean code implementation of the Byte Pair Encoding (BPE) algorithm, commonly used in LLM tokenization. The BPE algorithm is "byte-level" because it runs on UTF-8 encoded strings. This algorithm was popularized for LLMs by the GPT-2 paper and the associated GPT-2 code release from OpenAI. Sennrich et al. 2015 is cited as the original reference for the use of BPE in NLP applications. Today, all modern LLMs (e.g. GPT, Llama, Mistral) use this algorithm to train their tokenizers. There are two Tokenizers in this repository, both of which can perform the 3 primary functions of a Tokenizer: 1) train the tokenizer vocabulary and merges on a given text, 2) encode from text to tokens, 3) decode from tokens to text. The files of the repo are as follows: 1. minbpe/base.py: Implements the `Tokenizer` class, which is the base class. It contains the `train`, `encode`, and `decode` stubs, save/load functionality, and there are also a few common utility functions. This class is not meant to be used directly, but rather to be inherited from. 2. minbpe/basic.py: Implements the `BasicTokenizer`, the simplest implementation of the BPE algorithm that runs directly on text. 3. minbpe/regex.py: Implements the `RegexTokenizer` that further splits the input text by a regex pattern, which is a preprocessing stage that splits up the input text by categories (think: letters, numbers, punctuation) before tokenization. This ensures that no merges will happen across category boundaries. This was introduced in the GPT-2 paper and continues to be in use as of GPT-4. This class also handles special tokens, if any. 4. minbpe/gpt4.py: Implements the `GPT4Tokenizer`. This class is a light wrapper around the `RegexTokenizer` (2, above) that exactly reproduces the tokenization of GPT-4 in the tiktoken library. The wrapping handles some details around recovering the exact merges in the tokenizer, and the handling of some unfortunate (and likely historical?) 1-byte token permutations. Finally, the script train.py trains the two major tokenizers on the input text tests/taylorswift.txt (this is the Wikipedia entry for her kek) and saves the vocab to disk for visualization. This script runs in about 25 seconds on my (M1) MacBook. All of the files above are very short and thoroughly commented, and also contain a usage example on the bottom of the file.

キーワードやコンテクストに基づいて、詳細な画像プロンプトを時間軸、文化軸、感情軸、現実と虚構軸など、多角的な視点を取り入れて、あなたのビジョンを忠実に再現します。