Search Results for "research" - Page 3
Sort By:
Showing 112 open source projects for "research"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
LLM-Aided OCR Project
Enhances Tesseract OCR output using LLMs (local or API)
...This AI-assisted correction process helps reconstruct missing characters, fix formatting mistakes, and produce more coherent text outputs. The project is particularly useful for digitizing historical documents, research papers, and scanned materials where traditional OCR often struggles. It also includes tools for processing batches of images or documents, enabling automated document digitization workflows. -
2
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
AgentBench is an open-source benchmark designed to evaluate the capabilities of large language models when used as autonomous agents. Unlike traditional language model benchmarks that focus on static text tasks, AgentBench measures how models perform in interactive environments that require planning, reasoning, and decision-making. The benchmark includes multiple environments that simulate realistic scenarios such as web interaction, database querying, and problem solving tasks. These... -
3
Huatuo-Llama-Med-Chinese
Instruction-tuning LLM with Chinese Medical Knowledge
Huatuo-Llama-Med-Chinese is an open-source project that develops medical-domain large language models by instruction-tuning existing models using Chinese medical knowledge. The project builds specialized models by fine-tuning architectures such as LLaMA, Alpaca-Chinese, and Bloom with curated medical datasets. These datasets are constructed from medical knowledge graphs, academic literature, and question-answer pairs designed to teach models how to respond accurately to healthcare-related... -
4
LlamaGen
Autoregressive Model Beats Diffusion
LlamaGen is an open-source research project that introduces a new approach to image generation by applying the autoregressive next-token prediction paradigm used in large language models to visual generation tasks. Instead of relying on diffusion models, the framework treats images as sequences of tokens that can be generated progressively using transformer architectures similar to those used for text generation. -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
OpenPlanter
Language-model investigation agent with a terminal UI
...It emphasizes automation and extensibility, allowing integration with sensors, environmental data, and control logic for smart cultivation setups. The system is structured to support experimentation and customization, making it suitable for both research and DIY agriculture projects. With its modular Python codebase, users can adapt the platform for different plant types, hardware setups, or automation strategies. Overall, OpenPlanter aims to simplify the creation of programmable, data-driven plant care systems. -
6
Qwen2-Audio
Repo of Qwen2-Audio chat & pretrained large audio language model
Qwen2-Audio is a large audio-language model by Alibaba Cloud, part of the Qwen series. It is trained to accept various audio signal inputs (including speech, sounds, etc.) and perform both voice chat and audio analysis, producing textual responses. It supports two major modes: Voice Chat (interactive voice only input) and Audio Analysis (audio + text instructions), with both base and instruction-tuned models. It is evaluated on many benchmarks (speech recognition, translation, sound... -
7
RecAI
Bridging LLM and Recommender System
RecAI is an open-source research platform developed by Microsoft to explore how large language models can be integrated into modern recommender systems. Traditional recommender systems rely on structured behavioral data such as user interactions and item embeddings, while large language models excel at understanding language and reasoning about user preferences. -
8
FuzzyAI Fuzzer
A powerful tool for automated LLM fuzzing
FuzzyAI is an open-source fuzzing framework designed to test the security and reliability of large language model applications. The tool automates the process of generating adversarial prompts and input variations to identify vulnerabilities such as jailbreaks, prompt injections, or unsafe model responses. It allows developers and security researchers to systematically evaluate the robustness of LLM-based systems by simulating a wide range of malicious or unexpected inputs. The framework can... -
9
RAPTOR
The official implementation of RAPTOR
RAPTOR is a retrieval architecture designed to improve retrieval-augmented generation systems by organizing documents into hierarchical structures that enable more effective context retrieval. Traditional RAG systems typically retrieve small text chunks independently, which can limit a model’s ability to understand broader document context. RAPTOR addresses this limitation by recursively embedding, clustering, and summarizing documents to create a tree-structured hierarchy of information.... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA, short for Mixture of Block Attention, is an open-source research implementation of a novel attention mechanism designed to improve the efficiency of large language models processing extremely long contexts. The architecture adapts ideas from Mixture-of-Experts networks and applies them directly to the attention mechanism of transformer models. Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. ... -
11
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
how-to-optim-algorithm-in-cuda is an open educational repository focused on teaching developers how to optimize algorithms for high-performance execution on GPUs using CUDA. The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations... -
12
Integuru v0
The first AI agent that builds permissionless integrations
...This approach allows developers to automate workflows and build integrations with services that do not provide official APIs or developer tools. The project is designed as a research platform for exploring AI-driven automation and integration generation. -
13
CodeGen
Open-source model for program synthesis
CodeGen is a family of open-source large language models designed specifically for program synthesis and code generation tasks. Developed by Salesforce Research, the models are trained on large datasets containing both natural language and programming language content. This allows them to translate natural language descriptions into functional code across a variety of programming languages. CodeGen supports multi-turn program synthesis, meaning it can generate complex programs through a sequence of prompts that progressively refine the solution. ... -
14
WeClone
One-stop solution for creating your digital avatar from chat history
...By processing large volumes of conversation data, WeClone can build a profile of an individual’s writing tone, vocabulary preferences, and conversational tendencies. Developers can use the resulting model to create chatbots that simulate a specific user’s communication patterns for testing or research purposes. Overall, WeClone explores the idea of digital identity replication through machine learning and conversational modeling. -
15
HN Time Capsule
Analyzing Hacker News discussions from a decade ago in hindsight
...By preserving content that might otherwise be lost to time or buried in the fast-moving flow of new posts, HN Time Capsule becomes both an educational resource and a research tool for community dynamics and tech history. -
16
Coconut
Training Large Language Model to Reason in a Continuous Latent Space
Coconut is the official PyTorch implementation of the research paper “Training Large Language Models to Reason in a Continuous Latent Space.” The framework introduces a novel method for enhancing large language models (LLMs) with continuous latent reasoning steps, enabling them to generate and refine reasoning chains within a learned latent space rather than relying solely on discrete symbolic reasoning. -
17
Youtu-GraphRAG
Vertically Unified Agents for Graph Retrieval-Augmented Reasoning
Youtu-GraphRAG is a research framework developed by Tencent for performing complex reasoning using graph-based retrieval-augmented generation. The system combines knowledge graphs, retrieval mechanisms, and agent-based reasoning into a unified architecture designed to handle knowledge-intensive tasks. Instead of relying solely on text retrieval, the framework organizes information into structured graph schemas that represent entities, relationships, and attributes. -
18
AgentEvolver
Towards Efficient Self-Evolving Agent System
AgentEvolver is an open-source research framework for building self-evolving AI agents powered by large language models. The system focuses on improving the efficiency and scalability of training autonomous agents by allowing them to generate tasks, explore environments, and refine strategies without heavy reliance on manually curated datasets. Its architecture combines reinforcement learning with LLM-driven reasoning mechanisms to guide exploration and learning. -
19
DriveLM
Driving with Graph Visual Question Answering
DriveLM is a research-oriented framework and dataset designed to explore how vision-language models can be integrated into autonomous driving systems. The project introduces a new paradigm called graph visual question answering that structures reasoning about driving scenes through interconnected tasks such as perception, prediction, planning, and motion control. -
20
Sage Chat
Chat with any codebase in under two minutes | Fully local
Sage is an open-source AI developer assistant designed to help engineers understand and work with complex codebases more effectively. The tool functions similarly to an intelligent research agent that can analyze a repository and answer questions about how the software works. Instead of focusing solely on code generation, Sage emphasizes code comprehension, system architecture analysis, and integration guidance. Developers can ask natural language questions about a project, and the system responds with explanations supported by references to the relevant code, documentation, or external technical resources. ... -
21
tldw Server
Your Personal Research Multi-Tool
tldw-server (mirror) is a mirrored distribution of an open-source backend service designed to store, process, and serve summarized information extracted from long pieces of content. The name “tldw” reflects the phrase “too long; didn’t watch,” which refers to tools that condense lengthy videos, articles, or documents into concise summaries. The server component typically acts as the core infrastructure that manages summaries, metadata, and retrieval operations for client applications or user... -
22
ReCall
Learning to Reason with Search for LLMs via Reinforcement Learning
ReCall is an open-source framework designed to train and evaluate language models that can reason through complex problems by interacting with external tools. The project builds on earlier work focused on teaching models how to search for information during reasoning tasks and extends that idea to a broader system where models can call a variety of external tools such as APIs, databases, or computation engines. Instead of relying purely on static knowledge stored inside the model, ReCall... -
23
RLHF-Reward-Modeling
Recipes to train reward model for RLHF
RLHF-Reward-Modeling is an open-source research framework focused on training reward models used in reinforcement learning from human feedback for large language models. In RLHF pipelines, reward models are responsible for evaluating generated responses and assigning scores that guide the model toward outputs that better match human preferences. The repository provides training recipes and implementations for building reward and preference models using modern machine learning frameworks. ... -
24
WFGY 3.0
A tension reasoning engine over 131 S-class problems
WFGY is an experimental open-source reasoning framework designed to improve the reliability and interpretability of large language model outputs through structured reasoning layers. The project introduces a conceptual reasoning engine that analyzes complex problems by identifying semantic compression errors and residual assumptions within a system’s reasoning process. Its architecture treats reasoning failures as measurable signals that can be detected and analyzed rather than simply... -
25
PRIME
Scalable RL solution for advanced reasoning of language models
PRIME is an open-source reinforcement learning framework designed to improve the reasoning capabilities of large language models through process-level rewards rather than relying only on final outputs. The system introduces the concept of process reinforcement through implicit rewards, allowing models to receive feedback on intermediate reasoning steps instead of evaluating only the final answer. This approach helps models learn better reasoning strategies and encourages them to generate...
