SurveyX
Academic Survey Paper Generation.
Stars: 198
SurveyX is an advanced academic survey automation system that leverages Large Language Models (LLMs) to generate high-quality, domain-specific academic papers and surveys. Users can request comprehensive academic papers or surveys tailored to specific topics by providing a paper title and keywords for literature retrieval. The system streamlines academic research by automating paper creation, saving users time and effort in compiling research content.
README:
✨Welcome to SurveyX! This GitHub repository serves as a channel for users to submit requests for paper generation based on specific topics or domains.📚
🚀 We're actively developing a full-featured product with a sleek graphical interface!
⭐ Star this repo to stay updated and be the first to know about our progress and release announcements!
💡 Your support means everything to us as we work to bring this innovative solution to life. Stay tuned for more updates!
SurveyX is an advanced academic survey automation system that leverages the power of Large Language Models (LLMs) to generate high-quality, domain-specific academic papers and surveys.🚀
By simply providing a paper title and keywords for literature retrieval, users can request comprehensive academic papers or surveys tailored to specific topics.
If you're curious about how SurveyX works or want to understand the underlying technology and methodology, feel free to check out our 📑website, where we provide an in-depth explanation of the system's architecture, data processing methods, and experimental results.
This GitHub repository is designed to provide a platform where users can request the generation of high-quality, domain-specific academic surveys by simply submitting an issue. The main purpose of this repository is to allow users to easily create and receive tailored academic surveys or papers, which are generated using SurveyX📄
By submitting an issue with a paper title and keywords for literature search, users can quickly generate a comprehensive review paper or survey on a specific topic. This process streamlines academic research by automating paper creation, saving users time and effort in compiling research content. 📚💡
To request a paper, create a new issue with the following details:
- Paper Title: Provide the title of the paper you need.
- Keywords for Literature Search: Provide keywords separated by commas that will help retrieve relevant literature and guide the content generation (e.g. "AI in healthcare, climate change impact on agriculture, ethical implications of AI").
- Your email(optional): Please provide your email address so that we can notify you promptly once the paper is ready.
Title: Controllable text generation of LLM: A Survey
Keywords: AI, healthcare, ethical implications, technology adoption, AI-driven diagnostics
Email: [email protected]
Once your request is submitted, the generated paper will be placed in the user requests folder. Please allow 1-2 business days for processing and generation. ⏳
| Title | Keywords |
|---|---|
| From BERT to GPT-4: A Survey of Architectural Innovations in Pre-trained Language Models | Transformer, BERT, GPT-3, self-attention, masked language modeling, cross-lingual transfer, model scaling |
| Unsupervised Cross-Lingual Word Embedding Alignment: Techniques and Applications | low-resource NLP, few-shot learning, data augmentation, unsupervised alignment, synthetic corpora, NLLB, zero-shot transfer |
| Vision-Language Pre-training: Architectures, Benchmarks, and Emerging Trends | multimodal learning, CLIP, Whisper, cross-modal retrieval, modality fusion, video-language models, contrastive learning |
| Efficient NLP at Scale: A Review of Model Compression Techniques | model compression, knowledge distillation, pruning, quantization, TinyBERT, edge computing, latency-accuracy tradeoff |
| Domain-Specific NLP: Adapting Models for Healthcare, Law, and Finance | domain adaptation, BioBERT, legal NLP, clinical text analysis, privacy-preserving NLP, terminology extraction, few-shot domain transfer |
| Attention Heads of Large Language Models: A Survey | attention head, attention mechanism, large language model, LLM,transformer architecture, neural networks, natural language processing |
| Controllable Text Generation for Large Language Models: A Survey | controlled text generation, text generation, large language model, LLM,natural language processing |
| A survey on evaluation of large language models | evaluation of large language models,large language models assessment, natural language processing, AI model evaluation |
| Large language models for generative information extraction: a survey | information extraction, large language models, LLM,natural language processing, generative AI, text mining |
| Internal consistency and self feedback of LLM | Internal consistency, self feedback, large language model, LLM,natural language processing, model evaluation, AI reliability |
| Review of Multi Agent Offline Reinforcement Learning | multi agent, offline policy, reinforcement learning,decentralized learning, cooperative agents, policy optimization |
| Reasoning of large language model: A survey | reasoning of large language models, large language models, LLM,natural language processing, AI reasoning, transformer models |
| Hierarchy Theorems in Computational Complexity: From Time-Space Tradeoffs to Oracle Separations | P vs NP, NP-completeness, polynomial hierarchy, space complexity, oracle separation, Cook-Levin theorem |
| Classical Simulation of Quantum Circuits: Complexity Barriers and Implications | BQP, quantum supremacy, Shor's algorithm, post-quantum cryptography, QMA, hidden subgroup problem |
| Kernelization: Theory, Techniques, and Limits | fixed-parameter tractable (FPT), kernelization, treewidth, W-hierarchy, ETH (Exponential Time Hypothesis), parameterized reduction |
| Optimal Inapproximability Thresholds for Combinatorial Optimization Problems | PCP theorem, approximation ratio, Unique Games Conjecture, APX-hardness, gap-preserving reduction, LP relaxation |
| Hardness in P: When Polynomial Time is Not Enough | SETH (Strong Exponential Time Hypothesis), 3SUM conjecture, all-pairs shortest paths (APSP), orthogonal vectors problem, fine-grained reduction, dynamic lower bounds |
| Consistency Models in Distributed Databases: From ACID to NewSQL | CAP theorem, ACID vs BASE, Paxos/Raft, Spanner, NewSQL, sharding, linearizability |
| Cloud-Native Databases: Architectures, Challenges, and Future Directions | cloud databases, AWS Aurora, Snowflake, storage-compute separation, auto-scaling, pay-per-query, multi-tenancy |
| Graph Database Systems: Storage Engines and Query Optimization Techniques | graph traversal, Neo4j, SPARQL, property graph, subgraph matching, RDF triplestore, Gremlin |
| Real-Time Aggregation in TSDBs: Techniques for High-Cardinality Data | time-series data, InfluxDB, Prometheus, downsampling, time windowing, high-cardinality indexing, stream processing |
| Self-Driving Databases: A Survey of AI-Powered Autonomous Management | autonomous databases, learned indexes, query optimization, Oracle AutoML, workload forecasting, anomaly detection |
| Multi-Model Databases: Integrating Relational, Document, and Graph Paradigms | multi-model database, MongoDB, ArangoDB, JSONB, unified query language, schema flexibility, polystore |
| Vector Databases for AI: Efficient Similarity Search and Retrieval-Augmented Generation | vector database, FAISS, Milvus, ANN search, embedding indexing, RAG (Retrieval-Augmented Generation), HNSW |
| Software-Defined Networking: Evolution, Challenges, and Future Scalability | OpenFlow, control plane/data plane separation, NFV orchestration, network slicing, P4 language, OpenDaylight, scalability bottlenecks |
| Beyond 5G: Architectural Innovations for Terahertz Communication and Network Slicing | network slicing, MEC (Multi-access Edge Computing), beamforming, mmWave, URLLC (Ultra-Reliable Low-Latency Communication), O-RAN, energy efficiency |
| IoT Network Protocols: A Comparative Study of LoRaWAN, NB-IoT, and Thread | LPWAN, LoRa, ZigBee 3.0, 6LoWPAN, TDMA scheduling, RPL routing, device density management |
| Edge Caching in Content Delivery Networks: Algorithms and Economic Incentives | CDN, Akamai, cache replacement policies, DASH (Dynamic Adaptive Streaming), QoE optimization, edge server placement, bandwidth cost reduction |
| A survey on flow batteries | battery electrolyte formulation |
| Research on battery electrolyte formulation | flow batteries |
| Title | Keywords |
|---|---|
| Think and Draw! A survey on Vision-MLLMs that can understand and generate | vision-language models, multimodal learning, generative AI |
| A Survey of new intent detection and discovery for Conversational Understanding | Out-of-domain Detection， New Intent Discovery， Generalized Category Discovery |
| A Survey of Segment Anything Model (SAM) in Medical Imaging: Advances in Vision Foundation Models | Segment Anything Model (SAM), Medical Image Segmentation, Vision Foundation Models, Prompt Engineering, Efficient Fine-Tuning |
| A Survey of joint extraction of medical entities and relations | Medical Entity Recognition, Joint Extraction, Relation Extraction, Biomedical Text Mining, Deep Learning |
| Reinforcement Learning for Large Language Models: Methods, Challenges, and Applications | Large Language Models, Reinforcement Learning, RLHF, Reward Modeling, AI Alignment, Fine-Tuning, Prompt Optimization, Self-Supervised Learning, Model-based RL, Meta-Reinforcement Learning, AI Agents, Multi-Agent Reinforcement Learning (MARL), Curriculum Learning, Few-Shot Learning, Continual Learning, Adaptive Learning, Human-in-the-Loop Learning |
| Process Reward Models for LLM Reasoning | Process Reward Model, Reasoning, Large Language Model |
| Novel Multiferroics coupling ferroelectricity with Skyrmion, altermagnetism or Ferrovalley | Multiferroic, Skyrmion, altermagnetism, Ferrovalley, ferroelectricity |
| Comparative study of cardiac markers CKMB and LDH in pericardial fluid for postmortem diagnosis | Forensic medicine, Postmortem diagnosis, Sample timing, Cardiac muscle fibers, Myocardial infarction |
| A Multi-dimensional Perspective on Hybrid Human-Artificial Intelligence: Opportunities and Challenges in the Era of Large Language Models | Hybrid Human-Artificial Intelligence, Large Language Models, Deep Learning, Reinforcement learning |
| Multimodal fusion with Multimodal Temporal Data for Clinical prediction | Multimodal temporal data, Deep learning in healthcare, Clinical decision support systems (CDSS), Temporal alignment, Uncertainty quantification, Reinforcement learning in medicine, Medical image sequence analysis, Interpretable machine learning |
| A Survey on Unit Test Case Generation | Unit Test, Unit Testing, Large Language Model |
| Enhancing Blind Image Deblurring Robustness Against Saturated Images | Blind Deblurring, Impulse Noise Detection, Non-convex Optimization, Saturated Images |
| A Comprehensive Survey of Token Compression for Vision Transformers, Vision Generation, Large Language Models, Large Multimodal Models | Token Compression, Token Pruning, Token Reduction, Token Merging, Accelerating Diffusion Transformers, Vision-Language Models, Image Generation, Video Generation, Vision Transformers. Large Language Models, Acceleration, Efficient Large Multimodal Models |
| Automatic Detection of Age-Related Macular Degeneration in Mice Using OCT Images and Deep Neural Networks | Age-Related Macular Degeneration (AMD), Optical Coherence Tomography (OCT), Convolutional Neural Networks (CNN), VGG16, ResNet, Deep Learning,nnUNet, Biomedical Image Analysis, Classification Models, Artificial Intelligence in Ophthalmology |
| Deep learning for depression recognition with multimodal : A Review | Depression, Multimodal methods, Emotion recognition, Deep learning, Unimodal methods, Psychological abnormalities |
| Paper on the PET image reconstruction, focused on the methods in the generation AI era, comparing deterministic and generative methods | AI, medical imaging, PET, reconstruction, generative model |
| LLM-based Autonomous Agents Empowered Social Sciences: From a Social Simulation Perspective | large language models, LLM-based agent, social simulation, social science, social intelligence, world simulation |
| Multi-modal Knowledge Graph Completion and Its Application: A Comprehensive Survey | Knowledge Graphs, Multi-modal Knowledge Graph Completion, Multi-modal Fusion, Knowledge Graph Application, Link Prediction |
| A Fingerprint Localization Algorithm Based on Low-Density Tags | Indoor location, Fingerprint location |
| Document Understanding with Multi-modal Large Language Model : A Survey | Document Understanding, Multi-modal Large Language, Document AI, Document VQA |
| Towards human-like multimodal perception and cognition: A review of challenges and future prospects of MLLM multimodal alignment. | nan |
| Temporal Question Answering: A survey | Large Language Models, Temproal Knowledge Graph, Retrieval-Augmented Generation |
| Automated Material Synthesis Laboratory: A Survey | Robotics, AI, LLM, Autonomous laboratory, Active learning, Machine learning, Deep learning, High-throughput, DFT, Materials science, Chemistry |
| Emergent Abilities in Large Language Models: a Survey | Large Language Models, Emergent Abilities |
| A Comprehensive Survey of Text-to-Speech Synthesis: Technologies, Methodologies, and Applications | Text-to-speech (TTS) systems, speech synthesis architectures, parametric TTS, neural TTS, deep learning for speech synthesis, waveform generation, vocoders, prosody modeling, multilingual speech synthesis, real-time TTS, voice conversion, zero-shot TTS, evaluation metrics for TTS |
| From Signal to Parameter: A Complete Technical Guide to All PPG-Derived Measurements and Their Extraction Methods | Photoplethysmography, Biosensors, Signal processing, Optical monitoring, Vital signs, Biomedical engineering |
| The Potential and Challenges of Artificial Intelligence in Policing : A survey | AI, Policing, Law enforcement, Crime prevention, Surveillance, Predictive analytics, Ethics, Bias, Decision-making, Legal implications |
| Application of multi-modal large-scale model in robot orientation | Multi-modal large model, robot, Reinforcement learning, embodied intelligence,Hybrid model of experts |
| Application Research on fatigue detection using face recognition technology | Fatigue detection, face recognition, deep learning image processing |
| Deep Learning Applications in Single-cell Omics for Colorectal Cancer Research | Deep Learning, Single-cell Omics, Colorectal Cancer, Bioinformatics |
| Prediction of shear strength parameters of granite residual soil based on machine learning | granite residual soil, machine learning, shear strength parameters, data processing, model interpretability |
| Quantifying the Use and Impact of Machine Learning in Lung Sound Classification and Recognition | Machine learning, lung sounds, respiratory sound recognition, Pulmonary sound analysis,Feature extraction |
| Process Reward Models for Large Language Model Reasoning: A Comprehensive Review | Large Language Models, process supervision, step-level supervision, process reward model (PRM), step-level reward, process verifier, step-by-step verifier, Reinforcement Learning |
| A Comprehensive Survey of Low-Rank Adaptation (LoRA) in Large Language Models, Vision Generation, Large Multimodal Models and Beyond: Methods, Theories, Applications and Opportunities | LoRA (Low-Rank Adaptation), LoRA Hyperparameters, LoRA with Pruning, Multimodal learning, Vision-Language Models |
| Symbolic Regression: Architectures, Benchmarks, and Emerging Trends | symbolic regression, sparse regression, equation discovery, genetic algorithms, Reinforcement Learning, large language models |
| EEG Foundation Model: A Survey | AI, EEG, Foundation model, Deep Learning, Time Series, BCI |
| PCB defect detection: a survey | PCB defect detection |
| Diffusion Models in object detection: A survey. | Diffusion Models, object detection, object recognition |
| The Impact of AI Image Recognition Technology in Sports Fitness Training on Customer Participation and Repurchase Intention: A Survey | Image Recognition, Sports Fitness Training, Customer Participation, Repurchase Intention |
| A review of deep-learning-based approaches for Positron Emission Tomography Reconstrution | deep learning, Positron Emission Tomography, PET image reconstrution |
| Finetuning Mixture of Experts LLMs: Methods, Applications, Risks and Opportunities | LLMs, Large Language Models, Mixture of Experts, training, Continued Pretraining, Finetuning, SFT, Supervised Finetuning, MOE, Expert router, LORA, PEFT, Full Finetuning, retraining experts, finetuning experts |
| Progress and Prospects of Research on the Whole Stage of Coal Spontaneous Combustion | spontaneous combustion, comprehensive prevention and control throughout all stages, machine learning, artificial intelligence, informatization, monitoring and early warning, fire prevention and control, emergency rescue |
| a survey on large language model for debugging the programs | Autonomous agent, Large language model, Debug, Debug like a Human, Human in the loop, Human-Computer Interaction, Automatic Program Repair, self-debug, testing |
| Deepfake Detection Guided by data augmentation: A Survey | deepfake, data augmentation, inverse graphics, classifier, computer vision, faceswap |
| A Comprehensive Survey of Facial Landmark Detection | facial landmark detection, face alignment, 3d facial landmarks, face morphing, facial retouching, virtual makeup |
| A Comprehensive Review of Sepsis: Mechanisms, Clinical Management, and MIMIC Database-Driven Insights | Sepsis, mimic database, data mining, critical care, pathophysiology, clinical management, prognostic indicators, big data analytics, machine learning, deep learning, evidence-based medicine |
Please cite us if you find this project helpful for your project/paper:
@misc{liang2025surveyxacademicsurveyautomation,
title={SurveyX: Academic Survey Automation via Large Language Models},
author={Xun Liang and Jiawei Yang and Yezhaohui Wang and Chen Tang and Zifan Zheng and Simin Niu and Shichao Song and Hanyu Wang and Bo Tang and Feiyu Xiong and Keming Mao and Zhiyu li},
year={2025},
eprint={2502.14776},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2502.14776},
}
- Our retrieval engine may not have access to many papers that require commercial licensing. If your research topic requires papers from sources other than arXiv, the quality and comprehensiveness of the generated papers may be affected due to limitations in our retrieval scope.
- We currently only support the generation of English academic survey generation. Support for other languages is not available.
SurveyX uses advanced language models to assist with the generation of academic papers. However, it is important to note that the generated content is a tool for research assistance. Users should verify the accuracy of the generated papers, as SurveyX cannot guarantee full compliance with academic standards.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for SurveyX
Similar Open Source Tools
SurveyX
SurveyX is an advanced academic survey automation system that leverages Large Language Models (LLMs) to generate high-quality, domain-specific academic papers and surveys. Users can request comprehensive academic papers or surveys tailored to specific topics by providing a paper title and keywords for literature retrieval. The system streamlines academic research by automating paper creation, saving users time and effort in compiling research content.
Pearl
Pearl is a production-ready Reinforcement Learning AI agent library open-sourced by the Applied Reinforcement Learning team at Meta. It enables researchers and practitioners to develop Reinforcement Learning AI agents that prioritize cumulative long-term feedback over immediate feedback and can adapt to environments with limited observability, sparse feedback, and high stochasticity. Pearl offers a diverse set of unique features for production environments, including dynamic action spaces, offline learning, intelligent neural exploration, safe decision making, history summarization, and data augmentation.
MMLU-Pro
MMLU-Pro is an enhanced benchmark designed to evaluate language understanding models across broader and more challenging tasks. It integrates more challenging, reasoning-focused questions and increases answer choices per question, significantly raising difficulty. The dataset comprises over 12,000 questions from academic exams and textbooks across 14 diverse domains. Experimental results show a significant drop in accuracy compared to the original MMLU, with greater stability under varying prompts. Models utilizing Chain of Thought reasoning achieved better performance on MMLU-Pro.
taranis-ai
Taranis AI is an advanced Open-Source Intelligence (OSINT) tool that leverages Artificial Intelligence to revolutionize information gathering and situational analysis. It navigates through diverse data sources like websites to collect unstructured news articles, utilizing Natural Language Processing and Artificial Intelligence to enhance content quality. Analysts then refine these AI-augmented articles into structured reports that serve as the foundation for deliverables such as PDF files, which are ultimately published.
aiops-modules
AIOps Modules is a collection of reusable Infrastructure as Code (IAC) modules that work with SeedFarmer CLI. The modules are decoupled and can be aggregated using GitOps principles to achieve desired use cases, removing heavy lifting for end users. They must be generic for reuse in Machine Learning and Foundation Model Operations domain, adhering to SeedFarmer Guide structure. The repository includes deployment steps, project manifests, and various modules for SageMaker, Mlflow, FMOps/LLMOps, MWAA, Step Functions, EKS, and example use cases. It also supports Industry Data Framework (IDF) and Autonomous Driving Data Framework (ADDF) Modules.
MNN
MNN is a highly efficient and lightweight deep learning framework that supports inference and training of deep learning models. It has industry-leading performance for on-device inference and training. MNN has been integrated into various Alibaba Inc. apps and is used in scenarios like live broadcast, short video capture, search recommendation, and product searching by image. It is also utilized on embedded devices such as IoT. MNN-LLM and MNN-Diffusion are specific runtime solutions developed based on the MNN engine for deploying language models and diffusion models locally on different platforms. The framework is optimized for devices, supports various neural networks, and offers high performance with optimized assembly code and GPU support. MNN is versatile, easy to use, and supports hybrid computing on multiple devices.
Awesome-LLM
Awesome-LLM is a curated list of resources related to large language models, focusing on papers, projects, frameworks, tools, tutorials, courses, opinions, and other useful resources in the field. It covers trending LLM projects, milestone papers, other papers, open LLM projects, LLM training frameworks, LLM evaluation frameworks, tools for deploying LLM, prompting libraries & tools, tutorials, courses, books, and opinions. The repository provides a comprehensive overview of the latest advancements and resources in the field of large language models.
MeloTTS
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. It supports various languages including English (American, British, Indian, Australian), Spanish, French, Chinese, Japanese, and Korean. The Chinese speaker also supports mixed Chinese and English. The library is fast enough for CPU real-time inference and offers features like using without installation, local installation, and training on custom datasets. The Python API and model cards are available in the repository and on HuggingFace. The community can join the Discord channel for discussions and collaboration opportunities. Contributions are welcome, and the library is under the MIT License. MeloTTS is based on TTS, VITS, VITS2, and Bert-VITS2.
awesome-sound_event_detection
The 'awesome-sound_event_detection' repository is a curated reading list focusing on sound event detection and Sound AI. It includes research papers covering various sub-areas such as learning formulation, network architecture, pooling functions, missing or noisy audio, data augmentation, representation learning, multi-task learning, few-shot learning, zero-shot learning, knowledge transfer, polyphonic sound event detection, loss functions, audio and visual tasks, audio captioning, audio retrieval, audio generation, and more. The repository provides a comprehensive collection of papers, datasets, and resources related to sound event detection and Sound AI, making it a valuable reference for researchers and practitioners in the field.
GenAIExamples
This project provides a collective list of Generative AI (GenAI) and Retrieval-Augmented Generation (RAG) examples such as chatbot with question and answering (ChatQnA), code generation (CodeGen), document summary (DocSum), etc.
azure-search-vector-samples
This repository provides code samples in Python, C#, REST, and JavaScript for vector support in Azure AI Search. It includes demos for various languages showcasing vectorization of data, creating indexes, and querying vector data. Additionally, it offers tools like Azure AI Search Lab for experimenting with AI-enabled search scenarios in Azure and templates for deploying custom chat-with-your-data solutions. The repository also features documentation on vector search, hybrid search, creating and querying vector indexes, and REST API references for Azure AI Search and Azure OpenAI Service.
generative-ai-cdk-constructs
The AWS Generative AI Constructs Library is an open-source extension of the AWS Cloud Development Kit (AWS CDK) that provides multi-service, well-architected patterns for quickly defining solutions in code to create predictable and repeatable infrastructure, called constructs. The goal of AWS Generative AI CDK Constructs is to help developers build generative AI solutions using pattern-based definitions for their architecture. The patterns defined in AWS Generative AI CDK Constructs are high level, multi-service abstractions of AWS CDK constructs that have default configurations based on well-architected best practices. The library is organized into logical modules using object-oriented techniques to create each architectural pattern model.
data-prep-kit
Data Prep Kit is a community project aimed at democratizing and speeding up unstructured data preparation for LLM app developers. It provides high-level APIs and modules for transforming data (code, language, speech, visual) to optimize LLM performance across different use cases. The toolkit supports Python, Ray, Spark, and Kubeflow Pipelines runtimes, offering scalability from laptop to datacenter-scale processing. Developers can contribute new custom modules and leverage the data processing library for building data pipelines. Automation features include workflow automation with Kubeflow Pipelines for transform execution.
langkit
LangKit is an open-source text metrics toolkit for monitoring language models. It offers methods for extracting signals from input/output text, compatible with whylogs. Features include text quality, relevance, security, sentiment, toxicity analysis. Installation via PyPI. Modules contain UDFs for whylogs. Benchmarks show throughput on AWS instances. FAQs available.
NSMusicS
NSMusicS is a local music software that is expected to support multiple platforms with AI capabilities and multimodal features. The goal of NSMusicS is to integrate various functions (such as artificial intelligence, streaming, music library management, cross platform, etc.), which can be understood as similar to Navidrome but with more features than Navidrome. It wants to become a plugin integrated application that can almost have all music functions.
For similar tasks
SurveyX
SurveyX is an advanced academic survey automation system that leverages Large Language Models (LLMs) to generate high-quality, domain-specific academic papers and surveys. Users can request comprehensive academic papers or surveys tailored to specific topics by providing a paper title and keywords for literature retrieval. The system streamlines academic research by automating paper creation, saving users time and effort in compiling research content.
For similar jobs
Perplexica
Perplexica is an open-source AI-powered search engine that utilizes advanced machine learning algorithms to provide clear answers with sources cited. It offers various modes like Copilot Mode, Normal Mode, and Focus Modes for specific types of questions. Perplexica ensures up-to-date information by using SearxNG metasearch engine. It also features image and video search capabilities and upcoming features include finalizing Copilot Mode and adding Discover and History Saving features.
KULLM
KULLM (구름) is a Korean Large Language Model developed by Korea University NLP & AI Lab and HIAI Research Institute. It is based on the upstage/SOLAR-10.7B-v1.0 model and has been fine-tuned for instruction. The model has been trained on 8×A100 GPUs and is capable of generating responses in Korean language. KULLM exhibits hallucination and repetition phenomena due to its decoding strategy. Users should be cautious as the model may produce inaccurate or harmful results. Performance may vary in benchmarks without a fixed system prompt.
MMMU
MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).
1filellm
1filellm is a command-line data aggregation tool designed for LLM ingestion. It aggregates and preprocesses data from various sources into a single text file, facilitating the creation of information-dense prompts for large language models. The tool supports automatic source type detection, handling of multiple file formats, web crawling functionality, integration with Sci-Hub for research paper downloads, text preprocessing, and token count reporting. Users can input local files, directories, GitHub repositories, pull requests, issues, ArXiv papers, YouTube transcripts, web pages, Sci-Hub papers via DOI or PMID. The tool provides uncompressed and compressed text outputs, with the uncompressed text automatically copied to the clipboard for easy pasting into LLMs.
gpt-researcher
GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks. It can produce detailed, factual, and unbiased research reports with customization options. The tool addresses issues of speed, determinism, and reliability by leveraging parallelized agent work. The main idea involves running 'planner' and 'execution' agents to generate research questions, seek related information, and create research reports. GPT Researcher optimizes costs and completes tasks in around 3 minutes. Features include generating long research reports, aggregating web sources, an easy-to-use web interface, scraping web sources, and exporting reports to various formats.
ChatTTS
ChatTTS is a generative speech model optimized for dialogue scenarios, providing natural and expressive speech synthesis with fine-grained control over prosodic features. It supports multiple speakers and surpasses most open-source TTS models in terms of prosody. The model is trained with 100,000+ hours of Chinese and English audio data, and the open-source version on HuggingFace is a 40,000-hour pre-trained model without SFT. The roadmap includes open-sourcing additional features like VQ encoder, multi-emotion control, and streaming audio generation. The tool is intended for academic and research use only, with precautions taken to limit potential misuse.
HebTTS
HebTTS is a language modeling approach to diacritic-free Hebrew text-to-speech (TTS) system. It addresses the challenge of accurately mapping text to speech in Hebrew by proposing a language model that operates on discrete speech representations and is conditioned on a word-piece tokenizer. The system is optimized using weakly supervised recordings and outperforms diacritic-based Hebrew TTS systems in terms of content preservation and naturalness of generated speech.
do-research-in-AI
This repository is a collection of research lectures and experience sharing posts from frontline researchers in the field of AI. It aims to help individuals upgrade their research skills and knowledge through insightful talks and experiences shared by experts. The content covers various topics such as evaluating research papers, choosing research directions, research methodologies, and tips for writing high-quality scientific papers. The repository also includes discussions on academic career paths, research ethics, and the emotional aspects of research work. Overall, it serves as a valuable resource for individuals interested in advancing their research capabilities in the field of AI.