Information

Latest AI News

Explore AI Frontiers, Master Industry Trends

AI Daily Brief

Your Daily AI Brief - Never Miss What's Next

Information

AI Product Finder

Smart Product Discovery - Comprehensive Market Intelligence

AI Product Rankings

AI Product Power Rankings - Performance, Buzz & Trends

AI Product Submit

Submit Your AI Product - Amplify Reach & Drive Growth

Tools

AI Tools Directory

Discover The Best AI Websites & Tools

Information

AI Models Finder

Comprehensive AI Models Collection for All Your Development & Research Needs

Model Providers

Discover Trusted AI Model Partners - Guaranteed Reliable Support

Submit Your Model

Submit Your Model Info & Services - Precision Marketing & User Targeting

Tools

Compare LLMs

Multi-Dimensional Large Model Comparison - Find Your Perfect Match

LLM Cost Calculator

Calculate AI Model Costs Accurately - Optimize Your Budget

LLM Arena

Multi-Model Real-Time Evaluation & Quick Output Comparison

Information

MCP Servers

Discover Popular AI-MCP Services - Find Your Perfect Match Instantly

MCP Client

Easy MCP Client Integration - Access Powerful AI Capabilities

MCP Case Tutorials

Master MCP Usage - From Beginner to Expert

MCP Ranking

Top MCP Service Performance Rankings - Find Your Best Choice

MCP Service Submission

Publish & Promote Your MCP Services

Tools

MCP Playground

Test MCP Services Freely - Quick Online Experience

MCP Inspector

Quick MCP Service Testing - Fast Deployment

GEO Services

Achieve Dominant Visibility in AI Search for Your Business or Brand with GEO Services

Datasets

AI Compute

AI Tutorial

PaSa

PaSa is an advanced academic paper search agent driven by large language models, capable of autonomous decision-making and obtaining accurate results.

CommonProductEducationAcademic SearchLarge Language Models

Visit

PaSa is an advanced academic paper search agent developed by ByteDance, based on large language model (LLM) technology. It can autonomously invoke search tools, read papers, and filter relevant references to obtain comprehensive and accurate results for complex academic queries. This technology is optimized through reinforcement learning, trained using the synthetic dataset AutoScholarQuery, and has shown outstanding performance on the real-world query dataset RealScholarQuery, significantly outperforming traditional search engines and GPT-based methods. The main advantages of PaSa lie in its high recall and precision rates, providing researchers with a more efficient academic search experience.

Visit

PaSa Visit Over Time

Monthly Visits

493360068

Bounce Rate

36.08%

Page per Visit

6.1

Visit Duration

00:06:29

PaSa Visit Trend

PaSa Visit Geography

PaSa Traffic Sources

PaSa Alternatives

PaSa — PaSa is an advanced academic paper search agent driven by large language models, capable of autonomous decision-making and obtaining accurate results.

Education

•Academic Search•Large Language Models

762

Models Table — A comprehensive list and information about large language models

Others

•Large Language Models•Machine Learning

366

Search-R1 — A highly efficient reinforcement learning framework for training language models that perform reasoning and call search engines.

Productivity

•Reinforcement Learning•Natural Language Processing

d1 — Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

Productivity

•Reasoning•Reinforcement Learning

Large World Models — Large World Models: Understanding Video and Language

Productivity

• Artificial Intelligence•Machine Learning

1014

DiffusionRL — Large-scale Reinforcement Learning for Diffusion Models

Productivity

•Deep Learning•Image Generation

300

SWE-RL — Enhancing the reasoning capabilities of large language models in open-source software evolution through reinforcement learning.

Programming

•Reinforcement Learning•Large Language Model

300

Tülu 3 405B — Tülu 3 405B is a large-scale open-source language model enhanced through reinforcement learning.

Programming

•Artificial Intelligence•Natural Language Processing

1494

self-adaptive-llms — A real-time adaptive framework for unseen tasks using large language models.

Programming

•Artificial Intelligence•Large Language Models

258

Language Learning Games — AI text adventure games for language learning

Education

•language learning•AI game

666

FP6-LLM — Efficiently serving large language models

Programming

•Large language models•GPU inference

390

Eureka — A human-level reward design algorithm implemented by encoding large language models.

Programming

•Reward Design•Reinforcement Learning

582

RL4VLM — An open-source project that fine-tunes large vision-language models via reinforcement learning to act as decision-making agents.

Programming

•Reinforcement Learning•Vision-Language Models

378

BiTA — Bidirectional Adjustment for Large Language Models

Productivity

•Large Language Models•Plugin

210

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

Programming

•Large Language Model•Reinforcement Learning

984

CuMo — An advanced architecture for extending multimodal large language models (LLMs).

Programming

•Multimodal Learning•Large Language Models

270

VSP-LLM — A framework that combines Visual Speech Processing with Large Language Models

Programming

•Visual Speech Processing•Large Language Models

2706

Nemotron-4-340B-Reward — A multi-dimensional reward model to help build custom large language models.

Programming

•Large Language Model•Synthetic Data Generation

306

Prompt Engineering Guide — A comprehensive guide to prompt engineering for large language models

ChineseSelection

•Prompt Engineering•Large Language Models

1674

Level-Navi Agent-Search — Level-Navi Agent is a ready-to-use framework that utilizes large language models for in-depth query understanding and precise search.

Programming

•Large Language Model•Web Search

252

DataBonsai — A Python library for data cleaning and organization using Large Language Models (LLMs).

Programming

•Data Cleaning•Machine Learning

588

Benchmarking API Performance of Large Language Models — In-depth analysis of key metrics like TTFT and TPS

Others

•Performance Comparison•API Service

1542

EAGLE — Exploration of the design space for multimodal large language models

Programming

•Multimodal Learning•Large Language Models

474

Sonus-1 — Sonus-1: A New Era of Large Language Models (LLMs)

Productivity

•Artificial Intelligence•Large Language Models

1224

Open LLM Leaderboard — A publicly accessible leaderboard of large language models.

Others

•Large Language Models•Performance Comparison

492

Brainglue — Brainglue is an interesting experimental platform for large language models

Programming

•Large Language Models•Generative AI

690

Language REACTOR — A powerful language learning toolkit

Productivity

•Language Learning•Browser Extension

2004

Latest AI News

AI Daily Brief

AI Product Finder

AI Product Rankings

AI Product Submit

AI Tools Directory

AI Models Finder

Model Providers

Submit Your Model

Compare LLMs

LLM Cost Calculator

LLM Arena

MCP Servers

MCP Client

MCP Case Tutorials

MCP Ranking

MCP Service Submission

MCP Playground

MCP Inspector

GEO Services​

PaSa

PaSa Visit Over Time

PaSa Visit Trend

PaSa Visit Geography

PaSa Traffic Sources

PaSa Alternatives

PaSa — PaSa is an advanced academic paper search agent driven by large language models, capable of autonomous decision-making and obtaining accurate results.

Models Table — A comprehensive list and information about large language models

Search-R1 — A highly efficient reinforcement learning framework for training language models that perform reasoning and call search engines.

d1 — Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

Large World Models — Large World Models: Understanding Video and Language

DiffusionRL — Large-scale Reinforcement Learning for Diffusion Models

SWE-RL — Enhancing the reasoning capabilities of large language models in open-source software evolution through reinforcement learning.

Tülu 3 405B — Tülu 3 405B is a large-scale open-source language model enhanced through reinforcement learning.

self-adaptive-llms — A real-time adaptive framework for unseen tasks using large language models.

Language Learning Games — AI text adventure games for language learning

FP6-LLM — Efficiently serving large language models

Eureka — A human-level reward design algorithm implemented by encoding large language models.

RL4VLM — An open-source project that fine-tunes large vision-language models via reinforcement learning to act as decision-making agents.

BiTA — Bidirectional Adjustment for Large Language Models

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

CuMo — An advanced architecture for extending multimodal large language models (LLMs).

VSP-LLM — A framework that combines Visual Speech Processing with Large Language Models

DIAMOND — A reinforcement learning agent trained in a diffusion world model

LLM Maybe LongLM — Extends the context window of large language models

Language Atlas — Free language learning

Nemotron-4-340B-Reward — A multi-dimensional reward model to help build custom large language models.

Prompt Engineering Guide — A comprehensive guide to prompt engineering for large language models

Level-Navi Agent-Search — Level-Navi Agent is a ready-to-use framework that utilizes large language models for in-depth query understanding and precise search.

DataBonsai — A Python library for data cleaning and organization using Large Language Models (LLMs).

Benchmarking API Performance of Large Language Models — In-depth analysis of key metrics like TTFT and TPS

EAGLE — Exploration of the design space for multimodal large language models

Sonus-1 — Sonus-1: A New Era of Large Language Models (LLMs)

Open LLM Leaderboard — A publicly accessible leaderboard of large language models.

Brainglue — Brainglue is an interesting experimental platform for large language models

Language REACTOR — A powerful language learning toolkit

GEO Services