AI tools for Research

KIVA by Wellows is an advanced SEO automation platform engineered to streamline keyword research, content optimization, and performance tracking for startups, SMEs, agencies, an

Citely serves as an essential tool for serious researchers dedicated to maintaining the highest standards of academic integrity. This platform is specifically engineered to rigo

Virlo establishes itself as the definitive authority in the short-form video landscape, functioning as the world's most comprehensive data aggregator for platforms like TikTok,

SafeNew is designed to bridge the gap between machine-generated text and authentic human expression. It specializes in transforming raw output from content generators into fluid

RelayVSR performs 4x super-resolution on real-world video. It uses a large generative model selectively to recover detail and a smaller network for the rest of the sequence.

This Qwen3.5-0.8B checkpoint is the released result of a weight-space programming experiment. The authors tasked an external language model with modifying the smaller model's te

Hydrogen-1.0 is Deep Principle's language model for scientific problem solving. It is built on GLM-5.3 and targets tasks such as explaining derivations, organizing research ques

STRATA is NVIDIA's global atmospheric emulator for research on storm-resolving simulation. It learns to predict the evolving three-dimensional atmospheric state represented by t

ReLift reconstructs dense 3D point trajectories from a monocular video. It combines the output of a 2D tracker with a video geometry estimator to recover how points move in spac

GPT-6 Cyber is OpenAI's restricted model for authorized security research and defense. It can assist with investigating vulnerabilities, reproducing findings in approved test en

CoLa3D reconstructs an object-composed 3D scene from a single image. It outputs individual meshes that share a coordinate frame so the resulting objects can be inspected and man

Hyra Results is Tencent Hunyuan's repository of released scientific models and reproducible research artifacts. Its model directories provide usable packages and checkpoints for

SenseNova 6.8 Flash is SenseTime's multimodal agent model for office work and content creation. It supports tasks that span several steps or sessions and can deliver outputs suc

Xiaomi-Robotics-1 is a vision-language-action foundation model for mobile manipulation. Xiaomi trained the model on more than 100,000 hours of real-world manipulation trajectori

ToolSpace is a research toolkit for turning tool-use traces into executable training and evaluation environments. It focuses on long-horizon agent tasks that require several sta

FlowHMR reconstructs 3D human motion from monocular video. It targets motion that can be tracked in a physics simulation and provides tools to preview the recovered sequence and

P-JiT 21K is Linum's released research checkpoint for text-to-image generation. The two-billion-parameter model was trained on 660 million samples to investigate what a smaller

PhysAg3D turns an object image into a detailed 3D asset with object-specific interactions. It combines generated appearance and geometry with reasoning about parts, joints, and

UniAction is a released framework for controlling a shared world model with different kinds of actions. It supports force, camera movement, hand pose, and robot pose through one

Genie 4 is Google DeepMind's interactive world-simulation model. It generates explorable environments with coordinated visual motion and native audio, aiming to let users move t

RoboSkills is an open collection of lightweight agent workflows and tools for robotics. It packages five working approaches: automated research, agent-as-policy control, agentic

MotionBricks generates controllable character and humanoid motion in real time. NVIDIA provides pretrained human and Unitree G1 models, a Python runtime, interactive demos, and

AutoSwarm coordinates existing AI agents into a shared working team. Instead of requiring one assistant to provide every capability, it connects compatible local agent tools, sh

Apex-35B-V1.0 is Apex Intelligence's open-weight model for general assistance and research-oriented agent work. It supports coding, question answering, search, and computational