Video analysis

Models 16

• Research previewGen 3
  ACT 2

  By Sunday

  ACT 2 is a robotics foundation model developed by Sunday Robotics for autonomous home manipulation. Pretrained on a large, high quality sensorized human demonstration dataset, it generalizes learned behaviors to unseen home environments with minimal additional data. In evaluation it achieved a 99.1% zero shot success rate folding diverse garments across unfamiliar rooms, surfaces, and starting configurations, with no per home data collection or fine tuning required.

  🤖Robotics🤖Task automation🔍Image recognition🎥Video analysis🏠Home automation
  NewMultimodal

  Released 9d ago
• Gen 3
  MOSS VL Realtime

  By OpenMOSS

  MOSS-VL-Realtime is an 11B parameter vision language model built for continuous video streams. It perceives incoming frames and generates text in parallel, answers questions asked at any point in the stream, and can stay silent or revise earlier answers as new visual evidence arrives. It uses a cross attention architecture with timestamp aware frame encoding and a 256K context window.

  🎥Video analysis📷Images🎥Videos🔍Image analysis🔍Visual analysis
  NewMultimodal

  Released 12d ago
• Gen 3
  Muse Spark 1.1

  By Meta Platforms

  Muse Spark 1.1 is a multimodal reasoning model built for agentic tasks, with strengths in tool use, computer use, coding, and multimodal understanding. It manages a 1 million token context window and orchestrates multi-agent systems for complex, long-running projects.

  💬Chatting🎥Video analysis💻Coding🤖Agents🔍Image analysis
  NewMultimodal

  Released 17d ago
• Gen 4 LingBot
  LingBot Vision Giant

  By Robbyant

  LingBot-Vision-Giant is a ViT-g/16 self-supervised Vision Transformer backbone for dense visual perception. Pretrained with masked boundary modeling, a boundary-centric objective that produces spatially structured patch features while retaining strong semantic representations, intended for feature extraction and dense prediction research.

  🔍Image analysis🔍Image recognition🖼️Image segmentation🎥Video analysis👁️Computer vision assistance
  NewImage

  Released 20d ago
• AnnouncementGen 3
  Orca (BAAI)

  By Beijing Academy of Artificial Intelligence (BAAI)

  Orca is a world foundation model that learns a unified latent world state from multimodal signals to predict future states, rather than predicting next tokens, frames, or actions directly. It uses unconscious learning from continuous video and conscious learning from language described events to model physically consistent state transitions, which are read out through language, vision, and action interfaces.

  🎥Video analysis🔍Research🔍Image analysis🤖Robotics
  NewMultimodal

  Released 27d ago
• Gen 3
  MolmoMotion 4B H1 F32

  By Ai2

  4B vision-language model that forecasts 3D point trajectories from a single RGB observation frame, 2D query points, and a natural-language action instruction. Built on Molmo 2, it predicts where surface points on objects will move in 3D camera-frame space (in meters) over 32 future timesteps. Best used when only one observation keyframe is available.

  🖌️3D🎥Video analysis🤖Robotics🏃Motion capture
  NewMultimodal

  Released 1mo ago
• Gen 3 Step
  Step 3.7 Flash

  By StepFun

  StepFun's flagship multimodal reasoning model, a 198B total parameter sparse MoE with 11B active parameters. Natively understands images and video, supports adjustable reasoning effort, and is optimized for agent and coding workflows with reliable tool calling.

  💬Chatting🤖Task automation🎥Video analysis💻Coding🤖Agents🔍Image analysis
  NewMultimodal

  Released 1mo ago
• Gen 3
  Marlin 2B

  By NemoStation

  Marlin-2B is NemoStation’s open-source 2B video-language model for dense video captioning and natural-language temporal grounding.

  🎥Video analysis🔍Video search📝Video captions
  NewMultimodal

  Released 2mo ago
• Gen 3
  Perceptron Mk1

  By Perceptron AI

  Perceptron Mk1 is Perceptron’s closed-source vision-language model for video understanding, image reasoning, and embodied reasoning tasks.

  🎥Video analysis👀Video surveillance🧩Spatial intelligence🤖Robotics
  NewMultimodal

  Released 2mo ago
• Gen 3
  MiniCPM V4.6.

  By OpenBMB

  MiniCPM-V-4.6 is OpenBMB’s open-source lightweight multimodal model for efficient image, multi-image, and video understanding on mobile and edge devices.

  💬Chatting🎥Video analysis🔍Image interpretation📜OCR
  NewMultimodal

  Released 2mo ago
• Gen 3 Nemotron
  Nemotron 3 Nano Omni

  By NVIDIA

  Nemotron 3 Nano Omni is NVIDIA’s open multimodal reasoning model for agentic systems. It unifies text, image, video, and audio in a single efficient 30B-A3B hybrid MoE model, built to replace fragmented vision-language-audio stacks with one shared perception-and-context model for multimodal agents.

  🔍Image interpretation🎥Video analysis🤖Agents🗒Transcription📄Document analysis🤔Logical reasoning
  NewMultimodal

  Released 2mo ago
• Gen 3
  Brainiac

  By Nate Lorenzen

  Brainiac is an open-source neuroscience-based visual-content analysis tool for thumbnails, landing pages, and videos. It uses fMRI encoding models to predict how the human brain responds to visual media, then turns those activation patterns into actionable design feedback, channel-specific thumbnail analysis, and timestamped video editing recommendations.

  🔍Visual analysis🎥Video analysis🧠Neuroscience📷YouTube thumbnail optimization
  Multimodal

  Released 3mo ago
• Gen 3
  AURA

  By Huawei

  AURA is a real-time multimodal streaming system for continuous video understanding with speech interaction. It is built as an always-on assistant over live video streams and is released as an Apache 2.0 project built on top of Qwen3-VL-8B-Instruct.

  🎥Video analysis🔍Image interpretation
  Multimodal

  Released 3mo ago
• Gen 3 GLM
  GLM 4.6V FlashX

  By Z.ai

  Multimodal LLM with a 128K token context window accepting image, video, text, and file inputs with text output. The paid tier of the GLM-4.6V-Flash series offering higher capacity and stability. First visual model to natively integrate Function Call capability, enabling direct multimodal tool use without intermediate text conversion.

  📝Text generation🎥Video analysis🔍Image analysis
  Multimodal

  Released 7mo ago
• Gen 3
  FlowRVS

  By xmz111

  FlowRVS is a referring video object segmentation method that learns a text-conditioned continuous flow to deform a video’s spatiotemporal representation into the target object mask.

  🖼️Image segmentation🔍Image recognition🎥Video analysis👁️Computer vision assistance
  Multimodal

  Released 9mo ago
• Gen 4
  DINOv3

  By Meta Platforms

  DINOv3 is a self supervised computer vision model from Meta that produces universal image backbones without using human labeled data. Trained up to 7 billion parameters on 1.7 billion images, it generates high resolution dense visual features that power tasks like object detection, image segmentation, depth estimation and video object tracking without any finetuning.

  🔍Image analysis🔍Image recognition🖼️Image segmentation🎥Video analysis
  Image

  Released 11mo ago