Multimodal models / Neural Networks and Deep Learning

VideoJev: Open Model Answers Questions About Video as Accurately as Thinking Mode, but 100 Times Faster

14 October 2026

Кадр из видео, по которому VideoJev отвечает на вопросы: в вафли добавляют шоколад, вид сверху на стол с завтраком

VideoJev: Open Model Answers Questions About Video as Accurately as Thinking Mode, but 100 Times Faster

Researchers from Nanjing University, JD.com, and six other Chinese universities introduced VideoJev, a family of models for video question answering. They answer about 100 times faster than models in Thinking…

LLaVA-OneVision-2: Multimodal Model Analyzes Compressed Video Stream Through a Codec Instead of Frame Sampling

28 May 2026

LLaVA-OneVision-2: Multimodal Model Analyzes Compressed Video Stream Through a Codec Instead of Frame Sampling

Researchers from Glint Lab, AIM for Health Lab, and MVP Lab published LLaVA-OneVision-2 (LLaVA-OV-2) — a next-generation multimodal model that rethinks how a neural network “watches” video. Instead of slicing…

SenseNova-U1: NEO-unify multimodal architecture works directly with pixels without VAE

14 May 2026

SenseNova-U1: NEO-unify multimodal architecture works directly with pixels without VAE

SenseNova introduced a new multimodal architecture, SenseNova-U1, which combines image understanding, generation, and editing inside a single transformer without a separate visual encoder or variational autoencoder. This approach removes the…

DeepEyesV2: Multimodal Model Learns to Use Tools to Solve Complex TasksRetry

12 November 2025

DeepEyesV2: Multimodal Model Learns to Use Tools to Solve Complex TasksRetry

Researchers from Xiaohongshu introduced DeepEyesV2 — an agentic multimodal model based on Qwen2.5-VL-7B that can not only understand text and images but also actively use external tools: execute Python code…

Hybrid Image Tokenizer: Apple’s New Approach to Multimodal Models

22 September 2025

Hybrid Image Tokenizer: Apple’s New Approach to Multimodal Models

Apple Research Team introduced Manzano — a unified multimodal large language model that combines visual content understanding and generation capabilities through a hybrid image tokenizer and carefully designed training strategy.…

Mini-o3: A Multimodal 7B Model Outperformed GPT-4o in Visual Search With 30-Step Reasoning Chains

10 September 2025

Mini-o3: A Multimodal 7B Model Outperformed GPT-4o in Visual Search With 30-Step Reasoning Chains

Researchers from ByteDance and the University of Hong Kong introduced Mini-o3 — a multimodal model that performs deep multi-step reasoning to solve complex visual search tasks. Mini-o3 achieves SOTA results…

Show-o2: Open-source 7B multimodal model outperforms 14B models on benchmarks using significantly less training data

11 July 2025

Show-o2: Open-source 7B multimodal model outperforms 14B models on benchmarks using significantly less training data

Researchers from Show Lab at the National University of Singapore and ByteDance introduced Show-o2 — a second-generation multimodal model that demonstrates superior results in image and video understanding and generation…

Visual-ARFT: Multimodal AI Agents Outperform GPT-4o by 18.6% in Complex Visual Tasks

22 May 2025

Visual-ARFT: Multimodal AI Agents Outperform GPT-4o by 18.6% in Complex Visual Tasks

A research team from Shanghai Jiao Tong University and Shanghai Artificial Intelligence Laboratory has introduced Visual Agentic Reinforcement Fine-Tuning (Visual-ARFT) — a new approach to training large multimodal models with…

Molmo: Open Source Multimodal Vision-Language Models Outperform Gemini 1.5 and Claude 3.5

26 September 2024

Molmo: Open Source Multimodal Vision-Language Models Outperform Gemini 1.5 and Claude 3.5

Molmo is a new series of multimodal vision-language models (VLMs) created by researchers at the Allen Institute for AI and the University of Washington. The Molmo family outperforms many state-of-the-art…