AI Briefing#multimodal-llm
The latest AI and developer news about #multimodal-llm, with the original source and a short summary.
The latest AI and developer news about #multimodal-llm, with the original source and a short summary.
Kakao developed Kanana-v-4b-hybrid, a hybrid multimodal language model that generates answers through a thinking process.
Kakao has released the lightweight multimodal language model 'Kanana-1.5-v-3b' as open source for commercial use, achieving superior performance compared to competing models on Korean benchmarks.
Qwen has released Qwen2.5-VL-32B-Instruct, an open-source multimodal model at 32B scale optimized for performance through reinforcement learning.
A new dataset called Big Bench Audio, designed to evaluate the reasoning capabilities of audio language models, has been released.
With an average score of 75.1 on Korean benchmarks, surpassing GPT-4o (61.9), the model adopts Native resolution and the C-Abstractor architecture.
CinePile 2.0, a video QA dataset with improved performance through adversarial refinement techniques, has been released.
Qwen's next-generation audio model, **Qwen2-Audio**, has been released, supporting both voice and text input.