"Our general idea here has been to map and model the visual system in a systematic, unbiased way, in principle even using images that a person normally wouldn't encounter," Dr. Kuceyeski said.

"Our new model extends this principle to higher-order visual processing in bees, revealing how behaviorally driven scanning creates compressed, learnable neural codes.

Named LLava-CoT, the new model outperforms its base model and proves better than larger models, including Gemini-1.5-pro, GPT-4o-mini, and Llama-3.2-90B-Vision-Instruct, on a number of benchmarks.

Anthropic launches Claude 3.5 Sonnet to raise bar for model intelligence in coding and visual processing - SiliconANGLESiliconANGLE Media is a recognized leader in digital media innovation serving ...

Object knowledge representation in the human visual cortex requires a connection with the language system. PLOS Biology, 2025; 23 (5): e3003161 DOI: 10.1371/journal.pbio.3003161 ...

The second new model, Phi-4-multimodal, is an upgraded version of Phi-4-mini that can also process visual and audio input. Microsoft says that both models significantly outperform comparably sized ...