Tag: multimodal LLMs
Browse our exclusive articles!
Q-Zoom: Efficient Query-Aware Perception for MLLMs
Discover Q-Zoom, a query-aware adaptive framework boosting efficiency and accuracy in multimodal large language models for high-res visual tasks.
HybridKV: Efficient KV Cache Compression for Multimodal LLMs
HybridKV compresses KV caches to boost multimodal LLM inference, reducing memory by 7.9x and speeding decoding by 1.5x without losing accuracy.
Experience Transfer for Multimodal LLM Agents in Minecraft
Discover how Echo framework boosts multimodal LLM agents' efficiency in Minecraft by enabling experience transfer and faster task completion.
Predicting Learner-Video Interaction with Multimodal LLMs
Discover scalable, explainable models using multimodal large language models to predict learner interactions in educational videos.
FeynmanBench: Benchmarking AI on Physics Diagram Reasoning
FeynmanBench evaluates multimodal LLMs on complex diagrammatic physics tasks, testing AI's reasoning with Feynman diagrams and scientific notation.