activity
20242026
most citedDesigning Large Foundation Models for Efficient Training and Inference: A Survey

5 citations · 5 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

Haoyu Huang, Jinfa Huang, Zhongwei Wan +3

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. How…