Kimi K2.5 Makes Agent Work 4.5x Faster : Matching Top Models in Vision & Code

Kimi K2.5 handles up to 100 sub-agents and 1,500 tool calls, cutting task time 4.5x so you finish complex work sooner.
IEEE

IntelliRMS: A Robotic Manipulation System for Domain-Specific Tasks Using Vision and Language Foundational Models

Abstract: Recent advancements in large language models (LLMs) have significantly enhanced machines' ability to understand and follow human instructions. In many tasks, LLMs have demonstrated ...
IEEE

On the Zero-shot Adversarial Robustness of Vision-Language Models: A Truly Zero-shot and Training-free Approach

Abstract: Pre-trained Vision-Language Models (VLMs) like CLIP, have demonstrated strong zero-shot generalization capabilities. Despite their effectiveness on various downstream tasks, they remain ...