VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions Paper • 2603.23495 • Published 4 days ago • 3
iiiorg/piiranha-v1-detect-personal-information Token Classification • Updated Nov 1, 2025 • 29k • 235
Running 3.75k The Ultra-Scale Playbook 🌌 3.75k The ultimate guide to training LLM on large GPU Clusters
CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs Paper • 2408.10433 • Published Aug 19, 2024