VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions Paper • 2603.23495 • Published Mar 24 • 3
iiiorg/piiranha-v1-detect-personal-information Token Classification • 0.3B • Updated Nov 1, 2025 • 155k • • 249
Running 4.07k The Ultra-Scale Playbook 🌌 4.07k 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
Running on CPU Upgrade Agents 1.03k Open VLM Leaderboard 🌎 1.03k VLMEvalKit Evaluation Results Collection