arxiv:2512.16561
Boqiang Zhang
Cyril666
AI & ML interests
Multi-modal
Large Language Models
Vision-Language-Action Models
Recent Activity
authored
a paper
about 18 hours ago
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video
Understanding authored
a paper
about 18 hours ago
What Is a Good Caption? A Comprehensive Visual Caption Benchmark for
Evaluating Both Correctness and Thoroughness authored
a paper
about 18 hours ago
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and
Open Resources Organizations
models 6
Cyril666/av_model_v3
3B • Updated
Cyril666/whisper-large-v3-encoder
Automatic Speech Recognition • 0.6B • Updated
• 35
Cyril666/Qwen2-Audio-Encoder
0.6B • Updated
• 4
Cyril666/SFL-Encoder-Pretrained-Qwen3
Text Generation • 0.4B • Updated
• 94
Cyril666/exp003-softvq-l-64
Updated
• 1
Cyril666/exp002-softvq-l-64
Updated
• 1
datasets 0
None public yet