4 papers · 1 filter
DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
Shuyang Jiang, Nan Yu, Yiming Zhang +2
Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched in-batch pairs, and…
CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models
Yiming Zhang, Zhuokai Zhao, Chengzhang Yu +8
Autoregressive large vision--language models (LVLMs) interface video and language by projecting video features into the LLM's embedding space as continuous visual token embeddings.…
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen +3
Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains c…
RankCLIP: Ranking-Consistent Language-Image Pretraining
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen +3
Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-on…