9 papers
Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
Qihang Ma, Shengyu Li, Jie Tang +5
Multi-modal keyphrase prediction (MMKP) aims to advance beyond text-only methods by incorporating multiple modalities of input information to produce a set of conclusive phrases. T…
Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User Profiling
Yingxin Li, Jianbo Zhao, Xueyu Ren +8
User profiling, as a core technique for user understanding, aims to infer structural attributes from user information. Large Language Models (LLMs) provide a promising avenue for u…
Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modeling
Haoran Li, Zhiming Su, Junyan Yao +6
Synthetic data is widely adopted in embedding models to ensure diversity in training data distributions across dimensions such as difficulty, length, and language. However, existin…
SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement
Weijie Yin, Dingkang Yang, Hongyuan Dong +5
Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most Vi…
ContentV: Efficient Training of Video Generation Models with Limited Compute
Wenfeng Lin, Renjie Chen, Boyuan Liu +10
Recent advances in video generation demand increasingly efficient training recipes to mitigate escalating computational costs. In this report, we present ContentV, an 8B-parameter…
AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
Hongyuan Dong, Dingkang Yang, Xiao Liang +2
Learning rate is widely regarded as crucial for effective foundation model pretraining. Recent research explores and demonstrates the transferability of learning rate configuration…