11 papers
Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models
Rui Zhu, Song-Lin Lv, Zi-Kang Wang +1
Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios…
LoopViT: Scaling Visual ARC with Looped Transformers
Wen-Jie Shu, Xuerui Qiu, Rui-Jie Zhu +3
Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational de…
RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
Pengcheng Jiang, Lang Cao, Ruike Zhu +5
Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of…
UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
Yuanxin Liu, Rui Zhu, Shuhuai Ren +4
With the rapid growth of video generative models (VGMs), it is essential to develop reliable and comprehensive automatic metrics for AI-generated videos (AIGVs). Existing methods e…
Unified Personalized Understanding, Generating and Editing
Yu Zhong, Tianwei Lin, Ruike Zhu +9
Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-…
Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models
Song-Lin Lv, Rui Zhu, Tong Wei +2
Semi-supervised learning (SSL) alleviates the cost of data labeling process by exploiting unlabeled data and has achieved promising results. Meanwhile, with the development of larg…