6 citations · 12 across the 9 of their papers we have counts for
10 papers
Pretrained Image-Text Models are Secretly Video Captioners
Chunhui Zhang, Yiren Jian, Zhongyu Ouyang +1
Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these seq…
Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
Yiren Jian, Tingkai Liu, Yunzhe Tao +3
In this paper, we introduce , a streamlined framework designed for the pre-training of visually conditioned language generation models with high computatio…
Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
Yiren Jian, Chongyang Gao, Soroush Vosoughi
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current para…
Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task
Yiren Jian, Chongyang Gao, Chen Zeng +2
RNA, whose functionality is largely determined by its structure, plays an important role in many biological activities. The prediction of pairwise structural proximity between each…
Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings
Yiren Jian, Chongyang Gao, Soroush Vosoughi
Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encod…
Contrastive Learning for Prompt-Based Few-Shot Language Learners
Yiren Jian, Chongyang Gao, Soroush Vosoughi
The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. F…
Embedding Hallucination for Few-Shot Language Fine-tuning
Yiren Jian, Chongyang Gao, Soroush Vosoughi
Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language mo…
Label Hallucination for Few-Shot Classification
Yiren Jian, Lorenzo Torresani
Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such…
MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting
Yiren Jian, Chongyang Gao
Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data. To alleviate the data scarcity problem presented in the real…
Direct Information Reweighted by Contact Templates: Improved RNA Contact Prediction by Combining Structural Features
Yiren Jian, Chen Zeng, Yunjie Zhao
It is acknowledged that co-evolutionary nucleotide-nucleotide interactions are essential for RNA structures and functions. Currently, direct coupling analysis (DCA) infers nucleoti…