6 papers
Long-Horizon Visual Imitation Learning via Plan and Code Reflection
Quan Chen, Chenrui Shi, Qi Chen +6
Learning from long-horizon demonstrations with complex action sequences presents significant challenges for visual imitation learning, particularly in understanding temporal relati…
Ideal Registration? Segmentation is All You Need
Xiang Chen, Fengting Zhang, Qinghao Liu +4
Deep learning has revolutionized image registration by its ability to handle diverse tasks while achieving significant speed advantages over conventional approaches. Current approa…
GneissWeb: Preparing High Quality Data for LLMs at Scale
Hajar Emami Gohari, Swanand Ravindra Kadhe, Syed Yousaf Shah +29
Data quantity and quality play a vital role in determining the performance of Large Language Models (LLMs). High-quality data, in particular, can significantly boost the LLM's abil…
Region-based Cluster Discrimination for Visual Representation Learning
Yin Xie, Kaicheng Yang, Xiang An +9
Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved…
Towards Efficient Quantity Retrieval from Text:An Approach via Description Parsing and Weak Supervision
Yixuan Cao, Zhengrong Chen, Chengxuan Xia +2
Quantitative facts are continually generated by companies and governments, supporting data-driven decision-making. While common facts are structured, many long-tail quantitative fa…
Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
Kun Wu
As deep learning models scale, their training cost has surged significantly. Due to both hardware advancements and limitations in current software stacks, the need for data efficie…