728 citations · 1.3k across the 24 of their papers we have counts for
27 papers
DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
Moulik Choraria, Xinbo Wu, Akhil Bhimaraju +5
Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning a…
Semantically Grounded QFormer for Efficient Vision Language Understanding
Moulik Choraria, Xinbo Wu, Sourya Basu +5
General purpose Vision Language Models (VLMs) have received tremendous interest in recent years, owing to their ability to learn rich vision-language correlations as well as their…
FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory
Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal +5
Multi-turn textual feedback-based fashion image retrieval focuses on a real-world setting, where users can iteratively provide information to refine retrieval results until they fi…
Avoiding spurious correlations via logit correction
Sheng Liu, Xu Zhang, Nitesh Sekhar +3
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labe…
An interpretation of Union-Find Decoder on Weighted Graphs
Yue Wu, Namitha Liyanage, Lin Zhong
Union-Find (UF) and Minimum-Weight Perfect Matching (MWPM) are popular decoder designs for surface codes. The former has significantly lower time complexity than the latter but is…
Random Walk-based Community Key-members Search over Large Graphs
Yuxiang Wang, Yuyang Zhao, Xiaoliang Xu +3
Given a graph , a query node , and an integer , community search (CS) seeks a cohesive subgraph (measured by community models such as -core or -truss) from that…