1 citations · 2 across the 7 of their papers we have counts for
7 papers
ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation
Xinyi Wang, Heng Hao, Wenjun Hu +5
Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, reconstruction errors can cau…
Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
Zhuoping Zhou, Davoud Ataee Tarzanagh, Sima Didari +7
Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling…
PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning
Heng Hao, Wenjun Hu, Oxana Verkholyak +6
Text-to-SQL models allow users to interact with a database more easily by generating executable SQL statements from natural-language questions. Despite recent successes on simpler…
Bayesian Active Learning for Semantic Segmentation
Sima Didari, Wenjun Hu, Jae Oh Woo +3
Fully supervised training of semantic segmentation models is costly and challenging because each pixel within an image needs to be labeled. Therefore, the sparse pixel-level annota…
Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
JoonHo Lee, Jae Oh Woo, Juree Seok +11
Assessing response quality to instructions in language models is vital but challenging due to the complexity of human language across different contexts. This complexity often resu…
Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation
Ayaan Haque, Hankyu Moon, Heng Hao +3
3D deep learning is a growing field of interest due to the vast amount of information stored in 3D formats. Triangular meshes are an efficient representation for irregular, non-uni…
PatchNet: Unsupervised Object Discovery based on Patch Embedding
Hankyu Moon, Heng Hao, Sima Didari +2
We demonstrate that frequently appearing objects can be discovered by training randomly sampled patches from a small number of images (100 to 200) by self-supervision. Key to this…