16 citations · 38 across the 16 of their papers we have counts for
19 papers
From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models
Feiran Wang, Xiaoqi Wang, Ziwei Li +3
Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language models (VLMs) and benchmarks for…
From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models
Ziwei Li, Yi-Tang Chen, Xiaoqi Wang +3
Large-scale vectorized HD maps provide structured road information that is essential for perception, localization, and planning in autonomous driving. Constructing such maps requir…
Scaling Expert Feedback with Reflective Edit Propagation in Compositional Knowledge Bases
Jiajing Guo, Xueming Li, Jorge Piazentin Ono +2
Domain-specific knowledge bases (KBs) encode vertical expertise and proprietary information that organizations depend on, but curating them at scale is a persistent challenge. Alth…
Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks
Jiajing Guo, Kenil Patel, Jorge Piazentin Ono +2
Large language models (LLMs) are increasingly powering Text-to-SQL (Text2SQL) systems, enabling non-expert users to query industrial databases using natural language. While test-ti…
ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads
Yifan Li, Xin Li, Tianqin Li +3
Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leverag…
VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels
Xiwei Xuan, Xiaoqi Wang, Wenbin He +4
The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging do…
ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts
Xiaoqi Wang, Clint Sebastian, Wenbin He +1
The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among…
DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models
Chenbin Pan, Wenbin He, Zhengzhong Tu +1
The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based…
InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions
Juntong Chen, Jiang Wu, Jiajing Guo +6
The rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting…
InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillation
Jinbin Huang, Wenbin He, Liang Gou +2
The emergence of large-scale pre-trained models has heightened their application in various downstream tasks, yet deployment is a challenge in environments with limited computation…
USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation
Xiaoqi Wang, Wenbin He, Xiwei Xuan +8
The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recen…
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
Thang Doan, Sima Behpour, Xin Li +3
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting. The rise of Visi…
InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates
Jinbin Huang, Wenbin He, Liang Gou +2
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while inc…
GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
Sima Behpour, Thang Doan, Xin Li +3
Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approach…
UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
Xin Li, Sima Behpour, Thang Doan +3
In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing perfor…
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
Thang Doan, Xin Li, Sima Behpour +3
Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown…
CLIP-S: Language-Guided Self-Supervised Semantic Segmentation
Wenbin He, Suphanut Jamonnak, Liang Gou +1
Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S that leverages self-supervi…
Self-supervised Semantic Segmentation Grounded in Visual Concepts
Wenbin He, William Surmeier, Arvind Kumar Shekar +2
Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for i…
FTK: A Simplicial Spacetime Meshing Framework for Robust and Scalable Feature Tracking
Hanqi Guo, David Lenz, Jiayi Xu +7
We present the Feature Tracking Kit (FTK), a framework that simplifies, scales, and delivers various feature-tracking algorithms for scientific data. The key of FTK is our high-dim…