12 citations · 25 across the 19 of their papers we have counts for
20 papers
Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
Pengzhan Sun, Shiu-hong Kao, Shijie Li +4
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human in…
TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation
Hengyan Liu, Wenlve Zhou, Bo Yue +7
Reactive vision-language-action (VLA) policies suffer from task-state aliasing in long-horizon manipulation, where identical multimodal inputs call for distinct, context-dependent…
Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
Huayi Zhou, Wei Gao, Dekun Lu +12
End-to-end manipulation policies, combined with web-scale pretrained Vision-Language Models (VLMs), show the promise for generalizable and dexterous robotic manipulation. However,…
Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization
Yan Huang, Yongyi Su, Xin Lin +2
The emergence of foundation models has substantially advanced zero-shot generalization in monocular depth estimation (MDE), as exemplified by the Depth Anything series. However, gi…
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Yongyi Su, Haojie Zhang, Shijie Li +11
Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as genera…
AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
Jingyi Liao, Yongyi Su, Rong-Cheng Tu +6
While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrain…
SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
Adam Goodge, Xun Xu, Bryan Hooi +4
As point cloud data increases in prevalence in a variety of applications, the ability to detect out-of-distribution (OOD) point cloud objects becomes critical for ensuring model sa…
Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift
Jingyi Liao, Xun Xu, Yongyi Su +4
Anomaly detection plays a crucial role in quality control for industrial applications. However, ensuring robustness under unseen domain shifts such as lighting variations or sensor…
Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
Yushu Li, Yongyi Su, Adam Goodge +2
Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data eff…
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
Yongyi Su, Yushu Li, Nanqing Liu +4
Test-time adaptation (TTA) updates the model weights during the inference stage using testing data to enhance generalization. However, this practice exposes TTA to adversarial risk…
PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images
Nanqing Liu, Xun Xu, Yongyi Su +2
Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap betwe…
Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection
Yushu Li, Yongyi Su, Xulei Yang +2
Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annot…
CLIP-Guided Source-Free Object Detection in Aerial Images
Nanqing Liu, Xun Xu, Yongyi Su +3
Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather…
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
Haojie Zhang, Yongyi Su, Xun Xu +1
The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prom…
Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
Yongyi Su, Xun Xu, Kui Jia
Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions. However, these attempts may f…
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
Yushu Li, Xun Xu, Yongyi Su +1
Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches of…
STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
Yijin Chen, Xun Xu, Yongyi Su +1
Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain…
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training
Yongyi Su, Xun Xu, Tianrui Li +1
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenar…
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
Yongyi Su, Xun Xu, Kui Jia
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenar…
Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
Yongyi Su, Xun Xu, Kui Jia
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold an…