17 citations · 53 across the 29 of their papers we have counts for
33 papers
Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface
Zhizhen Zhang, Yuxia Fu, Zijian Wang +2
Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by training each task independent…
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
Bowen Yuan, Zijian Wang, Yadan Luo +2
Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from…
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
Shijie Wang, Zijian Wang, Yadan Luo +3
Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic ye…
MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation
Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3
A central challenge in mobile manipulation is preserving multiple plausible action modes while remaining reactive during execution. For example, grasping a bottle in a cluttered sc…
Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data
Shijie Wang, Yadan Luo, Zijian Wang +3
This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration N…
Language-driven Fine-grained Retrieval
Shijie Wang, Xin Yu, Yadan Luo +3
Existing fine-grained image retrieval (FGIR) methods learn discriminative embeddings by adopting semantically sparse one-hot labels derived from category names as supervision. Whil…
Distributed Zero-Shot Learning for Visual Recognition
Zhi Chen, Yadan Luo, Zi Huang +3
In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering…
Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
Hossein Askari, Yadan Luo, Hongfu Sun +1
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to da…
MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent
Yuxia Fu, Zhizhen Zhang, Yuqi Zhang +3
Recent Vision-Language-Action (VLA) models reformulate vision-language models by tuning them with millions of robotic demonstrations. While they perform well when fine-tuned for a…
OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
Zhuoxiao Chen, Hongyang Yu, Ying Xu +3
Radiology report generation (RRG) aims to automatically produce clinically faithful reports from chest X-ray images. Prevailing work typically follows a scale-driven paradigm, by m…
Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving
Djamahl Etchegaray, Yuxia Fu, Zi Huang +1
Interpretable communication is essential for safe and trustworthy autonomous driving, yet current vision-language models (VLMs) often operate under idealized assumptions and strugg…
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
Huitong Yang, Zhuoxiao Chen, Fengyi Zhang +2
Maintaining robust 3D perception under dynamic and unpredictable test-time conditions remains a critical challenge for autonomous driving systems. Existing test-time adaptation (TT…
Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning
Bizhe Bai, Jianjian Cao, Yadan Luo +1
Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding obj…
SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization
Bowen Yuan, Yuxia Fu, Zijian Wang +2
Dataset Condensation (DC) aims to obtain a condensed dataset that allows models trained on the condensed dataset to achieve performance comparable to those trained on the full data…
Color-Oriented Redundancy Reduction in Dataset Distillation
Bowen Yuan, Zijian Wang, Mahsa Baktashmotlagh +2
Dataset Distillation (DD) is designed to generate condensed representations of extensive image datasets, enhancing training efficiency. Despite recent advances, there remains consi…
Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs
Jia Syuen Lim, Yadan Luo, Zhi Chen +3
In the Detection and Multi-Object Tracking of Sweet Peppers Challenge, we present Track Any Peppers (TAP) - a weakly supervised ensemble technique for sweet peppers tracking. TAP l…
Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation
Zixin Wang, Dong Gong, Sen Wang +2
Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Te…
CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction
Zhi Chen, Tianqi Wei, Zecheng Zhao +6
In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting. This paper addresses the challenge…
FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuning
Zhi Chen, Zecheng Zhao, Yadan Luo +1
Conventional Text-guided single-image editing approaches require a two-step process, including fine-tuning the target text embedding for over 1K iterations and the generative model…
DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection
Zhuoxiao Chen, Zixin Wang, Yadan Luo +2
LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when…
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
Jia Syuen Lim, Zhuoxiao Chen, Mahsa Baktashmotlagh +4
Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discover…
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Zhuoxiao Chen, Junjie Meng, Mahsa Baktashmotlagh +3
LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies…
Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
Djamahl Etchegaray, Zi Huang, Tatsuya Harada +1
In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with a…
Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
Yiyun Zhang, Zijian Wang, Yadan Luo +2
Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their application…