2 citations · 6 across the 20 of their papers we have counts for
22 papers
VeriVLA: Adaptive Test-Time Verification for Flow-Based VLAs with Latent World Models
Xueli Sun, Yuxiang Lu, Yantong Liu +4
Flow-based Vision-Language-Action (VLA) policies are inherently stochastic: different noise seeds can produce action chunks of varying quality from the same observation. At test ti…
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Zhe Liu, Jinghua Hou, Yuxiang Lu +7
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting…
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Kaixin Ding, Xi Chen, Minghong Cai +9
Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consistency and action controllabi…
DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
Xianzhe Fan, Yuxiang Lu, Shenyuan Gao +4
Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly escalate into irrecoverable fai…
Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System
Yifei Wei, Linqing Zhong, Yi Liu +4
Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into executable physical actions. How…
HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labeling
Mei Li, Huayi Zhou, Suizhi Huang +3
Regressing 3D rotations of objects from 2D images is a crucial yet challenging task, with broad applications in autonomous driving, virtual reality, and robotic control. Existing r…
FASTER: Rethinking Real-Time Flow VLAs
Yuxiang Lu, Zhe Liu, Xianzhe Fan +5
Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smooth…
Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
Xianzhe Fan, Shengliang Deng, Xiaoyang Wu +7
Existing Vision-Language-Action (VLA) models typically take 2D images as visual input, which limits their spatial understanding in complex scenes. How can we incorporate 3D informa…
GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
Zhenya Yang, Zhe Liu, Yuxiang Lu +6
Physics-aware driving world model is essential for drive planning, out-of-distribution data synthesis, and closed-loop evaluation. However, existing methods often rely on a single…
MORE: Multi-Organ Medical Image REconstruction Dataset
Shaokai Wu, Yapan Guo, Yanbiao Ji +6
CT reconstruction provides radiologists with images for diagnosis and treatment, yet current deep learning methods are typically limited to specific anatomies and datasets, hinderi…
Is Diversity All You Need for Scalable Robotic Manipulation?
Modi Shi, Li Chen, Jin Chen +7
Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robo…
BECAME: BayEsian Continual Learning with Adaptive Model MErging
Mei Li, Yuxiang Lu, Qinyan Dai +3
Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledg…
AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
AgiBot World Contributors, AgiBot-World-Contributors, Qingwen Bu +50
We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 millio…
Discretized Gaussian Representation for Tomographic Reconstruction
Shaokai Wu, Yuxiang Lu, Yapan Guo +9
Computed Tomography (CT) enables detailed cross-sectional imaging but continues to face challenges in balancing reconstruction quality and computational efficiency. While deep lear…
Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
Yuxiang Lu, Shengcao Cao, Yu-Xiong Wang
Vision Foundation Models (VFMs) have demonstrated outstanding performance on numerous downstream tasks. However, due to their inherent representation biases originating from differ…
Towards Personalized Federated Multi-Scenario Multi-Task Recommendation
Yue Ding, Yanbiao Ji, Xun Cai +7
In modern recommender systems, especially in e-commerce, predicting multiple targets such as click-through rate (CTR) and post-view conversion rate (CTCVR) is common. Multi-task re…
Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
Weihao Jiang, Zhaozhi Xie, Yuxiang Lu +6
Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting repre…
Task Indicating Transformer for Task-conditional Dense Predictions
Yuxiang Lu, Shalayiding Sirejiding, Bayram Bayramli +3
The task-conditional model is a distinctive stream for efficient multi-task learning. Existing works encounter a critical limitation in learning task-agnostic and task-specific rep…
YOLO-MED : Multi-Task Interaction Network for Biomedical Images
Suizhi Huang, Shalayiding Sirejiding, Yuxiang Lu +4
Object detection and semantic segmentation are pivotal components in biomedical image analysis. Current single-task networks exhibit promising outcomes in both detection and segmen…
Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
Yuwen Yang, Yuxiang Lu, Suizhi Huang +3
The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model traini…
FedHCA: Towards Hetero-Client Federated Multi-Task Learning
Yuxiang Lu, Suizhi Huang, Yuwen Yang +3
Federated Learning (FL) enables joint training across distributed clients using their local data privately. Federated Multi-Task Learning (FMTL) builds on FL to handle multiple tas…
Prompt Guided Transformer for Multi-Task Dense Prediction
Yuxiang Lu, Shalayiding Sirejiding, Yue Ding +2
Task-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods. How to trade off performan…