2 citations · 3 across the 14 of their papers we have counts for
16 papers
PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training
Mingyu Liu, Chonghao Sima, Tianjian Feng +4
A vision--language--action (VLA) policy can complete complex tasks while ignoring the evidence that should determine its actions. An object held near the wrist camera can displace…
Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments
Mingyu Liu, Zeju Li, Jiuhe Shu +4
Expert demonstrations are widely assumed to be the gold standard for robot imitation learning. Yet for fine-grained manipulation such as insertion, stacking, and alignment, we unco…
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
Yiduo Jia, Muzhi Zhu, Hao Zhong +7
To extend the reinforcement learning post-training paradigm to omni-modal models for concurrently bolstering video-audio understanding and collaborative reasoning, we propose OmniJ…
StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
Mingyu Liu, Jiuhe Shu, Hui Chen +6
A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing meth…
GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
Mingyu Liu, Zheng Huang, Xiaoyi Lin +6
Vision-language models demonstrate strong reasoning and planning abilities, yet grounding these predictions into precise robot actions remains a central challenge. Existing Vision-…
NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
Zheng Huang, Mingyu Liu, Xiaoyi Lin +9
Vision-Language-Action (VLA) models represent a pivotal advance in embodied intelligence, yet they confront critical barriers to real-world deployment, most notably catastrophic fo…
Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning
Haozhe Zhang, Chenchen Jing, Mingyu Liu +2
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \textit{i.e.}, attributes and objects…
ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Kaijun Wang, Liqin Lu, Mingyu Liu +7
Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamen…
Generative Video Matting
Yongtao Ge, Kangyang Xie, Guangkai Xu +6
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and fo…
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
Hao Zhong, Muzhi Zhu, Zongze Du +6
Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution fra…
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
Muzhi Zhu, Hao Zhong, Canyu Zhao +9
Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of effic…
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
Cong Chen, Mingyu Liu, Chenchen Jing +5
This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we id…
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Canyu Zhao, Yanlong Sun, Mingyu Liu +6
This paper's primary objective is to develop a robust generalist perception model capable of addressing multiple tasks under constraints of computational resources and limited trai…
MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation
Weijia Wu, Mingyu Liu, Zeyu Zhu +6
Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with g…
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
Canyu Zhao, Mingyu Liu, Wen Wang +5
Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narrati…
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Guangkai Xu, Yongtao Ge, Mingyu Liu +5
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent…