11 citations · 20 across the 34 of their papers we have counts for
39 papers
MixVLA: Adaptive Mixing of Non-Invariant Information for Generalizable Vision-Language-Action Models
Pingrui Zhang, Yu Zhang, Pengyuan Wu +8
Vision-Language-Action (VLA) models have achieved remarkable advances in robotic manipulation, yet their zero-shot generalization under out-of-distribution (OOD) conditions remains…
WOLF: World Model Guided LiDAR Exploration with Predictive Frontiers
Yuyang Tian, Penghui Yang, Pengyuan Wu +7
LiDAR-based unmanned aerial vehicle (UAV) exploration builds maps by continually selecting where to observe next. However, decisions based on the measured map provide limited fores…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
Xianqiang Gao, Qizhi Chen, Delin Qu +5
Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language…
RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting
Yucheng Xin, Jiacheng Bao, Yubo Dong +5
Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting remains particularly challengin…
Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot
Yucheng Xin, Jiacheng Bao, Haoran Yang +6
The integration of imitation and reinforcement learning has enabled remarkable advances in humanoid whole-body control, facilitating diverse human-like behaviors. However, research…
Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy
Pengyuan Wu, Pingrui Zhang, Zhigang Wang +3
Diffusion-based policies have achieved remarkable results in robotic manipulation but often struggle to adapt rapidly in dynamic scenarios, leading to delayed responses or task fai…
PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking
Jiacheng Bao, Haoran Yang, Yucheng Xin +7
Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captu…
ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data
Haoran Yang, Jiacheng Bao, Yucheng Xin +5
Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperati…
Understanding Degradation with Vision Language Model
Guanzhou Lan, Chenyi Liao, Yuqi Yang +5
Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often…
Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
Pingrui Zhang, Yifei Su, Pengyuan Wu +7
Vision-and-Language Navigation (VLN) requires the agent to navigate by following natural instructions under partial observability, making it difficult to align perception with lang…
Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation
Yuanqi Yao, Siao Liu, Haoming Song +7
Building a lifelong robot that can effectively leverage prior knowledge for continuous skill acquisition remains significantly challenging. Despite the success of experience replay…
Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy
Guanzhou Lan, Yuqi Yang, Anup Teejo Mathew +5
Goal-conditioned dynamic manipulation is inherently challenging due to complex system dynamics and stringent task constraints, particularly in deformable object scenarios character…
Hume: Introducing System-2 Thinking in Visual-Language-Action Model
Haoming Song, Delin Qu, Yuanqi Yao +9
Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancem…
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
Junli Liu, Qizhi Chen, Zhigang Wang +6
Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual groundin…
MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation
Pingrui Zhang, Xianqiang Gao, Yuhan Wu +6
In mobile manipulation, navigation and manipulation are often treated as separate problems, resulting in a significant gap between merely approaching an object and engaging with it…
Exploring the Potential of Encoder-free Architectures in 3D LMMs
Yiwen Tang, Zoey Guo, Zhuhao Wang +8
Encoder-free architectures have been preliminarily explored in the 2D Large Multimodal Models (LMMs), yet it remains an open question whether they can be effectively applied to 3D…
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Delin Qu, Haoming Song, Qizhi Chen +8
In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundati…
Night-to-Day Translation via Illumination Degradation Disentanglement
Guanzhou Lan, Yuqi Yang, Zhigang Wang +3
Night-to-Day translation (Night2Day) aims to achieve day-like vision for nighttime scenes. However, processing night images with complex degradations remains a significant challeng…
Open-Vocabulary Octree-Graph for 3D Scene Understanding
Zhigang Wang, Yifei Su, Chenhui Li +4
Open-vocabulary 3D scene understanding is indispensable for embodied agents. Recent works leverage pretrained vision-language models (VLMs) for object segmentation and project them…
Efficient Diffusion as Low Light Enhancer
Guanzhou Lan, Qianli Ma, Yuqi Yang +4
The computational burden of the iterative sampling process remains a major challenge in diffusion-based Low-Light Image Enhancement (LLIE). Current acceleration methods, whether tr…
Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation
Yunpeng Gao, Zhigang Wang, Pengfei Han +3
Aerial Vision-and-Language Navigation (VLN) is a novel task enabling Unmanned Aerial Vehicles (UAVs) to navigate in outdoor environments through natural language instructions and v…
FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset
Zhaxizhuoma, Kehui Liu, Chuyue Guan +15
Real-world manipulation data involving robotic arms is crucial for developing generalist action policies, yet such data remains scarce since existing data collection methods are hi…
COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models
Kehui Liu, Zixin Tang, Dong Wang +3
Leveraging the powerful reasoning capabilities of large language models (LLMs), recent LLM-based robot task planning methods yield promising results. However, they mainly focus on…