16 papers
RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers
Jian Tang, Jiawei Fan, Qiannan Zhou +3
Diffusion Transformers (DiTs) have become the standard backbone for high-quality generative modeling, yet deploying them in conditional generation tasks remains computationally pro…
SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion
Pihai Sun, Gang Han, Jingkai Sun +17
Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We pres…
Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling
Shaokang Wang, Jinchang Xu, Peidong Jia +9
Most existing video compression algorithms follow a paradigm of transformation and quantization, optimizing the trade-off between distortion and bitrate. However, extremely low-bit…
Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
Zeyuan Ding, Wenhai Liu, Yang Xu +6
In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action prediction within a single archit…
WAM4D: Fast 4D World Action Model via Spatial Register Tokens
Ying Li, Xiaobao Wei, Jiajun Cao +10
World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video o…
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
Yi Zhang, Yinda Chen, Che Liu +26
We present Pelican-Unify 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unify 1.0 uses a single VLM as a unified understanding…
PriorZero: Bridging Language Priors and World Models for Decision Making
Junyu Xiong, Yuan Pu, Jia Tang +1
Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general intelligence. However, a fu…
FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
Jian Tang, Jiawei Fan, Qingbin Liu +3
While the overall inference latency of Video Diffusion Transformers (DiTs) can be substantially reduced through model distillation, per-step inference latency remains a critical bo…
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
Hao Wang, Xiaobao Wei, Jingyang He +10
Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image d…
PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control
Haozhuo Zhang, Michele Caprio, Jing Shao +4
We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations int…
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes
Haozhuo Zhang, Jingkai Sun, Michele Caprio +5
Physics-based human motion control can make a simulated character walk, sit, and manipulate objects with high physical realism. Almost always, though, this happens in short, isolat…
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
Wei Cui, Haoyu Wang, Wenkang Qin +19
Humanoid robot technology is advancing rapidly, with manufacturers introducing diverse heterogeneous visual perception modules tailored to specific scenarios. Among various percept…
Occupancy World Model for Robots
Zhang Zhang, Qiang Zhang, Wei Cui +12
Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajec…
RoboOcc: Enhancing the Geometric and Semantic Scene Understanding for Robots
Zhang Zhang, Qiang Zhang, Wei Cui +7
3D occupancy prediction enables the robots to obtain spatial fine-grained geometry and semantics of the surrounding scene, and has become an essential task for embodied perception.…
EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
Yi Zhang, Qiang Zhang, Xiaozhu Ju +13
While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex l…
HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
Qiang Zhang, Zhang Zhang, Wei Cui +13
The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We…