8 papers
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…
Holo-World: Unified Camera, Object and Weather Control for Video World Model
Xiangchen Yin, Wenzhang Sun, Jiahui Yuan +6
Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls r…
Current World Models Lack a Persistent State Core
Jinpeng Lu, Dexu Zhu, Haoyuan Shi +8
World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on d…
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Jiaoyang Ruan, Xin Gao, Yinda Chen +5
While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces…
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…
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
Haoyuan Shi, Xiancong Ren, Yingji Zhang +9
Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VLA-Trace, a progressive diagnostic…
MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models
Zheyuan Zhou, Liang Du, Zixun Sun +5
Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds a…
FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
Jiayi Han, Liang Du, Yinda Chen +3
The Mixture of Experts (MoE) paradigm has been successfully integrated into Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning (PEFT), delivering performance gains with…