6 citations · 11 across the 26 of their papers we have counts for
28 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…
SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
Ruihua Han, Rui Gao, Zhe Liu +6
Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneous robots, sparse workspaces, s…
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Runhui Huang, Qihui Zhang, Zhe Liu +3
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. I…
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
Brain Team, Ziyang Gong, Haoming Gu +28
Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, act through robot bodies, monitor progress, and improve f…
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
Junwei Luo, Shuai Yuan, Zhenya Yang +3
Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions. In this paper, we view this t…
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Xirui Li, Zhe Liu, Xiaoqing Ye +4
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action voca…
SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
Zheng Zhang, Lihe Yang, Tianyu Yang +6
We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods…
IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarking
Ruihua Han, Shuai Wang, Chengyang Li +8
Developing navigation policies requires simulation scenarios that support repeatable training and evaluation. Despite the availability of numerous simulators, constructing diverse…
Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention
Siyu Wu, Linjing You, Junjie Zhu +9
World Action Models (WAMs) jointly predict future visual observations and actions, but visual futures alone often miss slip, jamming, contact-direction changes, and subtle misalign…
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Runhui Huang, Jie Wu, Rui Yang +2
In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal…
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…
Continuous Latent Diffusion Language Model
Hongcan Guo, Qinyu Zhao, Yian Zhao +8
Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing…
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Xin Zhou, Dingkang Liang, Xiwu Chen +4
Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene gen…
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…
DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
Zhe Liu, Runhui Huang, Rui Yang +6
Although multi-modal large language models (MLLMs) have shown strong capabilities across diverse domains, their application in generating fine-grained 3D perception and prediction…
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…
Visual Spatial Tuning
Rui Yang, Ziyu Zhu, Yanwei Li +9
Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Visi…
UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs
Zhe Liu, Jinghua Hou, Xiaoqing Ye +3
Although transformers have demonstrated remarkable capabilities across various domains, their quadratic attention mechanisms introduce significant computational overhead when proce…
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
Xin Zhou, Dingkang Liang, Kaijin Chen +7
Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, prima…
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
Runhui Huang, Chunwei Wang, Junwei Yang +8
We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation. Existing unified…
HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
Rui Yang, Lin Song, Yicheng Xiao +4
Recent advancements in large language models (LLMs) have significantly propelled the development of large multi-modal models (LMMs), highlighting the potential for general and inte…
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Xin Zhou, Dingkang Liang, Sifan Tu +6
Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to inc…
Liquid: Language Models are Scalable and Unified Multi-modal Generators
Junfeng Wu, Yi Jiang, Chuofan Ma +5
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these…