11 papers
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
Xiaomi Robotics Team, Jun Guo, Piaopiao Jin +31
We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulatio…
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Xinghang Li, Jun Guo, Qiwei Li +21
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements f…
Towards One-to-Many Temporal Grounding
Qi Xu, Yue Tan, Shihao Chen +5
Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, ho…
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
Yueyi Sun, Yuhao Wang, Jason Li +8
Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limi…
AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy
Zhifeng Wang, Jason Jingshi Li, Kaihao Zhang +1
Large language models (LLMs) demonstrate strong performance in natural language processing but often generate factual errors when relying solely on parametric knowledge. Retrieval-…
Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
Junjie Wang, Xinghua Lou, Jason Li +8
Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm…
Threshold-Guided Optimization for Visual Generative Models
Jinbin Bai, Yu Lei, Qingyu Shi +6
Aligning large visual generative models with human feedback is often performed through pairwise preference optimization. While such approaches are conceptually simple, they fundame…
Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation
Xinshun Wang, Peiming Li, Ziyi Wang +5
Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms…
UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing
Lichen Ma, Xiaolong Fu, Gaojing Zhou +6
With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to ful…
RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning
Zipeng Guo, Lichen Ma, Xiaolong Fu +13
In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional…
Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
Xiaolong Fu, Lichen Ma, Zipeng Guo +9
The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these ga…