11 papers
SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations
Jun Guo, Xiaoshen Han, Qiwei Li +7
World action models (WAMs) are large embodied policies that jointly predict future video and the actions to execute, emitting a fixed-length action chunk per inference call. Such a…
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…
Extending Embodied Question Answering from Perception to Decision
Xicheng Gong, Qiwei Li, Peiran Xu +1
Embodied Question Answering (EQA) connects perception, reasoning, and interaction within embodied environments. However, existing datasets and benchmarks remain fragmented, each fo…
RotVLA: Rotational Latent Action for Vision-Language-Action Model
Qiwei Li, Xicheng Gong, Xinghang Li +5
Latent Action Models (LAMs) have emerged as an effective paradigm for handling heterogeneous datasets during Vision-Language-Action (VLA) model pretraining, offering a unified acti…
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
Jun Guo, Qiwei Li, Peiyan Li +7
We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, a…
ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation
Hongyu Yan, Qiwei Li, Jiaolong Yang +1
Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitati…
DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation
Kunming Shao, Zhipeng Liao, Jiangnan Yu +9
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval but faces challenges on edge devices due to high storage, ene…
Faster MoE LLM Inference for Extremely Large Models
Haoqi Yang, Luohe Shi, Qiwei Li +5
Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE mode…
CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental Learning
Qiwei Li, Jiahuan Zhou
Recently, prompt tuning methods for pre-trained models have demonstrated promising performance in Class Incremental Learning (CIL). These methods typically involve learning task-sp…
Hypergraph based Understanding for Document Semantic Entity Recognition
Qiwei Li, Zuchao Li, Ping Wang +2
Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relatio…
Enhancing Visually-Rich Document Understanding via Layout Structure Modeling
Qiwei Li, Zuchao Li, Xiantao Cai +2
In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly f…